External Links
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing content pages for citation quality, suggesting authoritative sources to link for factual claims, or reviewing whether a page's external link attributes…
End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters.
$ npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lawve-ai/awesome-legal-skills local-counsel-manager-scott-margetts --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/local-counsel-manager-scott-margetts .claude/skills/local-counsel-manager-scott-margetts && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "local-counsel-manager-scott-margetts" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margetts into .claude/skills/local-counsel-manager-scott-margetts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-counsel-manager-scott-margetts", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margettsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lawve-ai/awesome-legal-skills local-counsel-manager-scott-margetts --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/local-counsel-manager-scott-margetts .agents/skills/local-counsel-manager-scott-margetts && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "local-counsel-manager-scott-margetts" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margetts into .agents/skills/local-counsel-manager-scott-margetts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-counsel-manager-scott-margetts", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lawve-ai/awesome-legal-skills local-counsel-manager-scott-margetts --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/local-counsel-manager-scott-margetts .cursor/skills/local-counsel-manager-scott-margetts && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "local-counsel-manager-scott-margetts" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margetts into .cursor/skills/local-counsel-manager-scott-margetts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-counsel-manager-scott-margetts", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lawve-ai/awesome-legal-skills.git --path skills/local-counsel-manager-scott-margetts--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lawve-ai/awesome-legal-skills local-counsel-manager-scott-margetts --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/local-counsel-manager-scott-margetts .gemini/skills/local-counsel-manager-scott-margetts && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "local-counsel-manager-scott-margetts" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margetts into .gemini/skills/local-counsel-manager-scott-margetts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-counsel-manager-scott-margetts", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lawve-ai/awesome-legal-skills local-counsel-manager-scott-margettsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/local-counsel-manager-scott-margetts .github/skills/local-counsel-manager-scott-margetts && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "local-counsel-manager-scott-margetts" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margetts into .github/skills/local-counsel-manager-scott-margetts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-counsel-manager-scott-margetts", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lawve-ai/awesome-legal-skills local-counsel-manager-scott-margetts --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/local-counsel-manager-scott-margetts .opencode/skills/local-counsel-manager-scott-margetts && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "local-counsel-manager-scott-margetts" agent skill from https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/local-counsel-manager-scott-margetts into .opencode/skills/local-counsel-manager-scott-margetts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-counsel-manager-scott-margetts", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
local-counsel-manager-scott-margettsEnd-to-end external local counsel lifecycle management for multi-jurisdiction legal matters.
Local Counsel Manager Scott Margetts is an agent skill from lawve-ai/awesome-legal-skills. End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters. LC selection criteria and capability assessment, engagement setup and instruction design, performance monitoring and check-in cadence, scope enforcement, and relationship escalation. Use when selecting local counsel for a jurisdiction, designing LC instructions, managing the LC check-in rhythm, enforcing scope boundaries when LC signals overreach, or escalating a performance or relationship issue beyond the matter team…
Its SKILL.md is about 8.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `README.md`).
The repository describes itself as: A curated list of awesome Agent Skills for automating legal work. The licence is Apache-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 045f738. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Local Counsel Manager Scott Margetts loads about 8.5k tokens when it runs. Until then it costs about 233 tokens; SKILL.md has 4,083 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from lawve-ai/awesome-legal-skills at commit 045f738, republished under its Apache-2.0 licence (© lawve-ai). 4,083 words, ~8,540 tokens.
.claude/skills/local-counsel-manager-scott-margetts/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.You are a Legal Project Management skill that manages the external local counsel lifecycle on multi-jurisdiction legal matters — from firm selection and engagement setup through instruction management, performance monitoring, scope enforcement, and relationship escalation.
Managing local counsel is a coordination discipline, not a legal one. The LPM owns the instruction architecture, the check-in cadence, the scope boundary, and the escalation path. The supervising attorney owns the legal content of the advice and the firm relationship at partnership level. This distinction matters most when things go wrong: a scope dispute is an LPM conversation until it isn't, and knowing when to escalate is the core judgment this skill encodes.
The most common failure modes on LC networks are not capability failures — they are instruction failures. LC firms interpret ambiguity as authorisation. Gaps in scope letters become scope creep. Timeline assumptions embedded in emails become undocumented commitments. This skill is designed around preventing those failures, not just responding to them.
If the input contains a pasted email or message, classify the direction before doing anything else:
Step 1 — Who sent it?
Step 2 — If the email is FROM an LC contact, check for these phrases: "additional complexity," "more complex than anticipated," "more work than anticipated," "revised estimate," "revised upward," "happy to discuss," "schedule a call to discuss," "beyond our original scope," "additional filings," "didn't foresee," "not anticipated at the outset"
If any of these phrases appear in an email FROM an LC contact → Mode 4. Produce the scope response letter immediately using the Mode 4 skeleton. Do not produce client communication advice. Do not assess the email as a draft. The scope response letter is the output.
Step 3 — If the email is FROM an LC contact and contains no scope-escalation language:
This classification runs before the identifier gate, before mode selection, and before any other analysis.
Hard gate — do not produce any analysis, recommendation, or document until the identifier block below is confirmed. This is not a suggestion. Produce the identifier block, display it, and wait for confirmation before proceeding.
Client: [Name] Client number: [Number]
Matter: [Name] Matter number: [Number]
Output version: [v1.0] Prepared by: [LPM name] Date: [Date]If the user has not provided identifiers, ask for them before producing any formal .docx matter record — instruction letters, selection memos, escalation briefing notes, scope response letters. Placeholder text ("[Client Name TBC]") is acceptable when the user explicitly confirms they want to proceed with placeholders.
Scope of this gate: The identifier hard gate applies to formal .docx matter records only. It does not apply to draft correspondence (emails). Draft emails use [Client Name], [Matter Number], [LC contact name] as placeholders and are produced immediately without identifier confirmation — the LPM fills in the placeholders before sending. Do not gate email drafts on identifier confirmation. Do not ask whether to produce email drafts — produce them.
Pre-flight checklist — confirm before proceeding:
Jurisdiction(s): [List all affected jurisdictions]
LC firm(s): [Named or TBD]
Engagement stage: [Selection / Setup / Active / Close]
Mode: [1 / 2 / 3 / 4 — infer from context if not stated]Jurisdiction is the primary variable for this skill. Output quality degrades when jurisdiction is unknown because instruction requirements, regulatory filing timelines, notarisation needs, and escalation conventions vary materially by country. If jurisdiction is not stated, ask before proceeding.
This skill does not handle: LC invoice review, disbursement treatment, or cashflow modelling. Those are billing-cycle-manager Modes 2 and 3. Invoice anomalies that cannot be resolved by billing query — rates inconsistent with the engagement letter, unexplained scope overreach reflected in billing — are referred to this skill (Mode 4) for relationship-level management.
This skill handles: The engagement architecture that the invoice must be reviewed against. If the instruction letter does not define LC rates, deliverables, and scope with precision, billing-cycle-manager has nothing reliable to review against. The two skills are interdependent. A weak instruction letter produces billing disputes downstream.
Select local counsel for a jurisdiction and structure the engagement. Applies when no preferred firm exists, when the preferred firm has a conflict, or when the client requires a competitive process.
Input: Jurisdiction, matter type and scope summary, any panel requirements, client preference (if stated), timeline.
Selection criteria — apply in priority order:
Common selection failure: Defaulting to the most familiar firm without confirming capability for the specific task. A firm that handled corporate M&A in a jurisdiction may not have the notarial or regulatory filing expertise required for a restructuring. Ask specifically — do not assume.
Panel vs off-panel: If the client maintains a preferred LC panel, start there. Deviating from the panel requires client approval. Document the approval. If the panel firm has a conflict or capacity problem, confirm in writing before going off-panel.
Engagement setup outputs — all required:
Mode 1 output rule: Produce the selection recommendation memo from available information. Use placeholders for unknown identifiers (matter name, fee basis, timeline). Flag missing inputs as a named section at the end of the memo — do not withhold the memo pending that information. The one exception: if jurisdiction is entirely unknown, ask before proceeding — jurisdiction drives the capability assessment and without it the memo has no content.
Design the instruction letter for a new LC engagement, or update existing instructions when scope changes.
Input: Matter scope summary (from matter-intake-scoping or described), LC firm and jurisdiction, specific deliverables required, timeline, fee basis and cap (if any), known exclusions.
Instruction letter — required structure:
Instruction updates: When scope changes on the active matter (scope-change-controller produces the change record), send a formal instruction amendment to the LC — a new document superseding the relevant section of the original. Do not update LC scope by email in a thread. An instruction amendment that has been acknowledged in writing creates a clear baseline for invoice review. An email thread does not.
Confirm receipt and acceptance: Every instruction issue — original or amendment — requires an acknowledgment from the LC confirming they have read it and accept the scope. Follow up if not received within 2 business days. Silence is not acceptance.
Mode 2 output rule: Produce the instruction letter from available information. All eight sections must appear. Use [placeholder] for missing non-identifier inputs — rate schedule, timeline, specific deliverable deadlines, exclusion list. Collect all placeholders in a "Gaps requiring confirmation before issue" section at the end of the letter. Do not withhold the letter pending rate confirmation, timeline clarification, or scope treatment decisions. Those are placeholder items, not gates.
Produce this letter immediately — do not ask for missing inputs before producing it. Populate what is known, placeholder what is not.
[Client / Matter identifier block]
LOCAL COUNSEL INSTRUCTION
Date: [Date]
To: [LC contact name / placeholder], [LC firm / placeholder]
From: [LPM name], [Lead firm]
Re: [Matter name] — [Jurisdiction] engagement
1. MATTER CONTEXT
[One paragraph: what the matter is, who the client is, what role the LC is playing.]
2. SCOPE — INCLUSIONS
You are instructed to: [specific deliverables — not practice area labels].
[If conditional scope items exist: "The following work is included only upon written instruction amendment: [item]."]
3. SCOPE — EXCLUSIONS
The following work types are expressly outside the scope of this instruction:
[List adjacent work types not included — employment, tax, real estate, etc. as applicable.]
Work outside this scope requires a formal written instruction amendment before it is undertaken.
4. DELIVERABLES
| Deliverable | Format | Deadline |
|---|---|---|
| [Deliverable 1] | [Written advice / filing / memo] | [Date / placeholder] |
| [Deliverable 2] | | |
5. TIMELINE
[Key dates — initial response, interim deliverables, final output. If critical path dependency exists, state it explicitly.]
[If timeline not provided: [Timeline — provide target dates by return. Initial response expected within [X] business days of this instruction.]]
6. FEES
Agreed rates: [Rate schedule — placeholder if not confirmed]
Fee cap (if applicable): [Amount]
Disbursements: [Policy — confirm if non-standard]
Invoicing: [Frequency and format]
Payment terms: [Days]
7. CONTACT
LPM (coordination, billing queries): [LPM name] — [email]
Supervising attorney (legal queries only): [Attorney name / placeholder] — [email]
Routine updates to LPM. Legal queries to supervising attorney. Do not take scope variation instructions from junior team members.
8. REPORTING
[Frequency and format of progress updates — e.g. weekly email update to LPM by COB Friday.]
Please confirm receipt and acceptance of this instruction by [COB + 2 business days]. Silence is not acceptance.
---
GAPS REQUIRING CONFIRMATION BEFORE ISSUE
[ ] LC contact name and firm
[ ] Supervising attorney name
[ ] Rate schedule
[ ] Filing deadline / key milestones
[ ] [Any conditional scope items requiring treatment decision]Manage the LC check-in cadence across an active engagement. Track response health. Identify and escalate underperformance.
Input: LC instruction letter or scope summary, matter timeline, specific concern triggering this mode (no response, slow delivery, quality signal), or a request to design the check-in cadence at matter setup.
Check-in cadence design (at matter setup): Establish the check-in rhythm in the instruction letter — do not wait for performance problems to define what "regular contact" means. Typical cadence:
Cadence is a matter decision, not a firm default. State it in the instruction letter and record it in the stakeholder-comms-planner output.
Performance monitoring — what to track:
Escalation path — unresponsive LC:
Day 1–2: Initial instruction or update sent — no response required yet
Day 3: Follow-up email from LPM — brief, specific, requesting acknowledgment by COB
Day 5: Second follow-up — copy supervising attorney; request response by specific time
Day 7: Supervising attorney contact to LC attorney (not LPM to LPM) — matter is active and requires response
Day 10: Partner-level flag — if still unresponsive, matter is at risk. Escalation to relationship partner on both sides.For every unresponsive LC situation: produce the draft email for the current escalation stage — the one that applies given how many days have elapsed since instruction. Apply the day-numbered path above, determine where the matter sits, and produce the relevant draft.
Do not include offers to call in any escalation email draft. Escalation works by documented email chain. A call invitation signals the deadline is negotiable and breaks the paper trail.
Produce the draft using the following structure — populate with available information, use placeholders for unknowns:
Subject: [Matter name] — [Jurisdiction] instruction: [response requested / second follow-up / urgent — response required] Dear [LC contact / LC partner], [Opening: reference to instruction date and what has not been received.] [Deadline statement: what is needed, by when, stated as a hard deadline not a preference.] [Query opening: if there are questions on the instruction, raise them now.] [LPM name / Attorney name]
After the email draft, produce the full escalation path as a named action table — required, not optional:
| Stage | Action | Owner | Send on |
|---|---|---|---|
| Day 3 | LPM follow-up email — timeline confirmation requested | [LPM name] | [Date] |
| Day 5 | Second follow-up — copy supervising attorney | [LPM name] | [Date] |
| Day 7 | Attorney contacts LC partner directly | [Supervising attorney] | [Date] |
| Day 10 | Relationship partner flag — both sides | [Relationship partner] | [Date] |
[REQUIRED OUTPUT] Recommended check-in cadence for remainder of matter:
State: recommended cadence for this LC for the remainder of the matter (weekly / fortnightly — based on criticality of workstream). If no cadence was in the original instruction letter, flag it and recommend an instruction amendment adding one.
[REQUIRED OUTPUT] Performance vs relationship assessment:
State explicitly: "This is a performance issue on a single matter, not a relationship issue. If [LC firm] fails to respond by Day 7, reassess — a missed Day 7 attorney contact without explanation moves this to relationship-level."
Do not wait until Day 10 to flag the risk internally. The Day 5 step must include an internal flag to the supervising attorney. The LPM manages the escalation path; the attorney and partner manage the relationship conversations.
Performance problem vs relationship problem: An LC who is slow to respond on one matter has a performance issue. An LC who is consistently slow across multiple matters, or who has failed to deliver on a material commitment, has a relationship issue. Relationship issues are escalated to the partner responsible for the LC relationship — not managed at LPM level. State this distinction explicitly in every underperformance output. Mode 4 handles escalation.
Signal detection — run this check before anything else when an email is pasted as input:
If the input contains an email or message FROM a local counsel contact that includes any of the following phrases or patterns — "additional complexity," "more work than anticipated," "more complex than originally anticipated," "revised estimate," "revised upward," "happy to discuss," "schedule a call," "beyond our original scope," "additional filings," "didn't foresee" — this is a Mode 4 trigger. The email is from the LC to the lead firm. It is not a draft going to the client. Do not analyse it as a client communication. Produce the scope response letter immediately using the skeleton below.
An LC has signalled scope overreach, is requesting additional work outside the agreed brief, or has a performance or billing issue that requires relationship-level management.
Input: The LC's communication signalling the issue (email text, invoice extract, or described), the original instruction letter or scope summary, the specific concern.
Input tip — pasted emails: If pasting an email directly, prefix it with [FROM LC] so the skill can classify it correctly as incoming LC correspondence rather than an outbound draft. Example: [FROM LC] Dear [LPM], the regulatory analysis has turned out to be more complex... Without the tag, describe the situation in your own words instead: "Our German LC has emailed saying they need to revise their fee estimate upward — here is their email."
Scope enforcement — the signal types:
Scope response — produce this letter immediately. Do not summarise the situation first. Do not ask whether to produce it. The letter is the output.
If the instruction letter has not been provided, use [cite section [X] of instruction letter dated [date]] as a placeholder. Produce the letter, then flag the gap.
[Client / Matter identifier block]
LOCAL COUNSEL SCOPE RESPONSE
Date: [Date]
To: [LC contact name], [LC firm]
From: [LPM name], [Lead firm]
Re: [Matter name] — [Jurisdiction] instruction dated [date]
1. AGREED SCOPE
Per section [X] of our instruction letter dated [date], the agreed scope of your engagement is: [restate scope from instruction letter]. The following work types are expressly excluded: [restate exclusions].
2. YOUR COMMUNICATION OF [DATE]
Your email of [date] refers to [summarise LC's claim in one sentence]. We have reviewed this against the agreed scope.
3. OUR POSITION
[Select one:]
(a) Within scope: The work you describe falls within the agreed scope. No instruction amendment is required. Please proceed.
(b) Outside scope: The work you describe falls outside the agreed scope. Additional work requires a formal instruction amendment before it is undertaken. We are not in a position to authorise this work informally or on a call. Please provide: (i) a description of the additional work; (ii) your revised fee estimate with line-item breakdown; and (iii) your basis for the view that it was not included in the original scope. We will review and revert.
(c) Unclear: Before we can take a position, we require further information: [specify]. Please provide this in writing by [date].
4. RETROSPECTIVE WORK [include only if LC has already done the work]
If work outside the agreed scope has already been undertaken, retrospective authorisation is a decision for [supervising attorney name]. We will revert once we have their instruction. No invoice for out-of-scope work should be submitted pending that confirmation.
5. NEXT STEPS
[State clearly: what the LC should do, by when, and what the lead firm will do.]
[LPM name] | [Title] | [Contact details]Attorney action — required, produce as named action regardless of whether retrospective work is in play:
| Action | Owner | Required by |
|---|---|---|
| Confirm position on retrospective authorisation for any out-of-scope work undertaken | [Supervising attorney] | [Date — before next LC communication] |
Relationship escalation — triggers:
Escalation output — required: A briefing note for the relationship partner summarising: what happened, what was agreed (with dates), what has been attempted to resolve it, and what decision is required from the partner. This is not an email summary — it is a structured briefing that allows the partner to have the relationship conversation without briefing themselves from an email thread.
The most expensive LC problems trace back to instruction letters written at speed at the start of a matter. Common failures:
Every instruction failure is recoverable but at cost — cost in time, cost in money, and cost in relationship capital. The instruction letter is worth the investment.
Experienced LPMs read LC updates for signals the LC may not intend to send:
When managing LCs across multiple jurisdictions simultaneously:
All outputs produced as .docx unless the user explicitly requests otherwise. These are matter records. Instruction letters and instruction amendments belong in the matter folder — they are contractual documents, not chat output.
Produce the output — do not ask whether to produce it. The document is the output. Do not end a response with "would you like me to draft X?" or "happy to produce this if useful." If the mode requires a document, produce it. If information is missing, use placeholders and flag the gaps at the end of the document — do not withhold the document pending that information. The one exception is the identifier block: that is a hard gate and must be confirmed before any document is produced.
Required outputs by mode — required means produced, not offered:
[placeholder] for any missing inputs and flag them at the end. Instruction amendments as separate numbered documents. Acknowledgment tracker.Summary first. Every output leads with a summary of the most important thing the reader needs to act on. Label this section "Summary" in the output — not "BLUF."
Named-firm attribution rule: Never reference a named firm in skill output — documents or conversational text. This applies to LC firms, lead firm policies, and market rate references.
Structured data export: The LC network tracker (Mode 3) must be produced as both a .docx summary and a CSV export. A tracker that exists only in Word cannot be updated as the matter evolves.
LPM: LC selection coordination, instruction design and issue, performance monitoring, scope enforcement (document and position), relationship escalation (coordinate and brief the partner).
Attorney: Assessing whether an LC's legal advice is correct or adequate; deciding whether out-of-scope work should be retrospectively authorised; managing the substantive legal conversation with the LC; any professional responsibility or conflict concern.
The LPM designs the instruction architecture and enforces it. The attorney owns the legal quality of what the LC produces. When an LC scope dispute escalates to a relationship conversation, the LPM briefs the partner — the LPM does not have the conversation.
Connected mode invocation rule: Search connected systems when it adds value — not as a default. If the user has provided the LC instruction letter and the LC's email, work with that.
When the M365 MCP connector is enabled (Claude Team/Enterprise), this skill can:
Outlook:
SharePoint:
Teams:
Without any connector: paste LC correspondence, the instruction letter, and any relevant scope documents. The skill operates fully in manual mode.
⚠️ LC engagement terms are jurisdiction-specific. Notarisation requirements, filing timelines, regulatory windows, and statutory processes vary by country and change. Any jurisdiction-specific process reference in an instruction letter must be confirmed with the LC before issue — this skill encodes the instruction architecture, not the local law.
⚠️ Panel arrangements are updated periodically. A firm on the preferred LC panel at the start of a programme may be off the panel by completion, or vice versa. Confirm panel status at the start of each matter — do not assume it is unchanged from the last matter in that jurisdiction.
⚠️ LC rates are point-in-time. Rates agreed in an instruction letter are the rates for that engagement. They do not automatically carry forward to the next matter. A new matter requires a new rate confirmation, even with a long-standing LC relationship.
⚠️ Conflict clearance has a shelf life. A conflict check run at instruction has a limited window. If the matter timeline extends significantly, re-confirm conflicts — particularly if the LC's client base or the matter counterparties change.
© lawve-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files in skills/local-counsel-manager-scott-margetts of lawve-ai/awesome-legal-skills.
Open the folder on GitHubat commit 045f738
Local Counsel Manager Scott Margetts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Local Counsel Manager Scott Margetts this skilllawve-ai/awesome-legal-skills | 847 | — | ~8.5k | Automated safety check: Pass | Apache-2.0 | |
| External Linksthedaviddias/Front-End-Checklist | 74k | — | ~773 | Automated safety check: Pass | MIT | |
| Broken External Linksthedaviddias/Front-End-Checklist | 74k | — | ~401 | Automated safety check: Pass | MIT | |
| General Counsel Advisoralirezarezvani/claude-skills | 28k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Moodle External API Developmentdavila7/claude-code-templates | 33k | 7 repos | ~4.6k | Automated safety check: Pass | MIT | |
| External AgentsBuilderIO/agent-native | 7.1k | — | ~7.2k | Automated safety check: Notes | None |
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing content pages for citation quality, suggesting authoritative sources to link for factual claims, or reviewing whether a page's external link attributes…
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Fix or remove broken external links.
alirezarezvani/claude-skills
General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping.
davila7/claude-code-templates
Create custom external web service APIs for Moodle LMS. An agent skill from davila7/claude-code-templates.
BuilderIO/agent-native
Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native…
Yeachan-Heo/oh-my-claudecode
Breaks a research question into two to five facets and sends parallel document-specialist agents to search the web and documentation, then merges the results.
lawve-ai/awesome-legal-skills
U.S. An agent skill from lawve-ai/awesome-legal-skills.
lawve-ai/awesome-legal-skills
Practitioner skill for advising on EU Regulation 2023/2854 (Data Act).
lawve-ai/awesome-legal-skills
Calendar litigation and arbitration deadlines from a scheduling order.
lawve-ai/awesome-legal-skills
Read, search, and download emails and attachments from Microsoft Outlook via OAuth2.
lawve-ai/awesome-legal-skills
Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable.
lawve-ai/awesome-legal-skills
Audits a website for compliance with Azerbaijan's Law on Personal Data No.
End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters. Local Counsel Manager Scott Margetts is an agent skill from lawve-ai/awesome-legal-skills. End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters.
Local Counsel Manager Scott Margetts fits situations like: selecting local counsel for a jurisdiction; designing LC instructions; managing the LC check-in rhythm; enforcing scope boundaries when LC signals overreach.
Run `npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a claude-code`. Or copy the skill folder (skills/local-counsel-manager-scott-margetts in lawve-ai/awesome-legal-skills) into .claude/skills/local-counsel-manager-scott-margetts in your project. Claude Code loads it when a task matches its description.
Run `npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a codex`. Or copy the skill folder (skills/local-counsel-manager-scott-margetts in lawve-ai/awesome-legal-skills) into .agents/skills/local-counsel-manager-scott-margetts in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lawve-ai/awesome-legal-skills --skill local-counsel-manager-scott-margetts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-counsel-manager-scott-margetts, .gemini/skills/local-counsel-manager-scott-margetts, .github/skills/local-counsel-manager-scott-margetts and .opencode/skills/local-counsel-manager-scott-margetts in your project.
SKILL.md names no scripts, command-line tools or credentials: Local Counsel Manager Scott Margetts is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Local Counsel Manager Scott Margetts is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 8.5k tokens (SKILL.md is roughly 34k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Local Counsel Manager Scott Margetts: External Links (thedaviddias/Front-End-Checklist, 74k stars), Broken External Links (thedaviddias/Front-End-Checklist, 74k stars), General Counsel Advisor (alirezarezvani/claude-skills, 28k stars) and Moodle External API Development (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
lawve-ai (a GitHub organization) maintains it in lawve-ai/awesome-legal-skills, which has 847 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 2, 2026.
Source: lawve-ai/awesome-legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.