Agent skill

Client Instruction Schedule

by lawve-ai in lawve-ai/awesome-legal-skills

Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note.

Apache-2.0Auto-check passedDocuments & Office

Install Client Instruction Schedule

skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill client-instruction-schedule -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lawve-ai/awesome-legal-skills client-instruction-schedule --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/client-instruction-schedule-serhan-handani-fx44146u .claude/skills/client-instruction-schedule && rm -rf skills-src

Use ~/.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/

Facts

Skill name
client-instruction-schedule
GitHub stars
847
Token cost
~3.3k tokens
SKILL.md length
1,753 words
Files
6 (incl. references)
Skills in repo
154
Repo updated
First seen
Licence
Apache-2.0

At a glance

Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note.

  • Works in 10 steps: Read everything, identify by content → Extract the disputed issues → Build a coverage map (source-to-row) → …
  • The user asks for a client instruction schedule
  • SKILL.md covers Purpose, Important limits, Jurisdiction and register and Workflow, plus 2 more sections
  • Runs JavaScript scripts from its folder

What it does

Client Instruction Schedule is an agent skill from lawve-ai/awesome-legal-skills. Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note. Use whenever the user asks for a "client instruction schedule", "instruction schedule", "client questionnaire", "schedule of questions for the client", "get instructions from the client on the papers", or says the client is overwhelmed and needs the case broken into manageable questions. Also trigger when asked to turn…

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `README.md`, `references/build-schedule-example.js` and `references/schedule-data-example.js`).

It sits in Documents & Office, covering Word documents and Plain language and style rules. It works with Microsoft Word. The repository describes itself as: A curated list of awesome Agent Skills for automating legal work. The licence is Apache-2.0.

When your agent uses it

  • The user asks for a client instruction schedule
  • Instruction schedule
  • Client questionnaire
  • Schedule of questions for the client

Example prompts

  • “client instruction schedule”
  • “instruction schedule”
  • “client questionnaire”
  • “/client-instruction-schedule”

Requirements

  • Node.js

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Read everything, identify by content
  2. Extract the disputed issues
  3. Build a coverage map (source-to-row)
  4. Cross-check against what is already held
  5. Build the schedule (.docx)
  6. Accuracy conventions
  7. Covering note (.docx, one page)
  8. Verify before delivering
  9. Save and name
  10. Report back

What it can do on your machine

Read from SKILL.md and the folder at commit 045f738. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships script files (JavaScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Client Instruction Schedule loads about 3.3k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 208 tokens; SKILL.md has 1,753 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~208
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.6k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from lawve-ai/awesome-legal-skills at commit 045f738, republished under its Apache-2.0 licence (© lawve-ai). 1,753 words, ~3,256 tokens.

Download SKILL.mdSave it as .claude/skills/client-instruction-schedule/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
client-instruction-schedule
description
Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note. Use whenever the user asks for a "client instruction schedule", "instruction schedule", "client questionnaire", "schedule of questions for the client", "get instructions from the client on the papers", or says the client is overwhelmed and needs the case broken into manageable questions. Also trigger when asked to turn case papers into a structured request for client input. Do NOT use for court-facing Scott Schedules, pleadings, witness statements, or advice letters — this skill produces a client-facing working document only. Output is always a .docx draft for solicitor review, never a final document.
license
Apache-2.0
metadata.author
Serhan Handani
metadata.jurisdiction
UK (England & Wales)
metadata.category
litigation
metadata.language
en

Client Instruction Schedule

Purpose

Clients in document-heavy disputes often freeze when asked open-endedly for "their comments". This skill produces a client instruction schedule: a landscape Word table borrowing the discipline of a Scott Schedule, but written to the client in plain English, with one row per disputed issue and specific, mostly closed questions. It is paired with a short covering note telling the client how to complete it. Positions are sourced precisely to statements, letters and exhibit pages, so that a court-facing Scott Schedule can later be drafted from it far more easily (the client's plain-English answers will still need to be turned into pleaded positions — the schedule is a quarry, not a conversion).

Important limits

This skill drafts a working document for a solicitor to review, amend and approve. It does not give legal advice, it must not be sent to a client without human review, and every draft it produces carries a banner saying so. The solicitor remains responsible for the accuracy of every position, reference and question in the schedule. Four further limits apply:

  • Confidentiality first. The skill reads an entire litigation folder, including counsel's advice. Before running it, check the firm's AI and confidentiality policy permits loading these papers into the tool in use, and anonymise or exclude material where policy requires.
  • Witness evidence (PD 57AC). The schedule uses mostly closed questions and shows the client the other side's position before asking for their recollection. If any answer may later feed a trial witness statement, the solicitor should consider Practice Direction 57AC before sending: putting the opponent's account to the client may be criticised as leading on important disputed matters. Consider generalising or removing the "other side's position" column for contested recollection issues, and keep a record of what documents the client was shown.
  • Client suitability. Confirm with the supervising solicitor that a written schedule suits this client. Some overwhelmed clients are vulnerable clients for whom this format is the wrong tool and a phone attendance is the right one.
  • Residual risk. The verification steps below reduce, but do not eliminate, the risk of hallucinated references, unfair paraphrase and silently omitted issues. The coverage map (step 3) exists so the reviewing solicitor can see what was left out, not only what went in.

Jurisdiction and register

English law (England & Wales). UK spelling. £ for currency. No CPR jargon or statutory citations in anything the client must read or complete — "the court's disclosure order", not "the Order of ICCJ [X] under CPR 3.1(7)". Document references (e.g. "Mr [X]'s 2nd statement, para 22") are fine: they are what makes later conversion to a Scott Schedule possible. Practitioners elsewhere can adapt the register, but the plain-English discipline is the point everywhere.

Workflow

1. Read everything, identify by content
  • Read every document in the case folder. Identify documents by their content, never by filename — filenames lie (exhibit bundles stamped with the wrong witness's initials, cover sheets certifying the wrong exhibit name). Content-based identification can also be wrong: record the basis for each identification in the report-back (step 10) so the solicitor can check it.
  • Note any document that is referenced in the papers but absent from the folder (a statement that mentions an exhibit not supplied, correspondence referring to an enclosure). List these in the report-back — the folder cannot be assumed complete.
  • Scanned PDFs with no text layer must be OCR'd (pdftoppm at 200dpi + tesseract, pages in parallel). Verify OCR'd figures and quotations against the page image before relying on them.
  • Hash files (md5sum) to find duplicates before reading.
  • Note every internal inconsistency found in the papers (dates, exhibit labels, misquoted figures) — these become highlighted solicitor notes (step 6), not silent corrections.
2. Extract the disputed issues

List every issue on which the client's input — an answer, a recollection, or a document — is actually needed. Sources: witness statements on both sides (paragraph by paragraph), counsel's advice (especially "we need instructions on…" passages), solicitors' letters to the client with unanswered requests, and the client's own partial responses. Exclude:

  • procedural and legal argument (no client input needed);
  • costs and strategy points;
  • anything already answered in the papers — but exclude only where a complete answer exists and can be cited; cite it in the exclusions list (step 3).

Decision points awaiting the client (e.g. "do you agree to instruct an accountant?") count as rows; broad strategy decisions belong in the covering note or a separate advice, not the schedule.

3. Build a coverage map (source-to-row)

The most dangerous failure of this workflow is a silently missed issue: the reviewing solicitor sees a polished table and has no way to see what was dropped. So, before drafting, produce a source-to-row map: every witness-statement paragraph raising a factual dispute, every "we need instructions on…" passage in counsel's advice, and every unanswered request in correspondence must appear as either (a) a schedule row, or (b) an entry in an "Issues considered and excluded" list with a one-line reason each. That exclusions list goes into the schedule document itself, as a solicitor-notes appendix after the table (same highlighting convention as step 6), not only into the chat report — the artefact under review must carry its own account of what it left out.

4. Cross-check against what is already held

For each issue, check whether the material about to be requested already exists in the folder. Never ask the client for a document the firm already holds — instead ask them to identify the relevant entries in it (e.g. "the bank statements are already with us (exhibit X) — point us to the matching entries"). The "Evidence we already hold" column is the enforcement mechanism: filling it honestly exposes any lazy request.

Show full SKILL.md (812 more words)Show less
5. Build the schedule (.docx)

Landscape A4, Times New Roman 12, generated with the docx npm package (tested with docx@9.6.1; see references/build-schedule-example.js for a complete working script). One table, header row repeating (tableHeader: true), native Word automatic numbering for issue numbers (a numbering config with LevelFormat.DECIMAL) — never typed digits. Key docx package points: set columnWidths on the table AND width on every cell, both in DXA; use ShadingType.CLEAR for shading (never SOLID); for landscape pass portrait A4 dimensions plus orientation: PageOrientation.LANDSCAPE. Eight columns (widths in DXA summing to ≤15398 for 0.5" margins):

#ColumnContent rules
1IssueAuto number + bold short label (3–8 words)
2Our position1–2 plain-English sentences
3The other side's positionEqually short, but sourced precisely: statement + paragraph, letter + date, exhibit + stamped page
4Evidence we already holdDocument references for everything relevant already on file
5What we need from youSpecific, concrete, mostly closed questions ("Did you attend the meeting on [date]? Who else was there?"). Never "please comment". Tell the client "cannot recall" is an acceptable answer
6Your responseBlank, generously sized
7Documents you are sendingBlank — the client lists enclosures per row
8PriorityHigh / Medium / Low, so the client can triage rather than freeze

Above the table: title, "Draft NN" line, one italic instruction line (High rows first), then any highlighted solicitor notes.

Priority guidance: High = goes to the core dispute, limitation-sensitive, or a decision blocking next steps. Medium = matters but can follow. Low = context or already well-documented.

6. Accuracy conventions
  • Where any position, date, amount or attribution is unclear from the papers: insert [UNCLEAR — PLEASE REVIEW] — never guess, never fabricate a fact, reference or quotation. Other flags: [DATE TBC], [AMOUNT TO BE CONFIRMED], [SOLICITOR TO VERIFY].
  • Inconsistencies in the source papers (conflicting statement dates, mislabelled exhibits) go in bold, yellow-highlighted paragraphs above the table, prefixed [SOLICITOR TO VERIFY — DELETE BEFORE SENDING TO CLIENT: …].
  • Every page carries a header banner: AI-ASSISTED DRAFT — FOR SOLICITOR REVIEW — NOT YET APPROVED OR SENT, and a footer with client name, draft number, date and page X of Y.
7. Covering note (.docx, one page)

Separate portrait document, same font, letter form addressed to the client by first name. Contents: what the schedule is; how each row works; numbered how-to list (High rows first; where to write answers and list documents; closed answers with a sentence of explanation; "cannot recall" is proper; staged return is fine); timescale with [ ] for the solicitor to set; a costs-saving encouragement; sign-off. Same draft banner. Calm tone — the client is engaged but overwhelmed.

8. Verify before delivering
  1. Validate both files against the OOXML schema if a validator is available; at minimum, open them and check they render. Note: the docx package emits an invalid <w:highlightCs> element for highlighted runs — strip it from word/document.xml (unzip → sed 's|<w:highlightCs w:val="yellow"/>||g' → rezip) or schema validation fails.
  2. Convert to PDF and look at every page (soffice → pdftoppm): check column headers don't wrap badly, numbering renders, highlights show.
  3. Programmatically confirm native numbering (numPr present, no typed leading digits in cell text).
  4. For each row, re-read the cited paragraph or page and confirm the position as summarised is a fair paraphrase — not merely that the cited document exists. Quote-check every figure, date and quotation verbatim against the source (against the page image where the source was OCR'd).
  5. Re-check the coverage map (step 3): confirm every mapped source item appears as a row or a listed exclusion, and that the exclusions appendix is present in the document.
  6. Check priorities: confirm every limitation-sensitive or decision-blocking issue is marked High, and record the priority reasoning in the report-back.
9. Save and name
  • Suggested convention: <case>-client-instruction-schedule-draft-NN-YYYY-MM-DD.docx and <case>-client-covering-note-draft-NN-YYYY-MM-DD.docx (ISO date = date of drafting), saved to the matter's drafts area — never to any folder holding final or filed documents. Adapt to the firm's own naming and filing conventions.
  • If the firm keeps a blank precedent version for human completion (covering letter page then schedule), that precedent need not carry the AI-draft banner; AI-generated drafts must always carry the banner and solicitor notes described above.
10. Report back

Finish by listing: the issues found (grouped by priority, with the reasoning for each High marking); the coverage map, including every issue considered and excluded and why; documents referenced in the papers but absent from the folder; the basis on which each document was identified; every inconsistency flagged; and open questions for the solicitor.

Reference files

  • references/schedule-data-example.js — example row data from a fictional dispute (Frayne v Kestrel, an invented barn-conversion case), showing the register and sourcing style each column needs.
  • references/build-schedule-example.js — complete working build script for the schedule document.

Disclaimer

This skill is provided for use by legal professionals. It does not provide legal advice, and its output is a draft requiring review by a qualified solicitor before any use. The author accepts no liability for reliance on unreviewed output.

© 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

Files

SKILL.md and 5 other files (references) in skills/client-instruction-schedule-serhan-handani-fx44146u of lawve-ai/awesome-legal-skills.

  • SKILL.md
  • LICENSE
  • NOTICE
  • README.md
  • references/build-schedule-example.js
  • references/schedule-data-example.js

Open the folder on GitHubat commit 045f738

Compare with similar skills

Client Instruction Schedule 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.

Client Instruction Schedule compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Client Instruction Schedule this skilllawve-ai/awesome-legal-skills847—~3.3kAutomated safety check: PassApache-2.0
Suikonwiizo/suiko114—~1.8kAutomated safety check: PassMIT
PDF Conversion Routersickn33/agentic-awesome-skills47k1 repos~3.8kAutomated safety check: PassMIT
Offensive ReportingSnailSploit/Claude-Red7.4k—~3.7kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
DOCXrvdbreemen/OTGW-firmware20733 repos~4.3kAutomated safety check: PassProprietary

Similar skills

  • Suiko

    nwiizo/suiko

    日本語文書のAI由来の均一さ、翻訳調、不自然さ、論旨、読解負荷を、決定的なRust CLIと目視で診断し、依頼に応じて書く・直す。日本語の学術論文・研究報告では、中心命題、用語、論証、DOCX/PDF納品を監査契約で確認する。Use when the user explicitly mentions suiko, asks whether Japanese text looks…

    114 GitHub stars~1.8k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • PDF Conversion Router

    sickn33/agentic-awesome-skills

    A skill your agent uses when converting a PDF into another format such as Markdown, HTML, text, JSON, DOCX, or structured notes and the agent must choose the best extraction route, settings, and…

    47k GitHub starsUsed in 1 repo~3.8k tokens
    Documents & OfficeAuto-check passed
  • Offensive Reporting

    SnailSploit/Claude-Red

    Penetration test and red team report writing methodology. An agent skill from SnailSploit/Claude-Red.

    7.4k GitHub stars~3.7k tokensUpdated 21 days ago
    SecurityAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • DOCX

    rvdbreemen/OTGW-firmware

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    207 GitHub starsUsed in 33 repos~4.3k tokens
    Documents & OfficeAuto-check passed
  • Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed

More from lawve-ai/awesome-legal-skills

All 154 skills in this repo
  • Customs Trade Law Onur Kafkas

    lawve-ai/awesome-legal-skills

    U.S. An agent skill from lawve-ai/awesome-legal-skills.

    847 GitHub stars~4.1k tokensUpdated 8 days ago
    Auto-check passed
  • Eu Data Act Oliver Schmidt Prietz

    lawve-ai/awesome-legal-skills

    Practitioner skill for advising on EU Regulation 2023/2854 (Data Act).

    847 GitHub stars~3.9k tokensUpdated 8 days ago
    Auto-check passed
  • Litigation Deadline Calendar

    lawve-ai/awesome-legal-skills

    Calendar litigation and arbitration deadlines from a scheduling order.

    847 GitHub stars~4.3k tokensUpdated 8 days ago
    Auto-check passed
  • Outlook Emails Lawvable

    lawve-ai/awesome-legal-skills

    Read, search, and download emails and attachments from Microsoft Outlook via OAuth2.

    847 GitHub stars~672 tokensUpdated 8 days ago
    Auto-check passed
  • Ambiguity Report

    lawve-ai/awesome-legal-skills

    Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable.

    847 GitHub stars~4.6k tokensUpdated 8 days ago
    Auto-check passed
  • Az Eu Website Privacy Audit

    lawve-ai/awesome-legal-skills

    Audits a website for compliance with Azerbaijan's Law on Personal Data No.

    847 GitHub stars~3.8k tokensUpdated 8 days ago
    Auto-check passed

Works with

Questions about Client Instruction Schedule

What does Client Instruction Schedule do?

Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note. Client Instruction Schedule is an agent skill from lawve-ai/awesome-legal-skills. Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note.

When should I use Client Instruction Schedule?

Client Instruction Schedule fits situations like: the user asks for a client instruction schedule; instruction schedule; client questionnaire; schedule of questions for the client.

How do I install Client Instruction Schedule in Claude Code?

Run `npx skills add lawve-ai/awesome-legal-skills --skill client-instruction-schedule -a claude-code`. Or copy the skill folder (skills/client-instruction-schedule-serhan-handani-fx44146u in lawve-ai/awesome-legal-skills) into .claude/skills/client-instruction-schedule in your project. Claude Code loads it when a task matches its description.

How do I install Client Instruction Schedule in Codex?

Run `npx skills add lawve-ai/awesome-legal-skills --skill client-instruction-schedule -a codex`. Or copy the skill folder (skills/client-instruction-schedule-serhan-handani-fx44146u in lawve-ai/awesome-legal-skills) into .agents/skills/client-instruction-schedule in your project. Codex loads it when a task matches its description.

Can I use Client Instruction Schedule in Cursor, Gemini CLI or GitHub Copilot?

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 client-instruction-schedule -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/client-instruction-schedule, .gemini/skills/client-instruction-schedule, .github/skills/client-instruction-schedule and .opencode/skills/client-instruction-schedule in your project.

What does Client Instruction Schedule need to run?

Going by SKILL.md and its folder, Client Instruction Schedule needs JavaScript for the scripts in its folder. Our summary lists: Node.js.

Does Client Instruction Schedule access the network?

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.

Is Client Instruction Schedule safe to install?

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.

What licence does Client Instruction Schedule use?

Client Instruction Schedule is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Client Instruction Schedule use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Client Instruction Schedule?

Skills that share tags, products or a category with Client Instruction Schedule: Suiko (nwiizo/suiko, 114 stars), PDF Conversion Router (sickn33/agentic-awesome-skills, 47k stars), Offensive Reporting (SnailSploit/Claude-Red, 7.4k stars) and Markitdown (ImCa0/just-laws, 781 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Client Instruction Schedule?

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.