New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Termination Review

by anthropics in anthropics/claude-for-legal

Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction.

OfficialApache-2.0Auto-check passed

Install Termination Review

skills CLI
$ npx skills add anthropics/claude-for-legal --skill termination-review -a claude-code

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

GitHub CLI
$ gh skill install anthropics/claude-for-legal termination-review --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/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/employment-legal/skills/termination-review .claude/skills/termination-review && 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
termination-review
GitHub stars
9.6k
Used in
2 other repos
Token cost
~4.2k tokens
SKILL.md length
1,836 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction.

  • Works in 5 steps: The basic facts → High-risk flag scan → Jurisdiction-specific requirements → …
  • The user says reviewing a termination
  • SKILL.md covers Matter context, Purpose, Load context and Output header, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Termination Review is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction. Jurisdiction-specific rules and release consideration periods are researched per review, not stored. Use when the user says "reviewing a termination", "can we fire this person", "term review", or describes a termination scenario.

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • The user says reviewing a termination
  • Can we fire this person
  • Describes a termination scenario

Example prompts

  • “reviewing a termination”
  • “can we fire this person”
  • “term review”
  • “/termination-review”

Workflow steps

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

  1. The basic facts
  2. High-risk flag scan
  3. Jurisdiction-specific requirements
  4. Severance and release
  5. Documentation check

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Termination Review loads about 4.2k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 1,836 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k

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 anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 1,836 words, ~4,151 tokens.

Download SKILL.mdSave it as .claude/skills/termination-review/SKILL.md (or your agent's skills folder).
name
termination-review
description
Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction. Jurisdiction-specific rules and release consideration periods are researched per review, not stored. Use when the user says "reviewing a termination", "can we fire this person", "term review", or describes a termination scenario.
argument-hint
[describe the termination, or attach documentation]

/termination-review

  1. Load ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → termination review triggers, high-risk flags, severance practice, jurisdiction rules.
  2. Use the workflow below.
  3. Walk the checklist. Check every high-risk flag.
  4. Final pay timing per employee's jurisdiction. Severance + release if applicable.
  5. If any high-risk flag fires: escalate per table, don't proceed without sign-off.

Matter context

Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /employment-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/employment-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.

Purpose

Most terminations are fine. A few are lawsuits waiting to happen. This skill runs the checklist that catches the second kind before the decision is final. The skill does not state the law — every jurisdiction-specific rule and release-period requirement is researched and cited at the time of review.

Load context

~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → termination review triggers, high-risk flags, standard severance, jurisdiction table.

Output header

Prepend the work-product header from ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → ## Outputs (it differs by user role — see ## Who's using this). Match the memo format from seed term memos referenced in that config where one exists. The work-product header is always first.

Workflow

Step 1: The basic facts
  • Employee name (or role if staying abstract)
  • Jurisdiction (where they work)
  • Reason for termination (performance, misconduct, RIF, position elimination)
  • How long employed
  • Age (relevant to release requirements for older-worker protections)
  • Whether any other employees are being terminated as part of the same decisional unit or program (relevant to group-termination release rules)
  • When is the planned term date
Step 2: High-risk flag scan

This is the most important step. Check every flag from ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md. Default set:

FlagWhy it's high-riskCheck
Recent complaintRetaliation claimHas this employee filed any complaint (HR, ethics hotline, regulatory) recently?
Protected leaveLeave-law interference/retaliationCurrently on or recently returned from protected leave (FMLA/state equivalents, disability, parental, military)?
Protected class + timingDiscrimination claimProtected class AND recently disclosed/visible (pregnancy announcement, religious accommodation request, disability disclosure)?
WhistleblowerFederal and state whistleblower statutesHas this employee raised concerns about illegality, safety, fraud?
Thin documentation"Why now?" problemFor performance terms: is there a PIP, written warnings, documented feedback? Or did this come out of nowhere?
Comparator problemDisparate treatmentIs someone else doing the same thing and not being terminated?
Contract/handbook promiseBreachDoes the offer letter, handbook, or any writing promise a process that isn't being followed?
Exempt misclassificationFLSA + state wage claim with liquidated damagesSee the classification check below. Fires on state + classification + title.

Exempt/non-exempt classification flag. Fire this flag when ALL of the following are true:

  1. The employee works in a state with a high exempt salary threshold — CA, NY, WA, CO, AK (and any other state listed in ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → ## Wage & hour → Known classification risk areas as a high-threshold state) — AND
  2. The employee is classified exempt (salaried, no overtime) — AND
  3. The employee's title contains "supervisor," "lead," "coordinator," "analyst," "administrator," or "specialist" (case-insensitive, and any equivalent-scope title the practice profile flags as risky).

When all three fire, emit:

🔴 Potential exempt misclassification — [title] earning $[X] in [state]. The exempt salary threshold in [state] is approximately $[Y] [model knowledge — verify]. Before termination, route to /employment-legal:wage-hour-qa for a classification check — a misclassified employee who's terminated has a ready-made FLSA and state-wage claim with liquidated damages, attorneys' fees, and (in CA) PAGA exposure, which the separation agreement may not be able to release cleanly. A terminated plaintiff with unpaid-OT exposure is the most litigated wage-and-hour fact pattern in these states.

Do not suppress this flag because the title "looks managerial" — the whole premise of the misclassification claim is that titles lie. Route to /employment-legal:wage-hour-qa for the actual duties-and-salary test.

If a back-pay number is being computed as part of this review (severance modeling, settlement posture, exposure estimate), do NOT compute it in this skill. Route to wage-hour-qa → Step 2a and use its regular-rate scaffold: §207(e) inclusions (non-discretionary bonuses, commissions, shift diffs) in the regular rate, 0.5× premium when straight time was already paid for OT hours (else 1.5×), liquidated damages under §216(b), and 2-year / 3-year willful SOL under §255(a). Every back-pay number carries [verify — consult wage-and-hour counsel before asserting or paying]. A clean-looking wrong number here is the specific failure mode this scaffold prevents.

Any flag fires → escalate per ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md before the term proceeds. Not after. Before.

Step 3: Jurisdiction-specific requirements

Research the applicable rules for the employee's jurisdiction before finalizing the plan. Specifically:

  • Final-pay timing — this varies widely by state and often depends on whether the employee was terminated or resigned. Research the currently operative rule, including any waiting-time or late-pay penalties.
  • Accrued-PTO payout — research whether the jurisdiction requires payout, and any interaction with accrual-cap or use-it-or-lose-it policies.
  • Required notices — research any jurisdiction-specific notices required at termination (e.g., state unemployment, continuation-coverage notices beyond federal COBRA, benefits continuation).
  • Mass-layoff / plant-closing notices — research federal WARN Act and any state "mini-WARN" or local ordinance that may apply if this is part of a larger reduction. Coverage thresholds and notice periods differ.

Cite primary sources. Verify currency.

No silent supplement. If a research query to the configured legal research tool returns few or no results for the jurisdiction's final-pay, PTO, notice, or WARN rule, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: "The search returned [N] results from [tool]. Coverage appears thin for [jurisdiction / rule]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged [web search — verify] and should be checked against a primary source before relying, or (4) stop here and flag for attorney verification. Which would you like?" A lawyer decides whether to accept lower-confidence sources.

Source attribution. Tag every citation in the plan — final-pay rule, PTO rule, notices, WARN / mini-WARN, OWBPA consideration periods, state release restrictions — with where it came from: [Westlaw], [CourtListener], or the MCP tool name for citations retrieved from a legal research connector; [web search — verify] for web-search citations; [model knowledge — verify] for citations recalled from training data; [user provided] for citations the user supplied. Citations tagged verify carry higher fabrication risk and should be checked first. Never strip or collapse the tags.

Show full SKILL.md (763 more words)Show less
Step 4: Severance and release

Per ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → standard severance:

  • Is severance being offered? Per formula or discretionary?
  • Release required? (Usually yes if paying severance — that's the consideration.)

Research the applicable release-consideration rules. If the employee is 40 or over, federal law (OWBPA) imposes specific requirements that affect the consideration period, revocation period, required advisements, and — for group terminations — required decisional-unit disclosures. The specific consideration period differs between an individual termination, a group RIF, and a group exit incentive; the rule also depends on the employee's age and the number of employees affected. Do not state the day count from memory — research the currently operative rule for the specific situation and cite primary sources. Also research any state-law analogs or parallel release requirements. Verify currency.

Separately, consider whether any of the following apply to the release:

  • State-specific waiver restrictions (some states limit what can be released or require specific language).
  • Federal or state restrictions on non-disclosure or non-disparagement clauses that relate to sexual harassment, discrimination, or other protected categories.
  • Separation-agreement rules on NLRA-protected activity.
Step 5: Documentation check

For performance terminations especially:

  • Is there a paper trail? Written warnings, PIP, feedback docs?
  • Does the paper trail tell a consistent story?
  • Is there anything in writing that contradicts the reason (recent positive review, bonus, promotion)?

The "why now" question: if this person has been underperforming for a year, what changed? The answer should be documented.

Output

Research-connector pre-flight. Before emitting the memo, check whether a legal research connector is reachable for this session — Westlaw, CourtListener, or any firm-configured research MCP. Collect this into the reviewer note per CLAUDE.md ## Outputs: if no connector returns results in Step 3 (or none is configured at run time), record it in the Sources: line of the reviewer note — e.g., not connected — cites from training knowledge; the highest-fabrication topics in termination-law memos are final-pay timing, OWBPA group/individual distinctions, state-specific NDA / non-disparagement rules (e.g., CA SB 331), and NLRB positions (e.g., McLaren Macomb) — spot-check those first. Per-citation [model knowledge — verify] tags remain inline. Do not emit a standalone banner above the memo.

Jurisdiction assumption. This review assumes the employee's jurisdiction as stated in Step 1 and any defaults from ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → Jurisdictional footprint. Employment rules, final-pay timing, release requirements, and notice obligations vary materially by jurisdiction. If the employee works in a different state or country, or if choice-of-law is contested, this analysis may not apply as written.

Match the memo format from seed term memos referenced in ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md. If none:

markdown
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]

## Termination Review: [Role/Name] — [Date]

**Jurisdiction:** [State]
**Reason:** [Performance / Misconduct / RIF / Elimination]
**Planned date:** [Date]

---

### Bottom line

[Can you proceed / Need to fix X first / Stop — one-sentence why]

---

### High-risk flags

[Every flag from Step 2. ✅ Clear or 🔴 FLAG with detail.]

**Escalation:** [None needed | Escalate to [name] before proceeding — [which flag]]

---

### Jurisdiction requirements ([State])

- Final pay: [researched rule and cite; state whether PTO is included per the
  researched rule and any team policy]
- Required notices: [list, each researched and cited]
- Mass-layoff notice (if applicable): [researched rule and cite]

---

### Severance and release

- Severance: [amount per formula / none]
- Release: [required / not — if required, research and apply the
  consideration-period, revocation-period, advisement, and (for groups)
  decisional-unit-disclosure requirements that govern this specific
  situation; cite primary sources and verify currency]
- [Any state-law release rules or non-disclosure/non-disparagement
  restrictions that apply]

---

### Documentation

[Assessment of paper trail. Gaps flagged.]

---

### Go / No-go

[Clear to proceed | Proceed with changes below | Hold — escalation pending]

### Checklist for term day

- [ ] Final paycheck ready, correct amount, delivered per researched rule
- [ ] Continuation-coverage notices (COBRA / state analogs) prepared
- [ ] [State] unemployment notice prepared
- [ ] Severance agreement (if applicable) with the consideration period
      required for this specific situation
- [ ] Return of property / access cutoff coordinated
- [ ] [etc.]

Consequential-action gate (terminate an employee)

Before producing a "Go" recommendation or a term-day checklist marked ready: Read ## Who's using this in ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md. If the Role is Non-lawyer:

Terminating an employee has legal consequences — wrongful-termination, discrimination, retaliation, and wage-law claims all trace back to how this decision is structured. Have you reviewed this termination with an attorney? If yes, proceed. If no, here's a brief to bring to them:

  • Employee, jurisdiction, reason, planned date
  • Every high-risk flag the review surfaced (recent complaint, protected leave, protected class + timing, whistleblower, thin documentation, comparator, contract/handbook promise) — with detail
  • Jurisdiction-specific findings (final pay, PTO, required notices, mass-layoff rules) and where they were cited from
  • Severance/release analysis, including any OWBPA/older-worker-protection angles
  • Open questions and what's unresolved
  • What could go wrong (the claim theory this fact pattern supports)
  • What to ask the attorney (is this a clean term; do we need more documentation first; does the release need specific language; do we need to stagger decisional units)

If you need to find an attorney, solicitor, barrister, or other authorised legal professional: contact your professional regulator (state bar in the US, SRA/Bar Standards Board in England & Wales, Law Society in Scotland/NI/Ireland/Canada/Australia, or your jurisdiction's equivalent) for a referral service. Employment is one of the practice areas where a short consult before the termination meeting consistently outvalues a post-termination claim defense.

Do not produce a "Clear to proceed" output past this gate without an explicit yes. A marked-DRAFT flagged for attorney review is fine.

Close with the next-steps decision tree

End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

What this skill does not do

  • Make the termination decision. It checks the decision.
  • Have the conversation. The manager does that.
  • State release or jurisdiction rules from memory — every rule is researched and cited at the time of review.
  • Guarantee no lawsuit. It reduces the risk by catching the obvious problems.

© anthropics, 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

Just SKILL.md in employment-legal/skills/termination-review of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Termination Review 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.

Termination Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Termination Review this skillanthropics/claude-for-legal9.6k2 repos~4.2kAutomated safety check: PassApache-2.0
Flagsvercel/next.js143k—~746Automated safety check: PassMIT
Terminal Openeraffaan-m/ECC276k—~635Automated safety check: PassMIT
Pii Detectruvnet/ruflo74k—~350Automated safety check: NotesMIT
Threat Detectionalirezarezvani/claude-skills28k—~3.5kAutomated safety check: PassMIT
Detecting Arp Poisoning In Network Trafficmukul975/Anthropic-Cybersecurity-Skills34k—~3.8kAutomated safety check: NotesApache-2.0

Similar skills

  • Flags

    vercel/next.js

    Official

    How to add or modify Next.js experimental feature flags end-to-end.

    143k GitHub stars~746 tokensUpdated today
    DevelopmentAuto-check passed

  • Terminal Opener

    affaan-m/ECC

    Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery…

    276k GitHub stars~635 tokensUpdated today
    Marketing & SEOAuto-check passed

  • Pii Detect

    ruvnet/ruflo

    Detect and flag personally identifiable information (PII) in text, code, and configurations.

    74k GitHub stars~350 tokensUpdated today
    Auto-check: notes

  • Threat Detection

    alirezarezvani/claude-skills

    A skill your agent uses when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.

    28k GitHub stars~3.5k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Detecting Arp Poisoning In Network Traffic

    mukul975/Anthropic-Cybersecurity-Skills

    Detect Layer 2 ARP poisoning/spoofing by deploying ARPWatch, Dynamic ARP Inspection (DAI), Wireshark packet analysis, and custom Python monitoring scripts that flag gratuitous ARP floods, IP-to-MAC…

    34k GitHub stars~3.8k tokensUpdated 1 mo ago
    SecurityAuto-check: notes

  • Detecting Anomalies In Industrial Control Systems

    mukul975/Anthropic-Cybersecurity-Skills

    Deploys anomaly detection for OT/ICS environments using machine learning on OT network baselines, physics-based process models, and Modbus/DNP3/OPC UA traffic analysis to flag deviations, rogue…

    34k GitHub stars~3.2k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Questions about Termination Review

What does Termination Review do?

Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction. Termination Review is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction.

When should I use Termination Review?

Termination Review fits situations like: the user says reviewing a termination; can we fire this person; describes a termination scenario.

How do I install Termination Review in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill termination-review -a claude-code`. Or copy the skill folder (employment-legal/skills/termination-review in anthropics/claude-for-legal) into .claude/skills/termination-review in your project. Claude Code loads it when a task matches its description.

How do I install Termination Review in Codex?

Run `npx skills add anthropics/claude-for-legal --skill termination-review -a codex`. Or copy the skill folder (employment-legal/skills/termination-review in anthropics/claude-for-legal) into .agents/skills/termination-review in your project. Codex loads it when a task matches its description.

Can I use Termination Review 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 anthropics/claude-for-legal --skill termination-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/termination-review, .gemini/skills/termination-review, .github/skills/termination-review and .opencode/skills/termination-review in your project.

What does Termination Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Termination Review is instructions for the agent only.

Does Termination Review 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 Termination Review 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 Termination Review use?

Termination Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Termination Review use?

About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Termination Review?

Skills that share tags, products or a category with Termination Review: Flags (vercel/next.js, 143k stars), Terminal Opener (affaan-m/ECC, 276k stars), Pii Detect (ruvnet/ruflo, 74k stars) and Threat Detection (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Termination Review?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,633 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.