Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin…
$ npx skills add anthropics/claude-for-legal --skill build-guide -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install anthropics/claude-for-legal build-guide --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/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/legal-clinic/skills/build-guide .claude/skills/build-guide && 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 "build-guide" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guide into .claude/skills/build-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-guide", 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/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guideType 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 anthropics/claude-for-legal --skill build-guide -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install anthropics/claude-for-legal build-guide --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .agents/skills && cp -r skills-src/legal-clinic/skills/build-guide .agents/skills/build-guide && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "build-guide" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guide into .agents/skills/build-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-guide", 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 anthropics/claude-for-legal --skill build-guide -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install anthropics/claude-for-legal build-guide --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/legal-clinic/skills/build-guide .cursor/skills/build-guide && 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 "build-guide" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guide into .cursor/skills/build-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-guide", 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/anthropics/claude-for-legal.git --path legal-clinic/skills/build-guide--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 anthropics/claude-for-legal --skill build-guide -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install anthropics/claude-for-legal build-guide --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/legal-clinic/skills/build-guide .gemini/skills/build-guide && 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 "build-guide" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guide into .gemini/skills/build-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-guide", 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 anthropics/claude-for-legal build-guideInstalls 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 anthropics/claude-for-legal --skill build-guide -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .github/skills && cp -r skills-src/legal-clinic/skills/build-guide .github/skills/build-guide && 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 "build-guide" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guide into .github/skills/build-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-guide", 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 anthropics/claude-for-legal --skill build-guide -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install anthropics/claude-for-legal build-guide --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/legal-clinic/skills/build-guide .opencode/skills/build-guide && 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 "build-guide" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/legal-clinic/skills/build-guide into .opencode/skills/build-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-guide", 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.
build-guideHelp a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin…
Build Guide is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin checks, and local rules. Use when a supervising attorney wants to build or revise a per-practice-area guide, tune how the clinic skills behave for their clinic type, or set their teaching philosophy as plugin configuration.
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Human-in-the-loop approvals. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4a6c651. 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 (its code samples are markdown).
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.
Build Guide loads about 3.8k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 1,758 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 anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 1,758 words, ~3,751 tokens.
.claude/skills/build-guide/SKILL.md (or your agent's skills folder).~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → role (must be Supervising attorney), practice areas, jurisdiction./legal-clinic:ramp).~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md. Create the guides/ directory if needed./legal-clinic:draft under the configured posture so the supervisor sees what a student sees./legal-clinic:build-guideMultiple guides are fine — one per practice area. Re-run this command to revise. Edit the guide file directly for quick changes.
The supervisor guide is the dial that turns student-facing skills from "get the work done" into "teach the student to do the work." Every student-facing skill in this plugin reads the guide before producing output: intake asks the questions the supervisor wants asked, drafting skills pick a pedagogy posture (assist / guide / teach), review gates route to the supervisor on the items the supervisor cares about, and cross-plugin checks wrap other-plugin skills in a supervision layer.
This skill helps a supervisor author that guide in 5-10 minutes per practice area. The guide is plain markdown at a well-known path — edit it by hand anytime.
Audience: the supervising attorney. Not students. Students run /legal-clinic:ramp and then the student-facing skills; they don't author guides.
Every output from this skill is a supervisor-facing configuration artifact, not student work product. Do NOT prepend [AI-ASSISTED DRAFT — requires student analysis and attorney review] to the output of this skill — that label is for student outputs. The guide file this skill writes is a supervisor configuration document; it sits next to CLAUDE.md in the plugin config directory, not in a matter workspace.
Offer this as a checklist the supervisor can skip through or use as the table of contents for the interview:
Walk through the checklist at the start of the interview so the supervisor knows what's coming and can flag which items they already have strong views on versus which they want to think through. Skip any item the supervisor waves off; note it in the guide as "not specified — skill uses defaults."
This is a supervisor skill. Read ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → ## Who's using this → Role. If the role is not "Supervising attorney," say:
This skill is for supervisors — it configures how the student-facing skills behave. If you're the supervisor, make sure your practice profile role is set to "Supervising attorney" in
/legal-clinic:cold-start-interview. If you're a student, this isn't the right skill for you — run/legal-clinic:rampto onboard, or ask your supervisor to author a guide for your clinic.
Stop if the role is not supervising attorney.
What clinic is this guide for? (Immigration / Housing / Family / Transactional / Criminal defense / Consumer / Other)
If the answer is "Other," ask for a short name — that name becomes the filename (lowercase, hyphenated: immigration-removal-defense.md, transactional-nonprofit.md, etc.).
Check the practice areas listed in CLAUDE.md → ## Clinic profile → Practice areas. If the chosen practice area is not listed there, note it: "I'll write this guide, but your practice profile doesn't list [area] as one of your clinic's practice areas. That's fine — you can add it later with /legal-clinic:cold-start-interview --redo — but the student-facing skills won't route intakes to this area until the profile lists it."
If a guide already exists at ~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md, offer: "A guide for [area] already exists at [path]. Do you want to (a) revise it section-by-section, (b) start fresh and overwrite, or (c) see what's there first?"
What should students ask a new client for this clinic type? I'll start with a generic intake for [practice area] — tell me what to add, remove, or change. What red flags should students look for? What makes a case a good fit for your clinic vs. a referral out?
Show the generic intake defaults for the practice area — use the same defaults that client-intake uses (Immigration: status, entry, prior applications, country conditions, family, criminal history, timeline urgency; Housing: housing type, what happened, lease, habitability, timeline; Family: relationship, issue, children, safety, orders, hearings; Consumer: debt type, contacts, documentation, filings, deadlines). For practice areas outside those four, ask the supervisor to describe the intake from scratch.
Capture: questions to add, questions to remove, questions to rephrase, red flags (a list), good-fit criteria (what makes this a case the clinic takes vs. refers out).
How much should the skills do vs. how much should the student do?
- Guide (default): The skill produces structure; students fill in substance; the skill gives feedback. Balanced — most clinics start here.
- Assist: The skill produces work product; students review and learn by editing. Fastest, least pedagogical. Good for high-volume clinics or when deadlines are tight.
- Teach: The skill doesn't produce work product — students draft, the skill gives Socratic feedback and only shows models after two attempts. Slowest, most pedagogical. Good for seminar-style clinics or when learning is the primary goal.
You can set this per document type (e.g., teach for client letters, assist for file memos).
Capture the default posture for the practice area, and any per-document overrides. Per-document settings the skills read:
pedagogy_posture_default: assist | guide | teachpedagogy_posture_client_letter: [override]pedagogy_posture_memo: [override]pedagogy_posture_draft: [override]If the supervisor names a document type the skills don't currently have, record the intended posture in a pedagogy_posture_other: block with a note — future skills can read it.
Which work product needs your review before it goes to a client? Which can students send directly? Default: everything client-facing needs review.
Present the options as a table the supervisor fills in:
| Work product | Gate |
|---|---|
| Intake summary | [student writes; supervisor reviews at case rounds / supervisor reviews before client sees / student keeps] |
| Memo (internal) | [supervisor reviews / student keeps] |
| Client letter (appointment / doc request / brief status) | [supervisor reviews / student sends directly] |
| Client letter (substantive advice / bad news) | [always supervisor — cannot override] |
| Draft filing (court / agency) | [always supervisor — cannot override] |
| Status update to court | [always supervisor — cannot override] |
| Research-start roadmap | [student works from it directly] |
Some gates are non-negotiable: client letters that give substantive advice, court filings, and status to courts always route through the supervisor per the clinic's supervision structure. Flag those as fixed; the configurable gates are the routine ones.
Do you want students to use skills from other plugins (defined-terms checks, doc consistency, section references, research verification)? I can wrap them in supervision — the student runs the check, the output flags uncertainty for your review, nothing goes out without your sign-off.
Offer concrete examples tied to practice area:
commercial-legal:review (NDA triage, vendor review) wrapped so the student runs the review, the output is flagged for supervisor review before going to the client.litigation-legal:chronology for building a timeline from client documents, flagged for supervisor review before it feeds a filing.litigation-legal:subpoena-triage when the client brings in a subpoena, wrapped so the student drafts the response plan but the supervisor signs off.privacy-legal:triage if the student is handling any matter where personal data is shared outside the clinic.If the supervisor names a cross-plugin skill they want, record: skill name, when students should use it, what supervision wrapper applies (always reviewer, only when flagged, never without supervisor).
What court(s) does your clinic practice in? Any local rules or forms students need to use?
Check CLAUDE.md → ## Jurisdiction — the state and primary court are already set at cold-start. This step is for practice-area-specific local rules and forms (e.g., "Housing Court standing order on summary process answers," "USCIS filing address for the local field office," "Family Court self-help center forms and where to find them"). Offer to capture a short list of pointers the student-facing skills should use when drafting or advising.
Write to ~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md. Create the guides/ directory if it doesn't exist. Use this structure:
# Practice-area guide: [Practice area]
*Authored by the supervising attorney via `/legal-clinic:build-guide`. Student-facing skills read this before producing output. Edit directly anytime.*
**Last updated:** [date]
**Authored by:** [supervising attorney name from CLAUDE.md]
---
## Intake
**Questions to ask** (supplement/replace the generic defaults):
- [question 1]
- [question 2]
- ...
**Red flags** (surface these in the intake summary if present):
- [flag 1]
- [flag 2]
**Good-fit criteria** (cases this clinic takes):
- [criterion 1]
- [criterion 2]
**Refer-out criteria** (cases this clinic does not take):
- [criterion 1]
- [criterion 2]
---
## Pedagogy posture
`pedagogy_posture_default: [assist | guide | teach]`
Per-document overrides (optional):
- `pedagogy_posture_client_letter: [assist | guide | teach]`
- `pedagogy_posture_memo: [assist | guide | teach]`
- `pedagogy_posture_draft: [assist | guide | teach]`
**Rationale:** [one or two sentences from the supervisor on why this posture — helps next semester's supervising attorney understand the choice]
---
## Review gates
| Work product | Gate |
|---|---|
| Intake summary | [gate] |
| Memo (internal) | [gate] |
| Client letter — routine | [gate] |
| Client letter — substantive | supervisor (fixed) |
| Draft filing | supervisor (fixed) |
| Court-facing status | supervisor (fixed) |
| Research roadmap | [gate] |
---
## Cross-plugin checks
| Skill | When students use it | Supervision wrapper |
|---|---|---|
| [plugin:skill] | [situation] | [wrapper] |
---
## Local rules and jurisdiction
**Court(s):** [from CLAUDE.md or additional courts for this practice area]
**Practice-area-specific local rules and forms:**
- [pointer 1]
- [pointer 2]Fill every section from the supervisor's answers. Leave a section empty only if the supervisor said so — do not invent content.
Then tell the supervisor:
Your guide is at
~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md. Every student who uses the clinic plugin for [practice area] will have skills that follow it. Edit the file directly to change anything, or re-run/legal-clinic:build-guideto revise a section. You can have multiple guides — one per practice area.
Want to see how the pedagogy posture changes the experience? I'll run
/legal-clinic:draftwith a sample client letter under [posture] — you'll see what the student sees.
If the supervisor says yes, simulate the drafting skill reading the guide they just wrote and producing output under the configured posture. Walk through one full cycle so the supervisor sees exactly what a student would see.
The skill's "output" is the file written at ~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md. The conversation with the supervisor is the interview; the written guide is the artifact.
After writing, show a brief confirmation:
Guide written.
[practice-area]is now configured:
- Intake: [N] custom questions, [N] red flags, [N] refer-out criteria
- Pedagogy: [posture default], with overrides for [list if any]
- Review gates: [summary of what routes to supervisor vs. student]
- Cross-plugin: [N] skills wired in
Students will see these changes the next time they run a clinic command for this practice area. Edit
[path]anytime to change anything, or re-run/legal-clinic:build-guideto revise.
/legal-clinic:cold-start-interview.© 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
Just SKILL.md in legal-clinic/skills/build-guide of anthropics/claude-for-legal.
Open the folder on GitHubat commit 4a6c651
We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.
Build Guide 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 |
|---|---|---|---|---|---|---|
| Build Guide this skillanthropics/claude-for-legal | 9.6k | 3 repos | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Show Me Your Work Decision Logcursor/plugins | 10k | 9 repos | ~1.6k | Automated safety check: Pass | None | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Loop Constraints Enforcercobusgreyling/loop-engineering | 11k | 1 repos | ~475 | Automated safety check: Notes | MIT | |
| Ask User QuestionMemTensor/MemOS | 12k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Discernment Nudgeanthropics/skills | 180k | 3 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 |
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
cobusgreyling/loop-engineering
Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.
MemTensor/MemOS
Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.
anthropics/skills
Appends two or three targeted follow-up questions after a substantive answer, pointing at facts to verify, reasoning to probe, or context that was assumed.
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
anthropics/claude-for-legal
Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.
anthropics/claude-for-legal
Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.
anthropics/claude-for-legal
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.
anthropics/claude-for-legal
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.
anthropics/claude-for-legal
Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.
anthropics/claude-for-legal
Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.
Categories
Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin…. Build Guide is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin checks, and local rules.
Build Guide fits situations like: A supervising attorney wants to build; revise a per-practice-area guide; tune how the clinic skills behave for their clinic type; set their teaching philosophy as plugin configuration.
Run `npx skills add anthropics/claude-for-legal --skill build-guide -a claude-code`. Or copy the skill folder (legal-clinic/skills/build-guide in anthropics/claude-for-legal) into .claude/skills/build-guide in your project. Claude Code loads it when a task matches its description.
Run `npx skills add anthropics/claude-for-legal --skill build-guide -a codex`. Or copy the skill folder (legal-clinic/skills/build-guide in anthropics/claude-for-legal) into .agents/skills/build-guide 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 anthropics/claude-for-legal --skill build-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/build-guide, .gemini/skills/build-guide, .github/skills/build-guide and .opencode/skills/build-guide in your project.
SKILL.md names no scripts, command-line tools or credentials: Build Guide 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.
Build Guide 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.
About 3.8k tokens (SKILL.md is roughly 15k 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 Build Guide: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Loop Constraints Enforcer (cobusgreyling/loop-engineering, 11k stars) and Ask User Question (MemTensor/MemOS, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,611 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.