Guide to analyze a current work session and propose improvements to skills. Use (1) automatically after working with a skill to capture learnings, (2) when the user suggests improvements, corrections, or additions during a skill-related session, or (3) when the user manually invokes `self-improve`.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Analyze the current conversation and propose improvements to skills based on corrections, successes, and edge cases discovered during the work session.
self-improve - Analyze session and propose improvementsself-improve [skill-name] - Target a specific skillself-improve on - Enable automatic mode (hook)self-improve off - Disable automatic modeself-improve status - Show automatic mode statusself-improve [skill-name] history - Show modification historyself-improve)If skill name not provided, list available skills from skills/ directory and ask:
Which skill should I analyze for this session?
[List skills found in skills/ directory]
Scan the conversation for signals - moments where the user expressed feedback:
| Signal Type | Examples |
|---|---|
| Correction | "No", "That's not right", "It's missing X", "Always do Y", user rewrites output |
| Success | "Perfect", "Yes", "Exactly", user accepts without changes |
| Edge case | User needed a workaround, skill couldn't handle the request |
For each correction signal, evaluate if it can become a good skill instruction.
1. COMPLETE
The instruction includes all information needed to apply it. No need to look elsewhere or make assumptions.
| Grade | Example |
|---|---|
| Pass | "Structure output as: Key Terms / Risk Areas / Suggested Revisions" |
| Fail | "Use the standard format" (which format?) |
| Fail | "Follow our firm's guidelines" (what guidelines?) |
2. PRECISE
No vague or subjective terms. Two different people reading the instruction would understand it the same way.
| Grade | Example |
|---|---|
| Pass | "Flag non-compete clauses over 12 months as high risk" |
| Fail | "Be more thorough in the analysis" |
| Fail | "Make it more appropriate for clients" |
3. ATOMIC
One instruction addresses one single requirement. Multiple checks should be split into separate instructions.
| Grade | Example |
|---|---|
| Pass | "Check for governing law clause" |
| Fail | "Check for governing law, jurisdiction, and arbitration clauses" (three checks - split them) |
4. STABLE
If referencing regulations or standards, specify the version or date. The instruction should be evaluable the same way regardless of when it's read.
| Grade | Example |
|---|---|
| Pass | "Review the termination provisions under our internal policy [policy name and reference], dated December 12, 2024." |
| Fail | "Follow latest market standards" (which standards? will change over time) |
| Criteria Met | Action |
|---|---|
| All 4 criteria pass | Add to skill directly |
| Less than 4 criteria | Ask for clarification (see Step 5) |
When feedback doesn't meet all criteria, ask for what's missing using the AskUserQuestion tool:
I detected a correction but need more information to improve the skill.
You said: "[user's feedback]"
To create a clearer instruction, I need the following information:
[Structured tool call listing what's missing based on failed criteria]
If the user provides clarification → Update the instruction and proceed to Step 6.
If the user prefers the original → Proceed to Step 6 with the original instruction.
--- Learning: [skill-name] ---
Proposed additions:
1. "[exact instruction to add]"
Source: "[quote from conversation]"
2. "[exact instruction to add]"
Source: "[quote from conversation]"
---
Apply these changes? [Y/n]
Update SKILL.md
skills/[skill-name]/SKILL.mdUpdate skills/[skill-name]/CHANGELOG.md
## [DATE (format: "January 7, 2026")]
[Description of changes in natural language, 1-3 sentences]
For signals that couldn't be processed, offer to save:
Save these observations for later review?
- "[signal 1]" - Status: [why insufficient]
- "[signal 2]" - Status: [why insufficient]
If yes, append to skills/[skill-name]/OBSERVATIONS.md
rm -f ./.disabled
touch ./.disabled
Check .disabled file existence and report.
skills/[skill-name]/SKILL.mdskills/[skill-name]/CHANGELOG.md with a rollback noteUser said: "Always flag non-compete clauses over 12 months as high risk"
Evaluation:
Result: Add directly
User said: "Flag any non-market-standard indemnification clause"
Evaluation:
Action: Ask for clarification using the AskUserQuestion tool:
I detected a correction but need more details.
You said: "Flag any non-market-standard indemnification clause"
To make this actionable, can you specify:
- What makes an indemnification clause "non-market-standard"? (e.g., uncapped liability, coverage of indirect damages, no carve-outs for gross negligence)
Do you want to provide more details, or should I add the instruction as you stated it?
If user clarifies: Update the instruction and add it. If user prefers the original: Add the instruction as stated.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how the agent can be suspended, revoked, or escalated.
日本語の概要は準備中です。原文の説明を表示しています。
EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.
日本語の概要は準備中です。原文の説明を表示しています。
This skill builds a structured audit trail of an AI-assisted task: what the tool was asked to do, what materials it was given, what it produced, how the output was verified, and what was ultimately relied upon. It documents the workflow for supervision and later review without ruling on privilege or disclosure, so the record stays accurate rather than self-serving.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies required documentation and missing evidence, maps the use case to AI governance frameworks and applicable legal domains, and produces a preliminary or final governance review with scorecards, findings, owners, remediation actions, and follow-up questions.
日本語の概要は準備中です。原文の説明を表示しています。
Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable. Produces a multi-page website (default), a single-page interactive site, a Microsoft Word document, a PowerPoint deck, or a LaTeX/PDF. Use whenever a user has a stress-test result, ambiguity audit, or "where will this be litigated" scenarios and wants to publish, present, or share them. Triggers on "publish the audit," "make a report from this," "turn this into a website / deck / brief / Word doc," "make a Netlify site," "build slides of these ambiguities," "render the scenarios," "package this stress test," "produce a LaTeX version," and similar. Pairs with the ambiguity-stress-test skill (the underlying analysis) but works on any structured or semi-structured ambiguity analysis. Visual design is opinionated but the user can override colors, fonts, and brand label. Most formats need Python and a writable filesystem; single-file HTML works where the host has neither.
日本語の概要は準備中です。原文の説明を表示しています。
Adversarially stress-tests a legal text — a contract, statute, regulation, or judicial opinion — for interpretive ambiguity: it finds the seams where the people governed by it will later disagree about what it means and turns each into a concrete dispute scenario with both sides' arguments, the likely outcome, and a fix. Use it whenever someone wants to pressure-test, red-team, audit, or find weak spots, loopholes, gaps, ambiguities, or drafting problems in a legal document; whenever a drafter wants to tighten a contract, statute, regulation, or opinion before it issues; whenever a litigator wants to mine an opinion or contract for arguments; or whenever someone hands over a legal text and asks where it will be fought over or for issue-spotting. Trigger it for contract review, statutory-ambiguity analysis, judicial-opinion scope analysis, and drafting QA — even if the user never says "stress-test" or "ambiguity."
日本語の概要は準備中です。原文の説明を表示しています。