Agent skill
learn_skill
会話履歴や作業内容から、再利用可能なエージェントスキルを生成または追記する
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/learn-skill
SKILL.md
Meta Skill (Skill Generator)
This skill analyzes the current workflow or conversation to create reusable skills.
Instructions
-
Analyze Context:
- Review the recent conversation history to identify repeated tasks, complex procedures, or user preferences.
- Determine the inputs, steps, and desired outputs.
-
Draft Skill:
- Choose a concise name (snake_case).
- Write a short description.
- Draft the
SKILL.mdcontent with YAML frontmatter and clear Markdown instructions. - Important: The
descriptionin the YAML frontmatter MUST be in Japanese.
-
Save:
- Create a directory
.agent/skills/<skill_name>. - Write the content to
.agent/skills/<skill_name>/SKILL.md.
- Create a directory
-
Confirm:
- Notify the user that a new skill has been learned.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?