メニュー
Use when creating a reusable Claude Code skill, defining a new repeatable agent capability, or replacing a one-off workflow with discoverable instructions that need clear ownership, validation, and trigger behavior.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Creates a new specialist agent as two stitched source files, base.md plus frontmatter/claude.json, proposing model, effort, and permissions by role archetype and confirming them with the user before writing. Use when adding a new subagent, defining a new specialist role, scaffolding an agent definition, or when update-agent hands off new-agent creation.
Discover, validate, stitch, and install specialist agent templates contributed by Essential and other enabled plugins in the same marketplace. Use when asked to install agents, set up subagents, refresh the agent team, or configure Claude Code on a new machine.
[Description] — third person, what the skill does plus a 'Use when...' clause with concrete trigger phrases a user would actually type; 25-60 words; lead with the key use case.
Update explicitly selected agent definitions to the current two-file template or a stated behavior change while preserving useful role expertise, trigger boundaries, context, collaboration links, and working voice. Use when migrating agents to a template revision, correcting agent configuration, or batch-updating selected agents; require an exact selector and route genuinely new roles to create-agent.
Enforce coding standards mechanically across a selected scope with batched linters and independent reviewers. Use when source files need lint-error correction, standards enforcement, or consistent formatting, including calls extended by another plugin's portable lint profile; behavior-changing repairs belong to fix.
Review semantic correctness, security, test intent, documentation, sibling consistency, and alignment with the implementation plan. Use after code changes or for explicit review requests; report findings without editing code and leave mechanical standards enforcement to lint.
| name | create-skill |
| description | Use when creating a reusable Claude Code skill, defining a new repeatable agent capability, or replacing a one-off workflow with discoverable instructions that need clear ownership, validation, and trigger behavior. |
| model | opus |
| context | fork |
Follow ${CLAUDE_SKILL_DIR}/../../constitution/references/authoring-invariants.md.
Start from ${CLAUDE_SKILL_DIR}/../../constitution/templates/skill.md, adapting
headings to the capability.
${TMPDIR:-/tmp}/check.md) using
${CLAUDE_SKILL_DIR}/../../constitution/references/check.md as the
example table format with :white_check_mark:/:x: status markers.
Delete the scratch document before staging; these notes are reasoning aids,
not deliverables, and must not be committed.skills/<name>/SKILL.md that teaches the missing
behavior. Keep always-used instructions inline and conditional bulk in
references.claude plugin validate --strict <plugin-path>
python3 "${CLAUDE_SKILL_DIR}/../verify-skill/scripts/quick_validate.py" <skill-or-plugin-path>
Use governance:verify-skill when functional or trigger evaluation is needed,
with fix: true; loop fix and re-verify at most 3 times, then report partial
completion with the remaining issues.
Report the created path, ownership boundary, thought-experiment and blindspot coverage, validation results, runtime evaluation status (including "not exercised"), and any intentionally deferred cases. Confirm any temporary Markdown thought-experiment notes were deleted before commit.