メニュー
Use when creating, reviewing, or improving first-party agent skills in this repo. Apply whenever a user asks to add a skill, edit SKILL.md, optimize skill triggering, or adapt patterns from Anthropic's public skills into the canonical .cursor skill tree.
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。
Bump semver + promote CHANGELOG Unreleased via compiled harness. Use for /release, version bumps, or tagging. Runs scripts/agent_skills/release_bump.py; LLM only when Unreleased is ambiguous. Never commit/push unless the user asks.
Vexlum Scoring MCP — compact search+dispatch on is-be-mcp / is-be-live and gallery is-ui-mcp / is-ui-live.
Choose CLI tools and safe patterns before repo work. Install checklist, bounded search/read commands, and confirmation gates. Use when navigating the codebase, running shell commands, or setting up agent tooling on Windows, WSL2, or macOS.
Inspect JSON, YAML, and API responses with jq, yq, dasel, curl, and httpie. Use for package.json, config.json, and backend health checks. Never output secrets or full credential-bearing config.
Backend build, test, lint, and verify workflows via WSL pytest, ruff, doctor, and docker compose. Use before claiming work complete or opening a PR. Do not invent ad hoc Python commands outside documented venvs.
Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tree, bat, and structural search. Use when finding symbols, files, syntax patterns, or deciding which CLI search to use before reading or editing code.
| name | skill-authoring |
| description | Use when creating, reviewing, or improving first-party agent skills in this repo. Apply whenever a user asks to add a skill, edit SKILL.md, optimize skill triggering, or adapt patterns from Anthropic's public skills into the canonical .cursor skill tree. |
Create and improve durable first-party agent skills. A good skill is a compact routing layer: its frontmatter makes the agent load it at the right time, its body gives the next few decisions, and any large or deterministic material lives in bundled resources.
Canonical source: .cursor/skills/ (this repo is Cursor-first). After edits, run
python scripts/sync_assistant_trees.py so .claude/skills/ mirrors stay in sync.
SKILL.md, skill frontmatter, or bundled resources.cursor/skills/<name>/SKILL.md and optional
{references,scripts,assets}/. Do not hand-edit generated .claude/skills/ copies.python scripts/sync_assistant_trees.pypython scripts/sync_assistant_trees.py --check and
python scripts/ci/check_agent_frontmatter.py.agent/SKILL_CHANGE_AST10_REVIEW.md; update .agent/SKILL_INVENTORY.md.cursor/skills/<skill-name>/
├── SKILL.md # required: frontmatter + compact instructions
├── references/ # optional
├── scripts/ # optional (prefer scripts/agent_skills/ for shared harnesses)
└── assets/ # optional
Compiled procedural skills may use thin bootloaders pointing at scripts/agent_skills/*.py.
See .agent/SKILL_COMPILATION.md.
name must be the first key and match the directory name; description must be non-empty.
---
name: example-skill
description: Use when ...
---
.cursor/skills/python scripts/sync_assistant_trees.py and --check passpython scripts/ci/check_agent_frontmatter.py passes.agent/SKILL_INVENTORY.md updated