メニュー
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
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
Durable cross-provider user and project memory. Must use when asked to remember or persist something, when recording a preference or decision, or after substantial research produces a reusable fact, lesson, or recurring pitfall. Provider-native memory is not a substitute.
Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks.
Nix operational playbooks for package diffs, build debugging, closure analysis, dependency forensics, flake maintenance, and evaluation performance tuning. Use when comparing Nix build outputs, diagnosing derivation failures, finding unexpected runtime/build dependencies, inspecting closure size, maintaining flakes, or profiling slow NixOS/Home Manager/Nixvim evaluation.
GitHub issue discovery, targeted triage, issue creation, pull-request creation, review authoring, review-feedback handling, and CI check-fix workflows using gh CLI. Use for read or write work against GitHub issues, pull requests, reviews, or checks.
Git commit planning, fixup/autosquash, branch cleanup, conflict resolution, regression bisect, and multi-commit change-stack workflows. Use for safe local history operations or deciding how changes should be split, repaired, or validated.
Progressive context-architecture expert for repository instructions, AI prompts, rules, agents, commands, and skills. Use when initializing, designing, refactoring, or auditing AI configuration for clear boundaries and token-efficient disclosure.
| name | skill-creator |
| description | Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. |
| license | Complete terms in LICENSE.txt |
Create or update skills that add durable workflows, tool integrations, domain knowledge, scripts, references, or assets without wasting context.
references/design-principles.md: token budget, degrees of freedom,
progressive disclosure.references/package-layout.md: SKILL.md, scripts, references, assets.references/creation-workflow.md: step-by-step creation/update process.references/workflows.md: workflow-writing patterns.references/output-patterns.md: output contracts and examples.Use bundled scripts directly when useful:
scripts/init_skill.pyscripts/quick_validate.pyscripts/package_skill.pySKILL.md lean: trigger metadata plus essential workflow.references/.scripts/.assets/.SKILL.md and references.SKILL.mdSKILL.md + references/scripts/assets/name and description so trigger conditions are clear.Read only focused references needed for current skill design problem.
Run scripts/quick_validate.py <skill-dir> when available. Check:
SKILL.md existsname and description