ISTQB/JSTQB のテストプロセス各工程の出口ゲートとして、工程成果物(test-plan.md / test-analysis.md / test-design.md / test-case.md / テスト実装 / test-execution-log.md / test-monitoring.md / test-summary-report.md)をレビューするスキル。決定論スクリプトの機械検査(トレーサビリティ ID 突合・テンプレ準拠)と test-reviewer サブエージェントの定性レビューを行い、利用者が通過/条件付き通過/差し戻しを判定して軽量記録 test-review-<工程>.md を残す。上流の仕様・基本設計(spec / design-doc 工程。docs/dev/<対象>/spec.md・basic-design.md)は機械検査と利用者判定のみの軽量ゲートとして扱う。各工程スキル(test-plan〜test-report / feature-spec / basic-design)が完了宣言の前に本スキルの実行を促す。ソースコード diff のレビュー(diff-review)とは別物で、対象はテストプロセスの成果物のみ。成果物の修正・代作はしない。/test-review <テスト対象名> [工程] で明示的に呼び出されたときのみ使用する。
The English summary is being prepared. Showing the original description.
yasunori0418/skills☆ 9Updated Oct 14, 2026
Reorganize long AGENTS.md, CLAUDE.md, and similar instruction files into a short main file with links to topic-specific documents. Identifies conflicting rules and deletion candidates, then checks links and coverage so instructions remain organized and accessible.
- Shorten an oversized AGENTS.md
- Split CLAUDE.md into topic-specific files
- Resolve conflicting agent instructions
davila7/claude-code-templates☆ 32.8KUpdated Oct 20, 2026
Explore an unfamiliar codebase and turn its structure, request flow, and development conventions into a concise onboarding guide. Create or update CLAUDE.md with project-specific instructions, preserving existing guidance and identifying findings that remain uncertain.
- Understanding an unfamiliar project when joining a team
- Setting up Claude Code in an existing repository
- Creating CLAUDE.md from detected project conventions
affaan-m/ECC☆ 284.8KUpdated Oct 20, 2026
Create and edit documents that AI agents follow, including skills and project instructions. Organize steps and reference material, define clear completion criteria, and refine document links and wording to reduce duplication and unnecessary context.
- Creating or editing a skill document
- Organizing AGENTS.md or CLAUDE.md
- Clarifying when agents should read reference files
mattpocock/skills☆ 298.5KUpdated Oct 20, 2026
Create or update a SOUL.md file that defines an AI partner’s behavior through a guided conversation. Clarify communication style, autonomy, honesty, and expectations, then review a concise English profile before saving it with setup_agent.
- Define an AI partner’s initial personality and role
- Adjust tone and how the AI expresses disagreement
- Clarify which decisions the AI can make independently
bytedance/deer-flow☆ 84.2KUpdated Oct 20, 2026
AIエージェントのキャラクター定義ファイルを生成するスキル。ユーザーがキャラクター設定(名前、二つ名、年齢、属性、性格、支配の流儀、口癖、外見、絵文字など)を入力すると、それに基づいてIDENTITY.md、SOUL.md、USER.md、AGENTS.md、TOOLS.md、BOOTSTRAP.md、HEARTBEAT.mdの7つのファイルとavatar.pngを配置したキャラクターディレクトリを作成する。また、agent-identity/README.md にキャラクター情報とアバター画像を追加する。ユーザーが「キャラクターを作って」「新しいキャラクターを追加して」「○○っていうキャラクターのファイル作って」と言った時や、キャラクター設定を詳細に提供した時に使用する。
The English summary is being prepared. Showing the original description.
Sunwood-AI-OSS-Hub/zero-cc☆ 3Updated Feb 17, 2026
Create and manage DESIGN.md as a shared reference for design direction, reusable design values, and visual rules. This catalogue entry introduces the skill; its complete workflow requires installing the upstream bundle.
- Documenting a project's design direction
- Collecting reusable design values in one reference
- Managing visual rules in DESIGN.md
nexu-io/open-design☆ 102.8KUpdated Oct 20, 2026
Create, update, or audit AGENTS.md instructions using evidence from repository files and CI workflows. Preserve maintainer policies while clarifying commands, validation steps, and directory-specific rules that guide coding agents.
- Creating AGENTS.md from repository evidence
- Correcting stale commands and duplicated rules
- Organizing root and package-level instructions
sickn33/agentic-awesome-skills☆ 48.1KUpdated Oct 19, 2026
Review threat mitigations after a development phase is complete and update SECURITY.md with verification results. Use an existing security record or a threat model in the phase plan to guide the review.
- Check security mitigations after completing a development phase
- Audit mitigations documented in SECURITY.md
- Verify completed work against a threat model in PLAN.md
open-gsd/gsd-core☆ 10.7KUpdated Oct 20, 2026
AGENTS.md / CLAUDE.mdの作成・編集・整理を行うスキル。CLAUDE.mdを50行以下を推奨とし、詳細ルールはrules/やスキルにモジュール化して分割管理する。以下のリクエストで使用する: (1)「CLAUDE.mdを作って」「AGENTS.mdを整理して」などCLAUDE.mdの新規作成・編集、(2)「ルールを追加して」「rules/に分割して」などルールの追加・分離、(3)「ディレクトリ構成を更新して」など参照の更新、(4) 新しいディレクトリやルールファイルを作成した後のCLAUDE.md反映。
The English summary is being prepared. Showing the original description.
hukusuke1007/agent-skills☆ 8Updated Sep 12, 2026
Create, update, or audit CLAUDE.md files that introduce a project to an AI agent. Organize its structure, purpose, development commands, and important conventions into concise guidance, with references to detailed documents.
- Creating project instructions for an AI agent
- Shortening an overgrown CLAUDE.md
- Auditing existing project guidance
luongnv89/claude-howto☆ 42.1KUpdated Oct 19, 2026
Reduce the size of AGENTS.md or RESOLVER.md by grouping skills into functional areas. Each area keeps a list of its sub-skills, helping the agent find the appropriate skill through a two-level routing structure.
- Shortening a large AGENTS.md
- Grouping skill routes by functional area
- Checking routing accuracy after compression
garrytan/gbrain☆ 31KUpdated Oct 20, 2026
Write and revise documents that guide AI agents, including skills and AGENTS.md files. Organize steps, define checkable completion criteria, and clarify when to load references so agents can follow a consistent process across different tasks.
- Write or revise instructions for a skill
- Review AGENTS.md or CLAUDE.md guidance
- Move detailed references out of an overloaded main document
vinvcn/mattpocock-skills-zh-CN☆ 5.1KUpdated Oct 20, 2026
Refresh gbrain's searchable code data to match the repository and update agent search guidance in CLAUDE.md. Use it to reindex a project or investigate searches that no longer find the expected code.
- Refreshing search data after code changes
- Reindexing a repository
- Investigating missing code search results
garrytan/gstack☆ 137.1KUpdated Oct 20, 2026
Analyze a codebase and create a CLAUDE.md guide for future Claude Code sessions. Capture build and test commands, explain the overall architecture, and incorporate relevant information from existing documentation and development rules.
- Create a CLAUDE.md guide for a codebase
- Document build, lint, and test commands
- Explain the overall code architecture
asgeirtj/system_prompts_leaks☆ 69.9KUpdated Oct 20, 2026
Create, improve, or audit CLAUDE.md files that introduce AI agents to a project. Review project structure and development commands, keep shared instructions concise, and move detailed guidance into referenced documents, with drafts reviewed before changes are applied.
- Draft project instructions for AI agents
- Shorten an existing CLAUDE.md
- Audit instruction quality without editing files
luongnv89/claude-howto☆ 42.1KUpdated Oct 19, 2026
Check a software module’s folder structure, required README.md and DESIGN.md files, and whether documentation matches the code. Produce a report identifying missing content and issues to resolve before handoff.
- Checking a newly created module before handoff
- Reviewing documentation after refactoring
- Finding missing README.md and DESIGN.md sections
fengshao1227/ccg-workflow☆ 5.9KUpdated Oct 19, 2026
URL・画像・テキスト要件からAIコーディングエージェント向けのDESIGN.mdを生成するスキル。「example.comをDESIGN.md化して」「このサムネをDESIGN.md化して」「クールでポップなLP用のDESIGN.mdを作って」といったリクエストで使用する。Claude Code / Cursor / Stitch に渡せば一貫したUIを生成できる、getdesign.md / awesome-design-md 準拠の9セクション構成のデザイン仕様書を出力する。CSS解析・画像目視抽出・要件生成の3パターンに対応。
The English summary is being prepared. Showing the original description.
hukusuke1007/agent-skills☆ 8Updated Sep 12, 2026
Create or revise skills shipped within the Hermes Agent repository. The guidance covers file placement, required metadata, clear procedures, platform checks, tests, and documentation updates so contributions follow the repository’s authoring standards.
- Add a reusable skill to the Hermes Agent repository
- Revise an existing in-repository SKILL.md
- Choose bundled or optional placement
NousResearch/hermes-agent☆ 255.5KUpdated Oct 20, 2026
Create DESIGN.md files that combine exact design values with explanations for coding agents. Validate file structure and color contrast, compare versions, and export shared design settings to Tailwind or a standard design-token JSON format.
- Turning a style guide into a specification for agents
- Sharing consistent design settings across projects
- Checking color contrast and token references
NousResearch/hermes-agent☆ 255.5KUpdated Oct 20, 2026
Create and edit FreeCAD models using commands for dimension-controlled sketches, solid parts, assemblies, and technical drawings. Check geometry through previews, measure models, and export files for CAD exchange, 3D printing, or documentation.
- Create 3D parts with specified dimensions
- Build assemblies and generate parts lists
- Export dimensioned technical drawings as PDF
HKUDS/CLI-Anything☆ 55.6KUpdated Sep 22, 2026
Create, improve, or audit CLAUDE.md files that explain a project's purpose, structure, and development workflow to AI agents. Organize essential instructions, remove redundant content, and link to detailed documents where needed.
- Creating project instructions for AI agents
- Condensing an overly long CLAUDE.md
- Auditing existing instructions without editing files
luongnv89/claude-howto☆ 42.1KUpdated Oct 19, 2026
Create, improve, or audit CLAUDE.md files that explain a project's purpose, structure, and development workflow to AI agents. Organize essential instructions, remove redundant content, and link to detailed documents where needed.
- Creating project instructions for AI agents
- Condensing an overly long CLAUDE.md
- Auditing existing instructions without editing files
luongnv89/claude-howto☆ 42.1KUpdated Oct 19, 2026
Examine Windows shortcuts and Jump Lists, records of recently used files, to reconstruct user activity. Extract paths, timestamps, and device details with LECmd and JLECmd, including traces that remain after target files are deleted.
- Reconstructing file access and program execution timelines
- Investigating access to files that have been deleted
- Examining traces of removable media use
mukul975/Anthropic-Cybersecurity-Skills☆ 34.8KUpdated Aug 31, 2026