Loading...
Loading...
Found 2,001 Skills
ローカル改修した `.agents/skills/<skill-name>/` を upstream リポジトリ (Fandhe-AI/agent-cli-skills 等) へ PR として投稿する。`skills-lock.json` の `source` を読み、`Fandhe-AI/` 以外への push は安全弁で中止。clone → 反映 → セキュリティチェック → ブランチ作成 → push → `gh pr create` を実行。マージ後は sync-skills-lock で hash 更新。「スキルを upstream に貢献」「外部リポジトリに PR」などで使用。
Execute web cache deception attacks by exploiting path normalization discrepancies between CDN caching layers and origin servers to cache and retrieve sensitive authenticated content.
Implement identity and access management. Use when designing authentication, authorization, or user management. Covers OAuth2, OIDC, and RBAC.
Electron cross-platform desktop apps with web technologies. Use for desktop apps.
Use when user says "create workflow", "create a workflow", "design workflow", "orchestrate", "automate multiple steps", "coordinate agents", "multi-agent workflow". Creates orchestration workflows from natural language using Socratic questioning to plan multi-agent workflows with visualization.
CVE vulnerability testing coordinator that identifies technology stacks, researches known vulnerabilities, and tests applications for exploitable CVEs using public exploits and proof-of-concept code.
Use AddressSanitizer to detect memory safety bugs in C/C++ programs. Identifies use-after-free, buffer overflow, memory leaks, and other memory errors.
Security-related rules for Tauri application development.
Defines evaluation criteria and scoring methodologies for deliverable assessment
Performs comprehensive PR code review from 5 perspectives (quality/performance/tests/docs/security) in parallel, providing Blockers/Suggestions/Nice-to-have and merge decision. Args: /review [owner/repo] [pr-number] [--focus all|security|perf|qa|docs|types] Activates when user mentions "review", "PR確認", "コードレビュー", "マージ判定".
Secure credential management for trading platforms
Deep code audit that finds dead wiring, silent failures, unfinished features, placeholder stubs, bloated files, and unnecessary complexity. Produces an actionable report with file:line references grouped by severity. Think of it as a senior dev doing a thorough PR review of the entire codebase. Triggers on: "code review", "audit the code", "review the code", "find dead code", "find placeholders", "check for stubs", "prune the code", "code cleanup", "implementation review", "completeness check", "find unused code".