huuanh20/awesome-ai-agent-skills

huuanh20/awesome-ai-agent-skills

Command Claude Code

Explore and debate solutions before writing code — scout codebase, ask clarifying questions, research options, and produce a structured decision report. Ends with → /ck:plan (implement) or /ck:journal (archive). No code is written.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Code review — local uncommitted changes or GitHub PR (pass PR number/URL for PR mode).

huuanh20/awesome-ai-agent-skills

Command Claude Code

Set Claude's coding explanation level for this session/project (-1=Default → 5=God Mode).

huuanh20/awesome-ai-agent-skills

Command Claude Code

Implement a plan phase by phase. Cook never writes or runs tests; every phase requires an APPROVED ck:quality gate before completion. Modes: --fast or --hard. Flag: --tdd. --json selects the phased master plan.json; --plan selects a Markdown plan.md.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Generate a concise FE handoff doc for changed endpoints — branch, APIs, request/response contracts, search params, error codes.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Structured bug-fix pipeline. Scout → Diagnose+Fix → Review → Finalize. Modes (pick one): --fast (trivial errors — skip scout + review), --hard (mandatory review, no auto-approve).

huuanh20/awesome-ai-agent-skills

Command Claude Code

Bootstrap .claude/ configuration for another project — interactive wizard covering bundles, skills, hooks, CLAUDE.md, and .ck.json. Also: --show to print current config, --reset to wipe it.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Extract reusable patterns from the current session and save them as skill files. Run after solving a non-trivial problem.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Generate a phased JSON plan bundle. --spec is preferred but optional; inline feature description is the fallback. --output selects the master plan.json entry point (default plans/ /plan.json).

huuanh20/awesome-ai-agent-skills

Command Claude Code

Plan a feature or system with auto-detected complexity. Modes (pick one): --fast (quick plan → cook), --hard (research + red-team + validate). Composable flag (any mode): --tdd (tests-first per phase). Every phase gets Design Constraints and Quality/Testing State for the mandatory cook quality gate. Always starts with…

huuanh20/awesome-ai-agent-skills

Command Claude Code

Independent quality auditor. --gate blocks a ck:cook phase on architecture/ownership/maintainability findings. --audit , --diff , or --changed audit any target standalone (report-only unless --save). --verify re-checks prior findings. Never edits code or writes tests.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Generate impressive multi-section HTML presentations with parallax, theme toggle, bilingual VI/EN — then auto-capture as 16:9, 9:16, 1:1 social-ready images.

huuanh20/awesome-ai-agent-skills

Command Claude Code

Standalone testing skill. Default analyzes changed scope and runs relevant tests; --unit/--integration/--e2e/--all scope by type; --verify reruns prior failures; --all-phases sweeps every completed phase. --tdd --prepare /--tdd --verify bracket ck:cook for red-green TDD. Never edits production code; blocks until the…

huuanh20/awesome-ai-agent-skills

Command Claude CodeCursor

/review — Request code review.

huuanh20/awesome-ai-agent-skills

Command Claude CodeCursor

/srs — Run full SRS pipeline.