2ykwang
UserSkills for AI coding agents
Categories
Indexed Skills (14)
code-history
Trace the git history of specific code — when a function, pattern, or file was added, modified, or removed, and the intent behind each change. Use when the user asks when or why a piece of code changed, wants the evolution of a function, or needs the commit or PR that introduced a behavior. Read-only; not for plain git log or a single line's last author.
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
docs
Write and maintain project documentation under docs/generated/ — /docs write creates or updates a doc on a topic, /docs check reports stale content, broken code references, and orphan files. Use when the user wants to capture the design intent behind a feature, record an architectural decision, or verify existing docs still match the code. Docs use [symbol](file-path) reference pointers instead of inline code blocks.
html-visual
Generate an interactive single-file HTML visualization — mockup, wireframe, ERD, flowchart, chart, slides, architecture diagram, dashboard, timeline, mindmap, kanban, or table. Use when the user wants something rendered rather than described: a UI mockup or wireframe, a database schema as an ERD, business logic as a flowchart, data as a chart, or content as slides. Also use when they point at a file (schema, spec, data) and ask to see it visualized.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use when deciding whether to add a rule, when you need evidence that an existing rule can be deleted, when picking between two wordings of the same rule, or when checking whether material you placed is actually being read. Triggers on 'does this rule do anything', 'compare before and after adding this', 'can I drop this', 'difference with and without this', 'run an A/B'. Not for application code changes or anything automated tests already verify. Built on Claude Code: it spawns `claude -p` subprocesses to run both arms.
quick-pr
Split a minor change from the current work into a separate worktree and open a PR without interrupting your flow. Use when an unrelated small fix (typo, lint rule, config tweak) is sitting in a feature branch and the user wants it shipped on its own — "quick PR", "split this out", "ship this separately". Requires Claude Code (uses EnterWorktree, ExitWorktree, AskUserQuestion).
ralph-loop-template
Generate an iterable checklist PROMPT file for Ralph Loop from a plan file or the current conversation, and output the ready-to-run /ralph-loop command.
worth-building
Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?", "how should I approach X?", "quick script vs. robust system", "how much architecture?", "how much do I build here?". Fires even without "poc" or "right-size" — any time effort and complexity of what to build are being weighed.
write-pr
Draft a pull request title and body from the current branch's diff and commit history, following the project's PR template and title conventions. Use when the user is about to open a PR and wants ready-to-paste content, or asks to write, draft, or fill in a PR description. Read-only — never opens or pushes the PR.
code-review-report
Turn code changes into a single-file HTML code review report that pairs the diff with context a diff can't show — design decisions, rejected alternatives, tradeoffs, unfinished work — plus prioritized review points. Use when preparing for review after finishing a sizable change, refactor, or feature, or whenever the user asks for a review report, change report, or an HTML summary of their changes.
commit-fixup
Absorb uncommitted working tree edits into the existing commits on the current branch where each change belongs (fixup commits + autosquash rebase). Use on requests like 'fold this into the original commit', 'clean up the commit history', 'squash the review fixes into their commits', 'fixup', 'amend into an existing commit', or when review feedback and polishing edits need to land in the right commit. Not for reordering commits already in history, and not for splitting a commit apart.
commit-split
Split a pile of uncommitted changes into several context-scoped commits. Analyzes the diff first, proposes logical groups and a commit count, and once the user confirms the granularity, stages per file — down to hunks inside a single file when needed — and commits with messages matching the repo's convention. Use on requests like 'split this into commits', 'commit by context', 'atomic commits', 'how should I split these changes', or when uncommitted work mixes several topics (feature + bugfix + config). Not for rewriting already-committed history (rebase, fixup, squash), and not for a single-topic change one commit covers.
create-qa-list
Turn code, specs, a PR, or the current conversation into a QA test-case list a non-developer can read and run, exported as CSV, a shareable HTML report, or both. Trigger when the user wants QA test cases, a test plan, a QA checklist, or a test-case CSV/HTML (e.g. "write test cases for this", "make a QA list"). Output uses behavior-and-scenario language, never code symbols like function names or file paths. Not for writing or running automated test code (pytest/jest), code review, or test-strategy docs.
decision-board
Render an interactive HTML board for the user to pick among multiple comparable options side-by-side at once — engineering trade-offs, copy audits, action-item triage, architecture decisions, policy calls. Returns the picks (and optional hold/note flags) as a JSON file the agent can apply.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.