- Skills
- 19
- 仓库
- 1
- 职业覆盖
- 2
- 场景覆盖
- 4
- Stars
- ★ 5
TINHTUTE 的 Skills 19
read
Search the web and fetch URLs or PDFs as clean Markdown via a privacy-first cascade (local, gh, TinyFish/Firecrawl/Exa, opt-in proxy). Use to read, cite or save a URL. Not for repo files.
mono-write
Polish a research or learn draft (EN/VI) so it reads naturally, and write CHANGELOG entries and release notes from a commit list. Not for UI copy, marketing or tone changes.
librarian
GitHub code research via gh CLI, no cloning. Use to investigate external repos, find where a symbol is defined, or gather cited evidence and usage examples from GitHub.
git
Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.
work
Execution orchestrator after `brainstorm` (and `to-plan` for high-risk). Runs phases wave-by-wave from locked artifacts, verifies each task, and hands off to `check`, `git`, or `handoff`.
wayfinder
Chart a Goal too fogged for one session as a decision map in the active plan, settle one decision per session, then hand it to brainstorm lock. Use when grilling shows the work spans sessions.
watzup
Recap: read branch state, committed + uncommitted changes, handoff context, and artifact chain — then recommend the next action.
to-plan
Generate the approach, phases, waves, and checks inside the locked `.harness/plans/active/{slug}.md`. Use after `brainstorm` for a `high-risk` plan; a `normal` plan goes straight to `work`.
retro
Session retrospective: evidence-cited, severity-ranked findings about the agent's environment, then one user-approved fix — a guard or a rerun-gated experiment. Invoke only from a poteto playbook step or when the user asks for it by name.
handoff
Prospective: persist current session state into the active plan's Current State section so the next session can resume without context loss.
grill
Grill a fuzzy idea or a plan, one round of decisions at a time, until the Goal could lock. Writes nothing. Use for grill/interview/stress-test requests and before locking an unclear Goal.
check
Pre-commit and pre-merge gate. Runs tests, lint, build, then reviews security, performance, architecture, and code quality. Acts as the phase gate after `/work`.
brainstorm
Explore trade-offs and lock the Goal into `.harness/plans/active/{slug}.md`, including a decided `wayfinder` map. Use for ideation, architecture decisions, and RFC/PRD-to-spec work.
think
Reason hard before building: attack premises, run named thinking lenses, compare real alternatives, give one verdict. Use for design choices, is-it-worth-it, triaging asks. Not for bugs.
learn
Research an unfamiliar domain from primary sources into notes or a publish-ready draft, keeping contradictions visible. Use for deep dives. Not for one-URL lookups (use read).
hunt
Find the root cause before any fix: build a red-capable repro loop, rank falsifiable hypotheses, prove, fix, sweep siblings. Also triages bug issues/PRs. Use on errors, crashes, regressions.
arena
Design bakeoff: sub-agents build one artifact several ways, a rubric picks the base, the best parts of the rest are grafted on. Use when the right design is unclear.
ambition
Rewrite a task so it is done to a field-leading standard through one lens (depth, altitude, range), then lint the rewrite for raw material, instruments, a refutable assumption and an outside judge. Use for 'be ambitious', 'make this deeper', 'what would an expert do'.