Skip to main content
Manus에서 모든 스킬 실행
원클릭으로
XiaohanZhao123
GitHub 제작자 프로필

XiaohanZhao123

2개 GitHub 저장소에서 수집된 11개 skills를 저장소 단위로 보여줍니다.

수집된 skills
11
저장소
2
업데이트
2026-07-13
저장소 탐색

저장소와 대표 skills

planboard
소프트웨어 개발자

Browser-reviewable L1 acceptance-spec planning for non-trivial code or data changes. Use when the operator asks for planboard, a plan they can annotate in the browser, or a spec of "what must be true and how we verify it" before code. The Orchestrator runs a GQM intent interview, elicits requirements each fused to an acceptance gate, hardens every gate with a mutation-style attack via Codex sub-agents, then renders an annotatable HTML spec. Do not use for trivial one-file edits, quick questions, or research/docs tasks whose success has no writable verifier.

2026-07-13
verifier-driven-development
소프트웨어 개발자

Verifier-Driven Development (VDD) workflow for non-trivial implementation, rewrite, refactor, simplification, data-pipeline, exporter, adapter, prompt, UI preview, training-format work, failure investigation, review feedback, and completion claims. Use when Codex needs to turn operator intent into explicit contracts, mocks, code verifiers, sub-agent verifier passes, and layered validation before, during, or after code changes.

2026-07-13
shuorenhua
기술 작가

检查和清理中英文文本里的 AI 套路,适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求;按场景控制力度,同时保留事实、术语、语域和责任主体。

2026-06-26
docs-curator
소프트웨어 개발자

At session wrap-up, read the session and the docs and propose a short list of changes — what to ADD (things the human flagged out loud), what to RETIRE (now stale or duplicated), and what has earned a guardrail (PROMOTE to a hook, lint, or code structure). The Curator judges and proposes; the human accepts or rejects; the Librarian applies the survivors. It never reorganizes or deletes unattended.

2026-06-23
docs-librarian
소프트웨어 개발자

Apply the doc changes the human accepted and keep the documentation findable — relocate prose into the right doc, maintain docs/README.md as the index, write the pointers and hooks that make a doc reach an agent at the right moment, and apply small accepted lints. Runs after the Curator. It organizes and wires; it never judges what's worth keeping (the Curator's job) and never loses information.

2026-06-23
wrap
소프트웨어 개발자

End-of-session documentation reconcile. Runs the Curator to propose a short ADD/RETIRE/PROMOTE list, waits for the human to accept or reject, then runs the Librarian to apply only the survivors. Invoke as /wrap when finishing a working session. User-invoked; never auto-run.

2026-06-23
pr-review-tick
소프트웨어 품질 보증 분석가·테스터

One review cycle of the PR review pipeline (Agent A). Designed to be invoked by `/loop /pr-review-tick` inside a long-running tmux daemon session, one per repo. Each tick discovers open PRs that have explicitly opted into the pipeline (via the `[auto PR loop]` marker in title or body), dedups against the (pr_number, head_sha) → review_id map in `~/.local/state/claude-pr-pipeline/<repo>/`, and for each opted-in PR with new content runs a three-angle review — (1) codex GPT-5.5 cross-vendor adversarial, (2) `code-reviewer-opus` user-level Opus reviewer (CLAUDE.md mandated), (3) bespoke Opus PR-coherence pass covering cross-commit / scope / test-completeness / CI / arch-fit / breaking-change angles the per-commit hook can't see — then aggregates findings, posts ONE PR comment, and re-arms via ScheduleWakeup. Sibling skill is `pr-orch-tick` (Agent B, fix + verdict). Use this whenever the user says "start the review daemon", "kick off the PR review tick", "Agent A", or `/loop /pr-review-tick`. NEVER fixes code. NEV

2026-05-12
commit-defense-loop
소프트웨어 품질 보증 분석가·테스터

Defend a `git commit` blocked by the `second-opinion-commit-gate.sh` Claude Code hook (a non-Claude `codex review` on the staged diff). Triage each `[P0]` finding into worth-fixing / wrong-analysis / not-worth-fixing, fix the real ones with regression tests, retry the commit, and loop until it lands clean or you push back via `[skip-review]` with documented reasoning. Use this whenever the user asks to "run a commit defense loop", "fix the second-opinion findings", "address the P0s and retry the commit", "babysit this commit through the gate", "make the hook happy", or whenever a `git commit` tool call fails with `=== second-opinion BLOCKING ===` in stderr — even if the user doesn't name the skill, this is the workflow that turns hook output into real fixes instead of reflexive `[skip-review]` dismissals. Sibling to `pr-defense-loop` but tighter (single turn, no ScheduleWakeup, no /tmp state) because each iteration costs ~60s of hook latency, not minutes of waiting on external bots.

2026-05-11
commit-quality-pipe
소프트웨어 품질 보증 분석가·테스터

Three-stage quality pipeline for landing commits cleanly. Runs Claude's own multi-perspective Opus review, then a `simplify` pass for reuse/quality/efficiency, then runs the Codex / gpt-5.5 second-opinion review as the final gate. Operates in two modes — **Mode A (pre-commit)** runs against a staged diff and ends with `git commit`; **Mode B (post-commit audit)** runs against already-landed commits via `codex review --commit <SHA>` and lands fixes as a follow-up commit. Trigger phrases for Mode A include "ship this commit", "do the pre-commit ritual", "make this commit ready"; Mode B triggers on "audit those commits", "did our commits go through review?", "replay the gate on the recent commits", "run quality pipe on the apply work" (i.e. anything implying retrospective check after commits already landed). Do NOT use when the hook has already blocked a fresh commit — go straight to `commit-defense-loop` for that reactive case.

2026-05-11
pr-defense-loop
소프트웨어 품질 보증 분석가·테스터

Defend a GitHub PR against automated code-review bots (Codex / chatgpt-codex-connector, Claude Code Review, etc.) by triaging each round of comments into worth-fixing / wrong-analysis / not-worth-fixing, applying fixes for the worth-fixing ones, committing, pushing to retrigger review, and looping until the bots stop raising new actionable comments. Use this whenever the user asks to "run a defense loop", "fix all the bot comments", "loop until Codex is happy", "babysit a PR through review", or anything that implies polling a PR, addressing review feedback, and pushing fixes on a cadence. Self-paces via /loop ScheduleWakeup; survives multi-bot setups; handles Codex's re-anchored false positives without chasing them forever.

2026-05-11
pr-orch-tick
소프트웨어 개발자

One orchestration cycle of the PR review pipeline (Agent B). Designed to be invoked by `/loop /pr-orch-tick` inside a long-running tmux daemon session, sibling to `/pr-review-tick` (Agent A). Each tick discovers PRs that have a new review comment from Agent A, spawns a fix worker sub-agent (in an isolated git worktree at `/tmp/orch-<slug>-pr<N>`) following the `pr-defense-loop` triage discipline, applies fixes with `[auto N/4]` tagged commits, and after the worker reports "no more actionable findings" runs the merge-gate verdict — either posting a "would auto-merge" dry-run comment, executing `gh pr merge`, or @-mentioning the user with a summary. Use this whenever the user says "start the orchestrator daemon", "Agent B", "kick off the orch tick", or `/loop /pr-orch-tick`. NEVER reviews PRs (that's Agent A's job). Caps at `max_rounds=4` per PR; refuses to auto-merge external contributor PRs regardless of dry-run state; respects per-PR `flock` so it never collides with Agent A.

2026-05-11
저장소 2개 중 2개 표시
모든 저장소를 표시했습니다