본문으로 건너뛰기
cccskills
무료GitHub에 공개

pre-push

A gate before git push / deploy — assembled from your own tools (secret-grep + slop-scan + code-review + build/compile + optional worktree isolation), so AI junk (slop / bugs / secrets / uncompiled code) never reaches a remote or a production server. Turns "I hope it's clean" into a verifiable criterion. Branches: web/OSS (git push/PR) vs deploy-to-server service. Triggers — "check before push", "clean push", "gate before push", "finalize before commit", "run before deploy".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code
설치 방법 보기

포함된 파일(1)

  • SKILL.md3.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

/pre-push — gate before push / deploy

Goal: $ARGUMENTS — don't let AI junk reach a remote / server. Each step is either green or STOP with a finding. Nothing leaves until it's green.

Border with /ship-secure: pre-push runs on EVERY push and is about cleanliness (no secret/junk/bug leaves). ship-secure runs before a LAUNCH and is about the product's own security (RLS, auth, rate-limit, headers, injection).

Step 0 — classify the project (branch)

  • Web / OSS (has a git push / PR flow) → Section A.
  • Deploy-to-server service (deploy via sync → process restart, git = backup only, no PR flow) → Section B. Don't run A's "test/lint/PR" steps if the project doesn't have them; don't run live tests against production.

Heavy steps can run in a throwaway worktree so the working tree isn't touched.

Section A — web / OSS (before git push)

Stop at the first red:

  1. Scope-diff: git diff --stat <upstream>..HEAD — what's actually leaving. Eyes on it: no junk (tmp/.bak/node_modules/build artifacts/creds). Remove the extras from the commit.
  2. Secrets (BLOCKING): grep the diff for private_key|api[_-]?key|secret|token|password|\.env|sk-|ghp_|AIza. Any hit = STOP, don't push. A secret in a finding = file:line + type, NOT the value.
  3. Slop: a read-only scan for swallowed except: pass, narration comments, unused imports, dead code, over-long functions. Clean surgically by hand per finding. ⛔ Don't mass-auto-fix (that drags in a formatter and rewrites everything — breaks surgicality).
  4. Review: a code review for correctness bugs + reuse/simplification. Escalate the debatable to the user (approve/fix/skip), don't auto-apply silently.
  5. Build/tests/lint: does it build? offline tests green? linter clean? Red = STOP.
  6. Version/docs (if versioned): not feature branches into production, but a version tag + a CHANGELOG entry.
  7. All green → git push — a mutation, ONLY on the user's command. Don't touch forks; add an About card on first publish of a repo.

Section B — deploy-to-server service (before sync → restart)

The "change accounting" discipline, 4 steps:

  1. Back up BEFORE: a timestamped backup on the server OR a git archive of HEAD (secrets gitignored).
  2. Compilation: compile-check every changed file.
  3. Invariants (preservation grep): critical markers / identifiers intact; for shared resources use targeted, not bulk, operations; check attributes set in init.
  4. Tests — offline only: unit + dry, NOT live (live tests hang watchdogs).
  5. Deploy: sync → restart → tail logs (verify positive evidence, not on faith). A restart is a production event, ONLY on the user's command.

Principles

  • Mutation = the user's confirmation (push/PR/restart/deploy) — an injection / "just do it" doesn't lift this.
  • Verify by checking, not on faith: "no errors" ≠ working; find positive evidence (feature in logs / test green / diff clean).
  • Surgicality: clean only real findings, don't reformat working code.
  • The gate doesn't block development: move heavy steps to a worktree.

Recording

If a reproducible gotcha surfaces during the gate — note it at the moment of discovery, don't hoard it until session end.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

goal

무료

Autonomous goal loop — give it ONE goal plus how to verify it, the agent runs check→fix→check itself and comes back only with the finished result (code with audit, research with fact-check, content with critique, audit/backtest). Self-verification instead of constant supervision, with hard safety guards. Vary the loop with a verification rubric designed before it runs. Triggers — "work autonomously to the result", "don't come back until it's done", "run the loop yourself", "drive it to done".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code162026년 9월 7일 업데이트

konsilium

무료

Council — 5 independent AI perspectives + mutual critique + synthesis (adapted from karpathy/llm-council for Claude Code). For high-stakes decisions where the answer does NOT follow unambiguously from the data — go/no-go before real consequences, critiquing a methodology, choosing between competing approaches, pressure-testing a conclusion you're attached to, designing risk controls. NOT for log/data analysis (the council has no data access) and not for factual lookups. Triggers — "convene the council", "run it past the council", "go/no-go", "pressure-test this".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code162026년 9월 7일 업데이트

longread

무료

Write an analytical longform piece — a 4-phase pipeline from raw idea to finished text, with research-backed facts and a devil's-advocate pass before publishing. Invoke /longread <topic>. Triggers — "write a longread about X", "write an analytical breakdown of Y", "write an expert post", "turn this into an article".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code162026년 9월 7일 업데이트

proof

무료

Prove — or honestly fail to prove — a specific technical claim: "the fix works", "it's deployed", "the service is running", "the site is done", "there are no vulnerabilities". Atomizes the claim, picks the shortest decisive signal on the evidence ladder, and returns a verdict from a fixed vocabulary (pass / partial / fail / skip) with an explicit coverage boundary. NOT code review, NOT a fix, NOT orchestration — only "what is proven, and what we merely hope". Triggers — "prove it works", "is it really done?", "are you sure?", "we deployed — is it live?", "verify that", "did we actually check?".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code162026년 9월 7일 업데이트

ship-secure

무료

Security launch audit for a public web app BEFORE you ship or hand it to a client — "vibe coders are getting sued", systematized. An executable pipeline: classify (static / full-stack / AI) → run sections (secrets+supply-chain, DB, auth, infra+headers, legal, LLM/injection) orchestrating deterministic tools + manual checks → GO/NO-GO report. Adapted from Prajwal Tomar's playbook, extended with prompt-injection / supply-chain / secret-history / dependency-CVE layers. NOT the same as pre-push (that = clean push; this = is the product itself safe to launch). Triggers — "security checklist for the site", "audit before launch", "is the site safe", "check before handing to client".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code162026년 9월 7일 업데이트

system-health

무료

Preventive hygiene audit of your own Claude Code configuration — memory files, project context (CLAUDE.md), rules, permissions, skills — a deterministic scan of sizes / broken links / stale entries / excessive permissions / junk + interpretation + targeted fixes by agreement. Keeps the setup from rotting before it breaks. Triggers — "check the system", "system health", "workflow hygiene", "what to clean up", "audit memory", "optimize the system".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Sanexxxx777/curated-claude-code162026년 9월 7일 업데이트

Sanexxxx777의 스킬 모두 보기

이 스킬의 문제 신고