菜单
Ships working changes: stage, commit, create PR via gh. Accepts --merge to squash-merge after PR creation, and --dry-run to preview without executing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Returns the file path of the current session's JSONL log. With --stamp, adds provenance (session path + timestamp) to a file as YAML frontmatter (default) or HTML comment (--back). Use when a skill or agent needs to reference or annotate the current conversation's log file.
Onboarding interview for the personal development harness. Scans background/ for pre-loaded materials (code, resumes, writing, transcripts), runs a conversational interview to discover background, goals, current skills, and learning preferences, then generates a personalized CLAUDE.md and initial current-state.md. Use when setting up a new learner, onboarding, or bootstrapping the harness.
Cross-session learning pattern analysis. Reads multiple session logs and learning state to detect stalls, regressions, goal drift, and arc readiness that no single session review can see. Proposes updates to learning state files. Use when the user asks "how am I doing", "review my progress", "am I improving", or "progress review". Also dispatched automatically by startwork when enough sessions have accumulated.
Returns a structured learning-state diff from session evidence without quizzing or writing files. Callers (session-review, startwork, or the user's main context) handle presentation, approval, and writes. Use when learning state is stale, before startwork, or when the user wants to update scores without a full session review.
Discovers Claude Code conversation sessions on the local machine within a date range. Returns a structured manifest of sessions with metadata. Use when a skill or agent needs to find prior conversations — e.g., session-review gathering evidence, progress-review windowing, or startwork checking recent activity. Not user-facing; designed as infrastructure for other skills.
Audits Claude Code security configuration against the Safer YOLO guide. Checks sandbox, deny rules, hooks, DCG, and gitleaks. Surfaces findings in plain language with customized recommendations. Use when the user mentions YOLO mode, bypass permissions, skipping permissions, "dangerously-skip-permissions", security setup, or wants to harden their configuration.
| name | git-ship |
| description | Ships working changes: stage, commit, create PR via gh. Accepts --merge to squash-merge after PR creation, and --dry-run to preview without executing. |
Stage → commit → push → PR in one invocation.
| Flag | Effect |
|---|---|
--merge | Squash-merge the PR and delete the branch after creation |
--dry-run | Show the plan without executing |
Run simultaneously:
git statusgit diff --stat (staged + unstaged)git log --oneline -5git branch -agit rev-parse --abbrev-ref HEADmain or master)gh pr view --json state 2>/dev/nullGate: if current branch already has an open PR, stop. Report: "Branch already has an open PR. Create a fresh branch for new changes."
Gate: if on main/master, stop. "Cannot ship directly to main. Create a feature branch first."
Never stage .env, credentials, or secrets files.
On feature branch + changes fit → stay
On feature branch + changes don't fit → find or create matching branch
Finding a match: scan local and remote branch names. Confirm with user before switching.
Creating: generate a descriptive slug (e.g., fix-auth-redirect).
Confirm name with user. git checkout -b <slug>.
git add <file1> <file2> ... — name each file explicitlyCo-Authored-By: Claude <noreply@anthropic.com> trailerUse AskUserQuestion: "Ready to push and open PR for <branch>."
Options: Push / Abort. On abort, stop.
After confirmation:
git push -u origin <branch>gh pr create — inferred title from branch name and commits, brief
body summarizing changes. Report URL.gh pr merge --squash --delete-branchgit checkout <default-branch> && git pull origin <default-branch>git add: explicit file names only — never -A, ., --allgit commit: stage first — never -a / --allgit push: only to origin — never to other remotes--merge flag