Claude Skills by jckeen

Inspect and clean stale branches across multiple repositories using the dotfiles git-hygiene + gh-bootstrap toolchain. Use when the user asks about branch state, stale local branches, or "no ref was fetched" errors.

Update a project CHANGELOG.md or equivalent session log with concise notes about completed changes, decisions, and known issues.

Drive a native Claude Code installation as the implementer for requested software work while you own the outcome. Brief it from a prompt file, run it through the bundled evidence-recording runner, inspect the real diff and checks, send follow-ups into the exact same session, and finish only the delivery the user actually authorized. Use when the user asks you to run Claude, act as Claude's operator, or build something through Claude Code. Not for ordinary questions about Claude, not for work ...

Commit current work, push the branch, and create a GitHub pull request with a concise title, body, and verification notes.

Decompose substantial engineering work into explicit prerequisites, bounded workstreams, atomic acceptance criteria, and self-contained agent prompts. Use when the user asks to decompose, wants to review an execution plan before implementation, or needs a safe parallelization design for a multi-area task.

Bootstrap or audit a repository documentation contract, classify Markdown truth surfaces, migrate shadow trackers to GitHub issues, and reconcile stale operational facts. Use when the user says drift sweep, asks whether docs are stale, retires or renames a process, wants a .doc-contract, or is preparing a launch.

Pick up a GitHub issue or issue-like bug report end to end: investigate, reproduce when useful, implement, verify, commit, push, and prepare a PR when requested.

Generate a concise session handoff for resuming work later, including current state, decisions, open issues, and next steps.

Coordinate complex engineering work end to end with proportional planning, explicit acceptance criteria, isolated delegation, implementation, verification, adversarial review, and durable handoff. Use when the user asks to orchestrate, go all-in, use subagents or parallel agents, execute a multi-workstream task, run a maximum-effort pass, or carry a substantial issue or PR through completion.

Produce a read-only repository health briefing covering stack, git state, setup, tests, dependencies, blockers, and next steps.

Review recent or specified code changes for correctness, security, quality, and missing verification. Use when the user asks for a review, pre-ship check, PR review, or quality/security pass.

Propose one to three durable improvements to the shared agent toolset after meaningful work, including skill triggers, workflow gotchas, canonical instructions, parity gaps, and stale memory. Use when the user requests a retro, when a skill failed to trigger, after a notable workflow discovery, or at a genuine successful stopping point. Propose first and never edit without confirmation; unattended runs write proposals for later review.

Review and simplify recently changed code by removing unnecessary complexity without changing behavior. Use when the user asks to simplify, reduce over-engineering, clean up a patch, or make code easier to maintain.

Use when handed a runtime or browser verification task: prove a change actually works end-to-end in a running app, adversarially. Requires the Playwright MCP server (global mcp_config). Produces a verdict plus evidence other agents can audit.

Run an automated code review using your regular Antigravity subscription plan. Use when the user asks for a Gemini/Antigravity review, a second opinion on recent changes, or /antigravity-review. Reviews the working-tree diff for bug risks, boundary-condition errors, security issues, and over-engineering — the Gemini sibling of the Codex review gate.

Inspect and clean stale branches across multiple repositories using the dotfiles git-hygiene + gh-bootstrap toolchain. Use when the user asks about branch state, stale local branches, or "no ref was fetched" errors.

Records what changed this session into a CHANGELOG.md at the project root — reads git log since the last entry and prepends a dated entry (What changed / Decisions made / Known issues), then commits it. Use when the user explicitly wants to log/record changes — "update the changelog", "log this session", "add a changelog entry", "record what we did". For preserving context across /clear or a new session use handoff instead; for improving your skills use session-retro.

Starts a Claude Code remote-control server via `claude remote-control --spawn worktree`, running in an isolated git worktree so remote work doesn't touch local changes, and returns the connection info for claude.ai/code and the Claude mobile app. Use when the user wants to control this project remotely, asks to "start the remote server", "connect from my phone/mobile", "access this from claude.ai", or "spin up claude-server".

Commit, push, and create a PR in one shot — Boris Cherny's most-used daily command

Deep task decomposition into parallel workstreams with self-contained agent prompts. Use when you want to review the execution plan before committing to it.

Bootstrap a repo's doc contract or audit doc drift — declares every markdown surface (LIVING/GENERATED/SOURCE/HISTORICAL), wires the CI doc-truth checker, migrates shadow trackers to GitHub issues, and reconciles out-of-band drift (closed issues, migration high-water marks, stale PRs, ghost worktrees). Use when the user says "drift sweep", "bootstrap the doc contract", "are these docs stale", after a rename or process retirement, or pre-launch.

Pick up a GitHub issue, investigate, implement the fix, test, and create a PR

Generate a handoff note for clean session transitions — preserves context across /clear or new sessions. Use when ending a session, when context is getting high, or when the user says "hand off", "wrap up the session", or "save state for next time".

Drives jujutsu (jj) version control on the user's behalf so they don't have to memorize commands. Use for single-agent feature work (the default), whenever the user mentions jujutsu/jj, when undo-safety or a clean rewritable history matters, or when starting/finishing a change in a jj-managed repo. For MULTI-agent parallel work use git worktrees (or jj workspaces) instead — see "jj vs worktrees" below.

Scaffolds a new project in the current directory — creates CLAUDE.md, CHANGELOG.md, .gitignore, README.md, and a source dir, initializes git with a first commit, and offers to create a GitHub repo. Prompts for project name, description, and language/framework first. Use when the user wants to "start a new project", "bootstrap a repo", "set up a fresh project", "scaffold a codebase", or "kick off" a new build from scratch.

Records a recurring failure into ERRORS.md — classifies it (hallucination, instruction-ignored, context-lost, wrong-tool, incomplete, external), captures the goal, exact error, attempts tried, root cause, and lesson, then commits it; also logs wins on request. Use when the same error keeps recurring, an approach repeatedly fails, the user says "log this error", "document this failure", "this keeps happening", or "log that as a win" after a success.

Full-lifecycle orchestration for comprehensive execution — selects relevant skills, delegates bounded work, then simplifies, completes documentation, verifies, reviews the final artifact, and delivers with a durable handoff. Use when you want maximum effort, to go all-in, or to orchestrate a big task end-to-end.

Multi-agent review-gate mechanics for repos shared with Codex and Antigravity — which gate lane a change requires, how to run and check a receipt, the handoff payload (claim to disprove + exact repro), review independence, and persisting verdicts. Use before running any review gate, before handing work to another agent, before merging, or when a gate refuses a receipt.

Read-only review of recent git changes (diff since the last review/tag) for correctness, security, and quality — flags edge cases and missing boundary error handling, hardcoded secrets, injection risks (SQL/XSS/command), sensitive data in logs, over-engineering, and dead code, then returns a prioritized checklist. Reports only; does not edit — to actually apply simplifications use simplify. Use when the user asks to "review my changes", "check this before I ship", "look over the diff", "is th...

Runs a short retrospective that PROPOSES edits to the user's Claude Code skills — capturing a newly-found gotcha, fixing a description that didn't auto-trigger, retiring a dead skill, or extracting a reusable pattern into a new skill. Improves the TOOLSET, not the session log. Use when the user signals satisfaction at the end of real work ("thanks", "thanks that worked", "that worked great", "nice", "perfect", "exactly what I needed"), or when they explicitly run /session-retro. Always propos...

Review recently changed code for unnecessary complexity and edit it in place to simplify — removes over-engineering, dead code, and premature abstractions while preserving behavior. Unlike review (which only reports), this applies the changes. Use after building a feature, or when the user says "simplify this", "this feels over-engineered", "clean this up", or "de-engineer".