Git 与版本控制
Git 操作、提交助手与分支管理
magento-local-environment-specialist
maxnorm
Sets up and manages local Magento 2 development environments. Use when setting up local development, configuring local environments, or troubleshooting local setup issues. Masters local development tools, Docker, and development environment optimization.
crap4clj
unclebob
Use when the user asks for a CRAP report, cyclomatic complexity analysis, or code quality metrics on a Clojure project
voice — TTS & STT tool for AI agents
rgbkrk
Requires macOS with Apple Silicon, Git LFS, and Rust 1.85+. TTS model weights download on first voice say (~312MB, cached). STT model weights download on first voice listen (~246MB, cached).
commit-push
Mitscherlich
当用户要求"提交代码"、"commit"、"推送代码"、"push"、"提交并推送"、"提交变更"、"推送到远程"、"帮我提交一下"、"把代码推上去"时，应使用此技能。此技能提供规范化的 git 提交与推送工作流，自动分析变更内容、生成符合规范的提交信息并执行相应操作。
frontend-design
fairchild
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
unblock-auto
leodearden
"Autonomous dry-run version of /unblock. Investigate a blocked orchestrator task and emit a proposed action — read-only. Use this skill when you need to automatically assess a blocked task without human interaction. Never modifies any state; only reads worktree artifacts, git history, and task metadata to produce a structured proposal for review."
/do — package this decision, then execute it in a fresh context
leodearden
"Hand the direction just agreed in this conversation off to a fresh context for autonomous execution. ONLY runs when the user explicitly types /do — never auto-invoke it. Enters plan mode, distills the whole preceding discussion into a self-contained plan, and appends the user's fixed execution protocol (implement in a worktree → /merge-queue → /reflect) so the plan runs end-to-end after 'Clear Context and Follow Plan'."
unblock
leodearden
"Unblock a stuck orchestrator task — whether blocked on review issues, merge failures, or agent escalations. Use this skill when the user mentions a blocked or stuck task, wants to resolve review issues in a worktree, handle an escalation for a specific task, or says things like 'unblock task 64', 'task 107 is stuck', 'fix the review issues', or '/unblock <number>'. Also trigger when the user references a specific task number alongside words like 'blocked', 'stuck', 'failed', 'escalated', or 'review issues' — even if they don't say 'unblock' explicitly."
warm
leodearden
"Claim a warm, CoW-seeded git worktree for ad-hoc interactive work — 'put me in a warm worktree now' for work that doesn't go through /do. ONLY runs when the user explicitly types /warm — never auto-invoke it. Claims an _iact-* worktree on a task/<slug> branch via the escalation MCP's claim_warm_worktree, whose target/ build cache is seeded from the orchestrator's warm base so the first build recompiles near-zero; cold-falls-back to a plain EnterWorktree worktree (never errors) when the orchestrator/escalation MCP is unreachable or the claim fails."
unblock-low-risk
leodearden
"Autonomous, NON-INTERACTIVE unblock of a single blocked task — but ONLY when the orchestrator's at-block-time dry-run investigation labelled the fix risk_label == 'low'. This is the unattended counterpart to /unblock, built for AFK windows: the L2 escalation-watcher launches it as a sub-agent (no terminal) for task_failure/review_issues escalations whose latest metadata.dry_run_proposals[-1] is low-risk and fresh. It re-derives the fix from the proposal prose, applies it scoped to files_referenced, runs the project verify suite, and merges via the orchestrator merge queue — aborting cleanly (leaving the escalation pending for a human) on ANY doubt: non-low risk, stale proposal, scope creep, rebase conflict, verify failure, or a merge-queue result other than done. A merge the worker has already picked up and is still live at the polling ceiling is handed back to the watcher (outcome handed_off), never cancelled. It NEVER touches main directly, never --no-verify, never retries. NOT for: medium / human-review-required proposals, interactive unblocking (use /unblock), any task without a low-risk dry-run proposal, or post-merge-red-main fix-forward tasks (block reason starts with 'Post-merge unscoped type-check failed' — b3_gate.check_proposal hard-ABORTs this entire class regardless of risk_label; see task 1680)."
merge-queue
leodearden
"Merge a task branch to main via the orchestrator's merge queue using the submit→poll protocol. Use this skill whenever you need to merge a completed task branch into main and the orchestrator might be running — it submits via merge_request(wait_secs=100) then polls merge_status until the outcome is terminal, preventing races without blocking indefinitely. Trigger this when an agent says 'merge to main', 'submit merge', 'merge task branch', finishes fixing a blocked task and needs to merge, or any time code on a task branch is ready to land on main. If the escalation MCP isn't reachable, the skill falls back to direct merge. Prefer this over raw git merge --no-ff whenever working in the dark-factory repo."
orchestrate
leodearden
"Implement software from a PRD or task tree using the dark-factory orchestrator. Use this skill when the user wants to: run the orchestrator against a PRD, check orchestrator/task status, resolve blocked tasks, resume stalled work, or manage concurrent TDD workflows. Trigger on mentions of PRDs, orchestrating implementation, running tasks through the pipeline, checking task status, or resolving blocked/failed tasks — even if the user doesn't say 'orchestrator' explicitly."
architect-diagnose-errors
iterate
Diagnose error spikes and exception clusters with Cloudflare + PostHog evidence.
code-review
iterate
Review a selected set of code changes against provided rules, check rule-by-rule compliance, propose refactors and solutions, and write a consolidated markdown report. Use when the user asks for a code review, rules compliance review, or refactor recommendations for a change set.
recreate-production
iterate
Capture or restore a selected OS project after a deliberate proof-of-concept production erase.
secrets-gitleaks
AgentSecOps
Hardcoded secret detection and prevention in git repositories and codebases using Gitleaks. Identifies passwords, API keys, tokens, and credentials through regex-based pattern matching and entropy analysis. Use when: (1) Scanning repositories for exposed secrets and credentials, (2) Implementing pre-commit hooks to prevent secret leakage, (3) Integrating secret detection into CI/CD pipelines, (4) Auditing codebases for compliance violations (PCI-DSS, SOC2, GDPR), (5) Establishing baseline secret detection and tracking new exposures, (6) Remediating historical secret exposures in git history.
sast-bandit
AgentSecOps
Python security vulnerability detection using Bandit SAST with CWE and OWASP mapping. Use when: (1) Scanning Python code for security vulnerabilities and anti-patterns, (2) Identifying hardcoded secrets, SQL injection, command injection, and insecure APIs, (3) Generating security reports with severity classifications for CI/CD pipelines, (4) Providing remediation guidance with security framework references, (5) Enforcing Python security best practices in development workflows.
cairo-security
keep-starknet-strange
Use when reviewing Cairo contracts for security — common vulnerabilities, audit patterns, production hardening, Cairo-specific pitfalls, L1/L2 bridging safety, session key security, precision/rounding bugs, static analysis tooling. Sourced from 50+ public audits and the Cairo Book.
cairo-optimization
keep-starknet-strange
Improves Cairo performance after correctness is established. Trigger on "optimize", "gas usage", "reduce steps", "profile", "BoundedInt", "storage packing", "benchmark". Guides profiling, arithmetic optimization, and bounded-int hardening.
jj-history-investigation
edmundmiller
Investigate jj commit history, split commits, annotate file changes, and clean up redundant commits. Use when debugging history, splitting large commits, or explicitly authorized history rewrites.
done
edmundmiller
Lands finished Git worktrees or jj workspaces, publishes, proves remote equality, and cleans up.
tdd
edmundmiller
"Write behavior-first tests in small vertical slices, with separate regression-test and fix commits for bugs."
jj-merge-repos
edmundmiller
Merges two separate Jujutsu (jj) repositories into one. Use when combining repos, rebasing one repo onto another, or recovering from diverged histories.
initializing-memory
edmundmiller
Comprehensive guide for initializing or reorganizing agent memory into a deeply hierarchical file structure. Use when running /init, when user asks to set up memory, or when memory needs a major reorganization. Trigger phrases: "initialize memory", "set up memory", "populate memory", "build my memory", "memory init".