Git 与版本控制
Git 操作、提交助手与分支管理
ocas-finch
indigokarasu
'OCAS self-improvement orchestrator (Darwin''s finch — adaptive evolution).
nix-profile-manager
YPares
Expert guidance for agents to manage local Nix profiles for installing tools and dependencies. Covers flakes, profile management, package searching, and registry configuration.
working-with-jj
YPares
Expert guidance for using JJ (Jujutsu) version control system. Use when working with JJ, whatever the subject. Operations, revsets, templates, debugging change evolution, etc. Covers JJ commands, template system, evolog, operations log, and interoperability with git remotes.
using-git-worktrees
CommandCodeAI
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
using-fastlane-in-flutter-and-ci
rodydavis
Automate Flutter app builds and deployments to both the App Store and Google Play using Fastlane with this step-by-step guide.
automate-flutter-app-releases
rodydavis
Automate your Flutter app releases to beta or production with this handy shell script that handles version bumping, formatting, cleaning, rebuilding, and deployment via Fastlane.
install-flutter-from-git
rodydavis
Install Flutter SDK via git clone and configure for all platforms
how-to-manage-multiple-flutter-versions-with-git-worktrees-and-z
rodydavis
Manage multiple Flutter versions efficiently using Git worktrees, eliminating the need for external version managers like FVM.
task-ledger
cq-guojia
本地任务台账，跨会话记录在办任务的归属、进度与起止。当用户要登记一件新的事（新建任务 / 建个坑 / 这活我领了）、记录已有任务的进展（接着做 / 记一条进展 / 这轮先记下）、查看任务状态或历史（现在该做什么 / 这活谁在做 / 上周做过什么）时加载；对某个具体任务要求结案或退回时，只认用户的明确指令；只是改代码、讨论方案时不要用。
addressReview
jthorare
Address PR review comments by spawning domain-specific implementation agents in parallel. Reads from ~/.agentic-workflow/<repo-slug>/reviews/<pr>.json as source of truth, merges any new human GitHub comments, implements fixes, and updates the state file. Can be re-run to continue the review loop.
modular-go
PsiACE
Practical guidance for Go package design with minimal public APIs, single-responsibility boundaries, stateless-first flow, one-way state transitions, and orchestration-to-capability separation. Use when creating, refactoring, or reviewing Go architecture, package boundaries, interfaces, handlers, managers, builders, and execution flows.
push
ballred
Commit and push vault changes to Git with smart commit messages. Auto-stages files, creates meaningful commits, and syncs with remote. Use after making vault changes or at end of day.
review
IgorGanapolsky
Run a Codex review from Claude Code against the current uncommitted work, a base branch diff, or a specific commit. Use when the user explicitly asks for a Codex review or second reviewer.
Multi-Repo Coordination with Polygraph
nrwl
Only complete sessions when asked â Only call cloud_polygraph_complete_session when the user explicitly requests it. Do not automatically complete sessions.
chimera-write-the-check-before-the-code
brcampidelli
A criterion written after the implementation describes the implementation. Write the failing check first, watch it fail, then build.
fleet-coordination
IgorGanapolsky
Mandatory coordination contract for ANY agent working in IgorGanapolsky/ThumbGate. Runs automatically at session start (SessionStart hook). Before mutating shared repository or vault state, verify no other live agent owns this checkout, has an active vault claim on ThumbGate, or holds a Linear issue covering the same work. Invoke whenever you are about to edit shared files, create branches/worktrees, push, open a PR, or touch ~/Documents/AI-Agent-Sync. Prevents same-repo collisions (files deleted under a live agent, claims overwritten, work lost).
specToProvenPR
jthorare
Use when turning an approved spec or design doc into production-ready pull requests that are definitively proven to work in the running app. Use for staged multi-phase builds where each stage must be planned, implemented, tested by hand in the running app, evidenced, and only then driven to zero blocking review findings. Triggers include "take this spec to PRs", "ship this design", "prove it works then open the PR", staged epic delivery, and review-loop-until-clean. Also use when tempted to stop a review loop early, treat green tests as proof, or defer findings to a follow-up.
definition-of-done
musterd-io
What "done" has to mean before anyone says it — docs, traces and an eval as peers of tests, landed verified against the trunk rather than assumed, and a second party claiming it back. Use when finishing a task, defining a team's done, or when "done" and "merged" have started to drift apart.
seat-workspace-identity
musterd-io
Give every agent its own workspace with its own git identity, so "who wrote this commit" is answerable without asking anyone — and know the exact line where that goes wrong, because repo-local git config is shared across work trees and the last one written owns everybody's commits. Ships a checker that tells a scoped identity from a shared one. Use when running more than one agent on a repo, when commits carry the wrong author, or when setting up agent workspaces.
conventional-commits
bastos
Format commit messages using the Conventional Commits specification. Use when creating commits, writing commit messages, or when the user mentions commits, git commits, or commit messages. Ensures commits follow the standard format for automated tooling, changelog generation, and semantic versioning.
thumbgate-guard
IgorGanapolsky
Turn the agent's most recent mistake into an enforced ThumbGate prevention rule (a PreToolUse block gate) so the same bad tool call is intercepted before it runs again, in this and every future session across Claude Code, Cursor, Codex, Gemini, Amp, and Cline. Captures the failure with the capture_feedback MCP tool, then force-promotes it via npx thumbgate force-gate so it is enforced, not just logged. Use when the user says "guard against this", "block this from happening again", "never do that again", "make that a rule", "stop the agent from repeating that", or right after a bad action or thumbs-down that should become a hard rule. Do NOT use to merely log a thumbs-up/down without enforcement (use the thumbgate-feedback skill), to recall prior context before starting work (use the Agent Memory skill), or to list rules that already exist (use the thumbgate-rules skill).
ci-failure-triage
IgorGanapolsky
Triage a CI / PR check failure by READING the failure body before forming any hypothesis. Triggered whenever a required check is red, a PR is BLOCKED, a merge won't land, or you're about to call a failure "transient", "flaky", "stale", or "orphaned". Prevents dismissing a real failure (e.g. real CodeQL security alerts) as noise.
shipRelease
jthorare
"Ship a release — sync branch, run tests, audit coverage, push, open PR, then auto-chain → /landAndDeploy → /canary → /syncDocs (skip the deploy chain with --no-deploy)."
review
jthorare
Orchestrate a multi-agent PR code review. Spawns domain-specific reviewer subagents in parallel based on changed files. Findings are saved to ~/.agentic-workflow/<repo-slug>/reviews/<pr>.json — run /postReview to publish to GitHub.