Agent Workflows · Git · For developers

Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

alchaincyf/darwin-skill

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

fossasia/eventyay-interpretation

Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

HKUDS/OpenHarness

Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

colbymchenry/codegraph

Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

KKKKhazix/khazix-skills

Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

openobserve/openobserve

Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

gastownhall/beads

Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

slopus/happy

Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

automazeio/ccpm

Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

win4r/ClawTeam-OpenClaw

Traces a file, function or line back to the agent session behind its current commit, using git blame and a memory lookup, and reports only what the records show.

rohitg00/agentmemory

Runs the triage step of the review-framework loop: reads fetched PR review state, builds `review-actions.json`, validates it and renders `review-actions.md`.

prisma/orm

One-click initialization of a multi-agent repository from the RepoBrain template.

study8677/repobrain

Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.

codewhale-hq/Codewhale

Build PX4 board firmware on macOS in the px4-dev Docker container, including git worktrees, and stage commit-labeled artifacts without flashing hardware.

PX4/PX4-Autopilot

Migrate docs from bd (beads) to br (beadsrust). An agent skill from Dicklesworthstone/beads_rust.

Dicklesworthstone/beads_rust

Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

ROYIANS/foliq-print-template-designer

Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.

revfactory/harness

Checks Compound Engineering plugin health and repo-local config, or scaffolds a Compound Pack when you ask for one by id.

EveryInc/compound-engineering-plugin

Has Leon's agent investigate, change and verify code in a repository with its file, search and shell tools, staying inside the scope the owner authorized.

leon-ai/leon

agent-deck, the terminal session manager for AI coding agents.

asheshgoplani/agent-deck

Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.

jnMetaCode/superpowers-zh

Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.

jnMetaCode/superpowers-zh

Understand what you mean before anything is built. An agent skill from prekuter/dryforge.

prekuter/dryforge

Creates or reuses an isolated AgentsMesh Git worktree from a verified base branch, preserves existing changes, and optionally starts the worktree-scoped development environment.

AgentsMesh/AgentsMesh

设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。

vinvcn/mattpocock-skills-zh-CN

A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git…

farm-fe/farm

Upgrades a pinned agent SDK in the agor project, such as the Claude, Codex or Gemini CLI one, and plans the release that carries it to packaged installs.

preset-io/agor

This skill should be used when creating a Claude Code slash command.

meshery/meshery-operator

Run a document coherence, link integrity, and git repository status audit across repository markdown files using a dedicated subagent.

GoogleChrome/modern-web-guidance-src

Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.

win4r/ClawTeam-OpenClaw

多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。

alchaincyf/huashu-skills

Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.

Chachamaru127/claude-code-harness

Fills in issue-brief.md and pr-decisions.md for an existing pull request, so you can pick up a PR mid-flight with its linked issue and past review decisions summarized.

pydantic/pydantic-ai-harness

Coordinate parallel coding agents with Foremerge's local Git-compatible CLI and MCP server.

naw103/foremerge

Automate git worktree creation and copy private files (not tracked in git) to new workdirs.

k8zdev/k8z

Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.

professorpalmer/Puppetmaster

Bring an existing codebase into Dryforge, once. An agent skill from prekuter/dryforge.

prekuter/dryforge

A skill your agent uses when stuck, confused, or disoriented in a crosslink-tracked project — dumps the full context (session state, active issue, locks, blockers, hook config, git state, project…

openwpm/OpenWPM

Manage cs (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config, install, upgrade (cs upgrade — the only supported upgrade path)…

leeguooooo/claude-code-usage-bar

Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.

fynnfluegge/agtx

Parallel task orchestration CLI that dispatches work to AI workers (via Claude Code) in isolated git workspaces.

zippoxer/subtask

BMad Autonomous Development — orchestrates parallel story implementation pipelines.

stephenleo/bmad-autonomous-development

Turn the questions and instructions a user keeps typing into a project into short slash-command skills, mined from their real Claude Code, Codex and Cursor session history and git log.

kishormorol/cli-faq-shortcuts

Decides where a new agent skill belongs in the ToolJet repo, public root or private ee submodule, then wires the symlinks so it loads in Claude Code, Cursor and Codex.

ToolJet/ToolJet

Recall this repository's OwnMem local memory before changing code, and keep it healthy.

grpcer/ownmem

Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.

yologdev/yoyo-evolve

Manage agent skill dependencies with dotagents. An agent skill from getsentry/sentry-wizard.

getsentry/sentry-wizard