Agent Workflows · Git

Audits the current project against the development standards defined in ~/.claude/CLAUDE.md.

jeremylongshore/tons-of-skills-marketplace

End-of-day consolidation — analyzes agent memory, ADW logs, meetings, tasks, and learnings to generate a complete daily log.

evolution-foundation/evo-nexus

A skill your agent uses when starting feature work that should be isolated from the current checkout, especially in git repositories where a separate worktree would reduce risk.

6BNBN/FlowPilot

Start-of-session orientation routine that briefs Claude on the current state of a project before work begins.

aspi6246/Claude-Code-Skills-for-Academics

Apply minimal MCAF repository governance when the user explicitly asks to adopt MCAF or change MCAF-specific rules.

managedcode/dotnet-skills

Pause session and save current work state for later resume. An agent skill from bobmatnyc/claude-mpm.

bobmatnyc/claude-mpm

Explore ideas, compare approaches, and produce a validated spec before planning.

hashgraph-online/awesome-codex-plugins

A skill your agent uses when executing an implementation plan linearly with explicit human checkpoints between batches of tasks.

hashgraph-online/awesome-codex-plugins

A skill your agent uses when creating an isolated git worktree from the current branch for parallel development and only a build/compile check is required (no tests)

hashgraph-online/awesome-codex-plugins

Track progress across work sessions using SESSION.md with git checkpoints and concrete next actions.

Microck/ordinary-claude-skills

Create an isolated Git worktree/branch or Jujutsu workspace, then verify a clean test baseline before code.

danielvm-git/bigpowers

Plugin release process for MAG Claude Plugins marketplace. An agent skill from MadAppGang/claude-code.

MadAppGang/claude-code

A skill your agent uses when starting isolated feature work or before executing implementation plans.

MadAppGang/claude-code

Fix git pre-commit hook failures in Flutter projects when using git worktrees.

divinevideo/divine-mobile

Git-Notes-Based knowledge graph memory system. An agent skill from sundial-org/awesome-openclaw-skills.

sundial-org/awesome-openclaw-skills

Vibe-sunsang initial setup for Codex — self-heals the local workspace, links Codex session projects, classifies workspace types, generates AGENTS.md, and runs the first conversion.

fivetaku/gptaku-plugins-codex

Summarizes recent git changes for context recovery after session breaks.

athola/claude-night-market

Implements GitHub or GitLab issues via parallel subagents with review gates between task batches.

athola/claude-night-market

Detects git forge (GitHub/GitLab/Bitbucket) and maps CLI commands cross-platform.

athola/claude-night-market

Browse hookify rule catalog. An agent skill from athola/claude-night-market.

athola/claude-night-market

A skill your agent uses when writing skills, CLAUDE.md files, agent prompts, or any directives that involve shell commands, environment variables, API credentials, file creation, or git operations -…

ed3dai/ed3d-plugins

A skill your agent uses when a working session is ending, the context window is nearly full, work needs to pass to a teammate or a fresh session, or the user says "hand this off", "write this up…

OneWave-AI/claude-skills

Tech-stack-aware expert code review using specialized subagents.

hanamizuki/solopreneur

Covers Bash 前后台执行、stdin/终止、输出有界化、进程树与持久租约、Workspace 写沙箱，以及托管 Git worktree 的隔离和交付。

echoVic/blade-code

Isolating work in a linked worktree so another branch can be built, tested, or fixed without touching the current checkout.

Zfinix/aster

The driving manual for DeepReason - how to run the harness properly (session preflight, the public CLI lifecycle, live-run ladders) and where to look before modifying anything or when diagnosing a…

AHepi/DeepReason

Manage AI coding agents on a visual Kanban board. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

【Code Review 子 Agent · 门控三】基于 Sentry LOGAF 三级标注（h/m/l）对代码变更执行 8 维度全面评审（设计合理性、测试质量、预期行为验证、长期影响、代码复杂度、规范执行、变更范围、知识共享）。输出结构化 Checklist 报告并给出最终裁决。由 spec-driven-dev 的 codereview 阶段在门控二通过后自动调用。

LeoYeAI/openclaw-master-skills

为 spec-driven-dev 提供流程中断保存与恢复能力。在任意阶段触发 checkpoint 保存当前 Git 快照、迭代状态、Session 元数据和上下文重建包；rollback 命令可将 Git 仓库和 Agent 上下文恢复到任意历史 checkpoint。支持 savecheckpoint-{usid} 和 rollback {ckptid} 触发。

LeoYeAI/openclaw-master-skills