Agent Claude Code
Generates changelogs from git commit history and conversation context. Must be used immediately when the user asks to bump the version.
4,315 tagged Git and workflow, measured the same way as everything else here.
Browse within: agent-orchestration 69Multi-Agent 52agentic-workflow 50agentic 40agentic-coding 39Autonomous Agents 36code-quality 35claude-plugin 32ai-assisted-development 30spec-driven-development 29rust 28typescript 28bun 27claude-ai 26
Agent Claude Code
Generates changelogs from git commit history and conversation context. Must be used immediately when the user asks to bump the version.
microsoft/skills-for-copilot-studio
Agent
You are an ALM (Application Lifecycle Management) specialist for Copilot Studio agents. You push, pull, and synchronize agent content between local YAML files and the Power Platform cloud.
Agent
Forward Deployed Engineering Strategist. Use for architecture planning, task decomposition, and team coordination of Salesforce Agentforce and platform implementations. Plans and delegates — never edits files directly. Spawns FDE team (engineer, experience specialist), cross-cutting roles (QA engineer, release…
Agent
Implementation subagent for one decomposed unit of work in the evanflow-coder-overseer pattern. Uses vertical-slice TDD per evanflow-tdd. Tool-restricted to prevent any git ops or destructive actions — you cannot accidentally commit, push, or modify state outside your task scope.
Agent Claude Code
Use this agent when the user is about to perform git operations like creating branches, making commits, or needs guidance on git workflow standards for this project. Examples: Context: User needs to create a new branch for adding a login feature. user: 'I need to create a branch for adding user authentication'…
Agent
Tightens draft prose by removing filler and hedging. Use after any draft is written and before it is returned to the user.
bybren-llc/safe-agentic-workflow
Agent Claude Code
Data Engineer - Database schema changes and migrations.
bybren-llc/safe-agentic-workflow
Agent Claude Code
Release Train Engineer - PR creation, CI/CD validation, release coordination.
Agent Claude Code
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.
mistydew/tokenicode-deepseek-alpha
Agent Claude Code
Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.
Agent Claude Code
Implement a fix for a pi-lens issue as a branch plus PR. Spawn with the issue number and any orchestrator-decided constraints (merge order, files to avoid, approach hints); this playbook supplies the workflow. Use sonnet for well-specified contained fixes, opus (via model override) for cross-cutting or semantically…
Agent Claude Code
Adversarial pre-merge review of a pi-lens PR. Use for every PR before merge, including small and self-authored ones. Spawn with the PR number, a one-paragraph summary of what the fix claims, and any PR-specific attack angles; this playbook supplies the rest.
Agent
Liza embeds contracts and skills from internal/embedded/ at build time. In a worktree, those embedded copies can lag behind the repo masters after branch switches or edits.
Agent
The worktree root already ends in the task id: .worktrees/ . Relative paths inside the worktree are rooted there — you do NOT prepend the task id again.
Agent Claude Code
Use this agent when you need a thorough code quality analysis and refactoring recommendations for specific files, directories, or an entire branch. This agent reads code deeply, questions every pattern, checks for modern best practices, and produces a detailed report — without making any changes.\n\nExamples:\n\n…
Agent Claude Code
Linter pass over a /verify report. Receives the report path and emits one enumerated audit row per finding with a verdict (KEEP, CUT, UNSURE), the trigger that fired, and a one-line reason. Verifies each finding's evidence against the actual code, git state, or AGENTS.md where it can. Runs as the last stage of…
Agent Claude Code
Runs the ci-settle loop (formula convergence, step X3) — watches CI checks, triages bot comments, fixes real findings or declines with a stated reason, regenerates generated artifacts. No merge authority.
Agent
Adversarial code review - verify demos work, then spec compliance, then code quality.
Agent
Git merge conflict resolution - analyzes both sides, preserves intent.
fullstack-development/front-end-best-practices
Agent
Use when reviewing React+TypeScript code for compliance with frontend standards. Reviews modified files from git diff or a specific file/folder. Reports violations with file:line references and suggests fixes. Invoke as: @frontend-reviewer (reviews git diff) or @frontend-reviewer (reviews specific path).
Agent Claude Code
Builds a designed MuninnDB increment RED-first in an isolated worktree, then pushes the branch WITHOUT opening a PR so the adversarial review runs first. Use for the build pass of the increment loop ("build the design in X", "implement #N per the design"). Every behavior change lands with a test proven to fail without…
Agent Claude Code
代码实现者 (隔离 worktree). 接 task spec, 实现 + TDD, 输出可被 reviewer 验证的 commit.
Agent
Use when starting a new round (substrate-touching / fix-round / admin) to generate a complete handoff doc from scope + prior-round context. Replaces hand-written 18/12/10-section handoff docs.
Agent
Finalizes version bumps, creates standalone version docs, and drafts bilingual commit messages. Only triggered by Orchestrator or Coordinator when user says "发布" / "release" / "commit". Never commits or pushes without explicit approval.