Workflow plugins

Fallback Adviser consultations using a review-only Opus subagent when the native Advisor tool is unavailable.

1 command

Collaborative design — builds shared understanding of any project before acting

1 skill

Mid-session checkpoint (log, database, commit, push) without closing

1 skill

One skill that makes your agent question requirements and delete parts before it simplifies, speeds up or automates anything.

1 skill

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

Go build, test and lint scripts, a golangci-lint v2 config, and format-on-edit. Install per project, with --scope project

hooks

Fable 5's working discipline, distilled — outcome-first reporting, act-don't-ask autonomy, faithful verification. Load at session start on a smaller model.

1 skill

Nine testable principles: think before coding, simplicity first, surgical changes, goal-driven execution, verify don't claim, check before retry, fact vs inference, untrusted content, failure classification

1 skill

Create multi-agent skills following the skills/agents architecture, from a curated reference library.

1 skill

Package skills and agents as marketplace plugins across Claude Code / Codex / Cursor / Hermes.

1 skill

Package skills as npx-installable packages: the npx loader model, scope flags, and per-agent target paths.

1 skill

Take a messy git working tree back to clean (untrack build output, complete .gitignore, sort changes into commit / stash / discard) without leaking a secret or losing uncommitted work.

1 skill

Turn PRDs, briefs and research into a customer-centric framing using Amazon's 5 Customer Questions.

1 skill

Push a Markdown file to a Google Doc via Drive; the Doc ID round-trips through front matter so later pushes update in place.

1 skill

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

太陽スタイルのコピーライティング、動画制作、Deep Research、要件定義、13層防御システムを含む統合プラットフォーム

1 skill

An engineering method for working with coding agents, carried to every project: principles with their reason and a test, scaled by stakes (prototype, internal tool, live system). A thin layer over Superpowers.

1 skill

老鸟工具集：把资深开发者打磨过的私房实践，纯本地、安全（不联网、不入库）地蒸馏成可复用机制。local-distill-me（在本机把『CLAUDE.local.md 索引 + ~/.claude/shared 共享规则』私有指令体系蒸馏并一键移植到项目，为多 git worktree 配置不漂移的统一私有规则；三层 + 软链架构，引导式向导）。

1 skill

Turn an existing REST API, stdio MCP, or HTTP MCP into a monetized DPYC Tollbooth Operator MCP.

1 skill

Capture a hard-won golden path from the current session as a reusable Agent Skill, so future sessions start already knowing it.

1 skill

Command-safety PreToolUse guards: blocks npx/bunx-style runners, broad `git add`, `--no-verify`, force-push, commits on protected branches, staging secret files, and (best-effort) reading .env files.

hooks

Git worktree isolation workflow: require edits inside a worktree, block escaping back to the main checkout, and auto-provision a worktree on entry / tear it down on exit.

hooks

Converges on ONE call instead of a menu of options. Two modes: a three-agent sequential loop for value-tradeoff decisions, and a Persona Panel of 3-5 parallel independent experts for domain-expertise decisions.

1 skill

Drive the end-to-end execution of any coherent piece of code work in a GitHub-hosted project: size-scaled design pass, issue, Kanban, branch, implement, internal code and security review loops, validation gates, atomic commits, live verification, PR, automated-reviewer loop, review-thread triage, merge per project policy, optional release, and persisting what was learned. Project-specific values come from the project's own workflow doc.

1 skill

An IT-company operating skill with 80 roles, durable delivery records, independent review and optional cross-team coordination.

1 skill

跨仓拆分与编排——把已确认的多 repo 目标拆成可交付切片，按依赖交给 Dev Team 或 subagent，协调原责任并按完整目标验收；自己不写产品代码。用于继续跨仓 goal、协调多个 repo 升级或跟踪整体交付，不替代 PRM。

1 skill

06 周期维护的未启用源码入口：按有效决定核对公开仓当前文档与相关实现，准备有证据的普通 backlog 或待澄清草稿。用于维护规则审查和离线演练；真实运行仍受启用 HOLD 约束。

1 skill

运行恢复辅助——控制面、daemon、runner 不可用或执行者中断时，定位故障层并按已有授权恢复，由原责任方接回。用于控制面不可达、runner offline、review pending 或任务中断；不接管 PR 交付，不授权主机配置或凭据变更。

1 skill