Workflow plugins

The multi-person shared-workspace layer on top of desk: starting a team workspace (monorepo or dual-repo), crew onboarding through an overlay-supplied identity, read-across/write-own desks/<alias>/ subtrees, the facts-vs-perspectives-vs-decisions attribution taxonomy, the conflict-safe write protocol, and perspective queries. Vendor-neutral.

7 skills

Lightspeed Labs platform skills -- publish prototypes, collect feedback, run usability tests, synthesize learnings, and generate research reports. Includes: lightspeed-labs, lightspeed-labs-publish, lightspeed-labs-feedback, lightspeed-labs-test-setup, lightspeed-labs-synthesize, lightspeed-labs-research-report. Targets lightspeed-labs.vercel.app via LABS_BASE_URL and authenticates with LABS_PAT (see plugins/lightspeed-labs/skills/references/labs-config.md).

7 skills

受託開発のデリバリー上流を支援。PM運営、要件定義（RDRA・受入基準）、顧客との合意形成、業務設計・サービス設計・システム化範囲の線引き

7 skills

OpenSpec の change ワークフローと、全 change の横断整合性レビューを行う日本語化スキル集

6 skills · 1 agent

In-progress skills from Matt Pocock — decision mapping, review, writing, and experimental workflows

7 skills

Join and participate in the Wasteland federation — browse work, claim tasks, submit completions, earn reputation.

1 skill · 6 commands

Take any GitHub repository from issue scan to merged pull request: repository profile, target scouting, recon, build with self-review, and paced submission, with scripted gates between each phase.

6 skills · 1 command

Splits work across Claude models. Ships three read-only Haiku subagents (repo-map and call-sites query a local Graphicle code graph and check it against the source, api-docs fetches library documentation), a delegate skill that tells the main session when to use them, a setup skill that configures the main model, the Opus advisor, Flightdeck, permissions and the CLAUDE.md rules, and hooks: a Sonnet gate on six risky Bash command families and a Stop check for missing test reports and breaches of the global CLAUDE.md writing rules. The gates are second opinions that fail open on timeout.

2 skills · 3 agents · 1 MCP server · hooks

In-progress skills from Matt Pocock — decision mapping, review, writing, and experimental workflows

7 skills

全社共通の開発ワークフロー

7 skills

求人ボックス(採用ボード)の求人原稿づくり、レビューシートでの修正、本番入稿、写真、月次リライト、成果分析を Claude から操作する。kba Remote MCP server に接続して使う。

6 skills · 1 MCP server

Standardize Claude Code configuration across your team. Bootstrap, sync, and manage CLAUDE.md, hooks, MCP servers, and settings from a shared profile.

1 skill · 4 commands · hooks

Notas, decisões e diário no repositório. Housekeeping com subagente, decisão humana garantida por hook.

4 skills · 1 agent · hooks

JIRA ticket management. Triage, task creation, roadmap items, consolidated comments with transitions, and smart routing.

1 skill · 5 commands

Report how often a Claude Code session has been compacted, checkpoint what it concluded before compaction swallows it, and hand that to the next session.

6 commands

人間が所有する目的の木、セッションを跨ぐ会話の引き継ぎ、そして目的と手段の間の drift 検知 —— hook と skill として、あらゆる Claude Code セッションへ運ばれる。

5 commands · hooks

Six skills for working with coding agents seriously: methodical (spec-first execution, with a failure model for stateful work), review (independent second opinion on the plan before building, ideally from a different model family), verify (adversarial check of agent work against its spec), independent-tests (failure-model tests written from the spec alone), handoff (survive context exhaustion), reflect (proactive offers without nagging).

6 skills

Slash commands for orchestrating multi-phase implementation workflows using the conductor pattern

6 commands

GitHub issue and project tracking for superpowers development workflows.

2 skills · 3 commands · hooks

상황별 Agent Teams 오케스트레이션 프리셋. /team:develop, /team:verify, /team:debug, /team:refactor, /team:review-pr 커맨드로 개발 라이프사이클 전 단계에서 최적화된 팀 구성을 즉시 실행.

6 commands

Lyon's DevOps engineering guidelines - Terraform IaC patterns, AWS EKS operations, Grafana LGTM observability, and infrastructure decision-making for production systems

5 skills · hooks

PostSharp engineering workflows: git conventions, PRs, releases, TeamCity CI/CD, build diagnostics

1 skill · 5 commands

Maintains durable scoped context with optional cross-project hybrid retrieval.

5 skills · hooks

Agent-powered development workflow with parallel codebase exploration, architecture design, code review, and acceptance criteria verification

2 skills · 1 command · 3 agents

One ponytail skill, /ponytail-audit, held on purpose at its pre-v5 version (pin 2ed6c52): a ranked, repository-wide list of over-engineering to delete, simplify or replace with the standard library or the platform; bugs, security and performance are out of its scope. ponytail v5 rewrote it into a full quality audit, which repeats the review step, so the pin is not raised (#715). Applies nothing; no hooks. Not installed by default (#598). The full ponytail plugin is below.

6 skills

The full ponytail plugin, hooks included. Not installed by default; for the opt-in hooks profile.

6 skills

行政(実務)の一式。契約に沿って実装し決定性証拠を揃える implement、出荷/運用の create-issue、書記の職能エージェント、PR 単位の振り返りを PR コメントと retro issue に残す学ぶループ(retro)。判定は出さず、証拠を揃えて指揮に返す。

3 skills · 3 agents

Software delivery lifecycle domain skills for the harness framework. Provides 5 domain skills (SDLC, EA, BA, SA, Ops) and an index skill for profile routing.

6 skills

Sales domain skill suite for the harness framework. Provides 5 domain skills (Sales, Sales Engineering, Tender Management, Sales Enablement, Sales Operations) and an index skill for profile routing.

6 skills

Specification doctrine and toolkit for work executed by coding agents: declared-executor headers, a LOCKED/WORKING/OPEN facts ledger, stable anchor IDs with CI verifiers, an OpenAPI contract set, impact maps, and a read-only spec auditor. Pairs with spec-human.

5 skills · 1 agent