Workflow plugins

The seats and the skills that drive them. The ledger and every delphi command come from the CLI: `npm install -g delphi-team`.

6 skills · 17 agents · hooks

Engineering leadership and people management: 1:1s and skip-levels, difficult conversations, delegation, managing up, cross-functional collaboration, timelines and status, meetings and offsites, decision processes, OKRs, org design and transformation, team culture and rituals, post-mortems, and systems thinking. Twenty-four skills with a router.

24 skills

Korean-first agentic coding harness: plan, implement, chain-plan, karina-systematic-debugging, 2-stage review subagents, push gate verifier subagent, wiki page writer subagent. Safety hooks run on pwsh 7 / Windows PowerShell, cross-platform (Windows verified, macOS/Linux experimental); skills work on any OS (chain-plan needs the Karina app on Windows).

17 skills · 6 agents · hooks

14 generated specialists, five cross-model artifact gates, mandatory metrics, and attach-only mobile QA.

4 skills · 4 commands · 14 agents · hooks

Claude Pipeline — CI workflow for automating code updates through GitHub issues (classify → plan → review → execute → PR review).

18 skills · 3 agents · 1 MCP server · hooks

Claude Code skills from Annetaan Inc. Holds workflow, which runs one implementation as design, approval, per-task implement and review rounds, an integration review when there is more than one task, and a finish step that resolves any conflict with the base under review and opens a pull request, all in a worktree of its own. It also resolves the conflicts of a pull request that is already open, when you ask in plain words. Also pj1-plan, pj2-issues, pj3-doctor and pj4-running, which run a larger piece of work as projects on GitHub. pj1-plan cuts the work into projects with the dependencies between them, and pj2-issues splits one project into tasks, one sub-issue each, once the projects it waits on are merged. From there the work goes through decisions you tick on GitHub and pj3-doctor's review of the whole project to one merged pull request per sub-issue through pj4-running, and a pull request that brings the whole project back for you to merge. pj-auto drives pj3-doctor and pj4-running on a project until it needs you, and pj-cleanup closes the project, removes its worktree and branch, and brings your branch up to date once you have merged it, and workflow-cleanup does the same for a workflow run. pj-roadmap brings the repository's roadmap file into the format the pj skills read, through a pull request. And doc-write, which writes a document in plain words that says each thing once and in order, and doc-meta, doc-review and doc-revise, which let you flag sentences in a document with an opinion and have the document revised to match. And experience-video, which interviews you about your customer's experience and renders a video of under one minute from it.

14 skills · 9 agents

Flow OS · Bazuca, a versão gratuita do harness da Flowgrammers para Claude Code: um modo de trabalho simples para projetos de pequeno e médio porte, com plano, teste primeiro, revisão de código, requisitos verificados, validação e entrega ao cliente em HTML e guardas contra segredo, comando perigoso e texto sem acento.

7 skills · 10 commands · 5 agents · hooks

LogosFortuna-Skill - UDIV dongusu ile derin anlama, tasarim, artimsal uygulama ve dogrulama meta-orkestrasyon sistemi.

2 skills · 5 commands · 15 agents

Security-first, requirements-first Solana full-stack companion: 15 skills, cohort knowledge base, agents, and workflows.

16 skills · 6 agents

Personal development toolkit for Claude Code — scaffolding, conventions, and config generation

12 skills · 9 commands · hooks

The PDD skills, grouped by move. MAP: read-the-system, footgun-register, silent-failure-census, system-truth-atlas. PIN: characterize-before-change, reproducibility-baseline. CARVE: decompose-by-attention, design-assumptions-register, one-meaning-per-term, cover-the-mirror, design-completeness, derisk-gate, decision-gate. SHIP: boundary-tests, no-op-paths, assert-by-shape, trace-requirements-to-tests, pr-sizing, cohesion-review. GRADE: properties, mutation-grading, keep-properties-honest.

22 skills

The FRONT DOOR, ARRIVAL layer, and meta-layer of the marketplace — the marketplace-level surface the specialist plugins never had. /i2p:help browses the powers you have now, grouped by the DISCOVER ▸ IDEATE ▸ BUILD ▸ DESIGN ▸ SECURE ▸ PUBLISH value flow (listing only what is installed); /i2p:review fans out EVERY installed reviewer — code (deliver), design (design), rendered docs (publish), security (secure) — into ONE adversarial verdict in I2P_REVIEW.md; /i2p:check consolidates every plugin's readiness into one table; /i2p:flow maps where each plugin sits and the next command to run; /i2p:focus declares the active lifecycle phase for context routing so out-of-phase skills stay dormant ('focus, don't uninstall'), broadcast by a SessionStart hook so it survives /clear. It also GREETS whoever opens a repo: a SessionStart hook renders a maintainer-authored .claude/welcome.md (/i2p:define-welcome authors it), and /i2p:statusline turns on the rich two-line idea-to-production status line (context & rate-limit gauges, the product-lifecycle phase, a ⚔ reviewer-catch tally), offered once on first activation. Introduces itself on session start and surfaces occasional ≤25-word tips. A thin orchestrator that delegates to the specialists by capability and never re-implements them. Carries the KAIZEN self-improvement covenant.

10 skills · 10 commands · 1 agent · hooks

Multi-agent development stack. Reviewer x packs, durable run folder, evidence-gated findings.

11 skills · 10 agents

Orchestrator + specialist agent roster + on-demand skills for the AI-DLC lifecycle (Inception -> Construction -> Operations), human as sole arbiter.

21 skills

Build production-ready MCP servers — guided discovery, security audits, and code generation using @modelcontextprotocol/sdk

8 skills · 8 commands · 4 agents · hooks

Enhanced Rails development workflow (v0.3.0) with 7 specialized AI agents, 4 documentation skills (Ref integration), 6 auto-invoking quality skills, and 3 security hooks. Features automatic validation of conventions, security, performance, and testing. Optimized for Rails 8 with Solid Queue and modern patterns.

10 skills · 3 commands · 8 agents

The SZA portfolio canon as working skills: release, store/winget publishing, feature-to-site propagation, spec-to-self-audit, canon adoption, and shared-contract alignment. Carries the full rule set in rules/ so any session on any project can reach it without a local path.

20 skills · hooks

Spec→plan→TDD→verify→clean-code→review workflow skills + verify hook + house tone/coding-standards.

19 skills · hooks

Role separation with real authority boundaries, deterministic policy enforcement below the model, mission contracts with independently authored acceptance criteria, and a metrics loop.

7 skills · 4 commands · 8 agents · hooks

Multi-agent ATDD pipeline: impact map -> Gherkin -> GitHub Issues -> RED/GREEN with parallel reviewers and autonomous sub-PR merging. Two human gates: spec, and the final PR.

16 skills · 3 agents · hooks

The OPERATE phase owner — what runs a mission AFTER launch. OPERATE keeps the live product alive and improving: it verifies operational readiness at go-live, instruments and watches the four golden signals (observability), runs incident response (severity, incident-command roles, mitigate-first, runbooks, blameless postmortems), keeps a maintenance cadence (dependency upkeep + CVE patching + tech-debt), and closes the build-measure-learn loop by turning production signals into a new opportunity that re-enters DISCOVER (the cyclic re-entry). /operate-gate is the front door — an operational-readiness check at go-live and the steady-state health view with a READY / WATCH / NOT-READY verdict. Grounded in named canon (SRE SLIs/SLOs/error budgets + golden signals, the Incident Command System, build-measure-learn, ITIL-lite). Stands alone on any live project, or advances the idea-to-production lifecycle OPERATE → DISCOVER (↻) when i2p is installed. Composes the secure plugin's scan-dependencies and hands new opportunities to discover/ideate by capability. Carries the KAIZEN self-improvement covenant: every incident becomes a runbook, every alert gap becomes an SLO.

9 skills · 9 commands · 1 agent · hooks

Run one job from one Claude Code chat, workers as background subagents (separate chats on opt-in): a shared task queue, reports written to files, a frame-count check before every browser observation, and a gate that refuses a fix without a reproduction that failed first. Ten mission kinds, from test sweeps and fixes to refactors, research and design.

13 commands · 7 agents

weigh -> shape -> design -> ticketize -> crew (implement/review/qa/ship/close). House conventions travel with the agents.

14 skills · 5 agents

個人開発を「設計/開発/レビュー/テスト + セキュリティ」の 5 部署体制で運用するプラグイン。対話型コマンドで仕様書・実装・テスト・手動タスクを一元管理する

13 commands · 5 agents · hooks

Middle-down planning: decide and write down what gets built. Thirteen skills and six principles for an interactive session — intake routing, relentless grilling, domain modeling, frontier scouting, triage, specs and tickets. Every session ends in a written artifact carrying which of the four dimensions it closed. Requires ph-lib.

19 skills

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

14 skills · 3 commands · 1 agent · hooks

Interview -> SPEC -> PRD -> GitHub issues -> autonomous multi-day build with Fable-5 orchestration, Cursor + Codex executors, self-verification, loop guards and destructive-op protection. Includes daily issue triage: builds 'ai-ready' issues on their own branch and opens reviewed PRs.

1 skill · 9 commands · 8 agents · hooks

Fluxo com o Orca em pt-BR para Laravel, Python e JS/TS (Windows, Linux, macOS): delegação por workers do Orca, worktree com banco próprio, agentes escritor/revisor/verificador, fila de testes, revisão de cota, board do GitHub, perfil do ambiente local e skills de metodologia, com hooks que impõem as regras. Instalador conduzido pela IA no GUIA.md.

15 skills · 3 agents · hooks

Scope protection, deterministic context, model routing and verification for researcher-to-developer task handoff.

15 skills · 3 agents · hooks

Research → Position → Create → Gate → Measure for marketing your own product: a MARKETING_MAP.md evidence file, hooks that block unsourced social proof and gate publishing, skills and review agents.

15 skills · 3 agents · hooks