Product & Planning

bahayonghang Bundle

Independent review of Trellis task planning artifacts. Treats the selected task and its recursive current or archived children as one review scope, verifies repository claims and path:line citations against code, traces every acceptance-criterion clause to a requirement and design mechanism, rechecks arithmetic and units, writes one combined evidence-backed Markdown report under the reviewed project's .trellis/reviews directory, and returns one copyable handoff prompt. Compares the plan with the real diff after the task starts. Use when the user asks to 审阅 trellis 父子任务, 审阅规划, 审查 prd design implement, 检查验收标准有没有机制支撑, review a trellis plan or task tree, audit a plan another agent wrote, or verify plan claims before implementation. Not for a code-diff-only review, writing or repairing the plan, or running the task.

g2060308919-star Bundle

Use when a PRD, module description, module-description, 需求文档, 模块说明, 功能变更, 规则变更, 验收标准, 交互说明, 接口契约, 粘贴需求, 测试用例, 测试点, or 测试场景 must become manual functional test Cases with high accuracy, high coverage, end-to-end traceability, explicit Blocked accounting, and convergent clarification. Do not use for Playwright, 浏览器 E2E, API automation, API 自动化, 接口自动化, 单元测试代码生成, code-review-only, or 仅代码审查 requests.

g2060308919-star Bundle

Orchestrate complete browser E2E acceptance when the user provides or will provide a PRD and non-production B2B Web target URLs. Do not use for case generation alone, execution of existing Runner v2 JSON alone, production testing, API automation, or Playwright code generation.

g2060308919-star Bundle

Use when confirmed semantic E2E test cases must be executed against an unfamiliar non-production B2B web system through Chrome DevTools MCP with deterministic run artifacts and an auditable report.

g2060308919-star Bundle

Use when a PRD, module description, module-description, 需求文档, 模块说明, 功能变更, 规则变更, 验收标准, 交互说明, 接口契约, 粘贴需求, 测试用例, 测试点, or 测试场景 must become manual functional test Cases with high accuracy, high coverage, end-to-end traceability, explicit Blocked accounting, and convergent clarification. Do not use for Playwright, 浏览器 E2E, API automation, API 自动化, 接口自动化, 单元测试代码生成, code-review-only, or 仅代码审查 requests.

hraness Bundle

Reviews and fixes a just-implemented phase of a multi-phase plan during a phase-orchestrator run. Use after a phase's implementation and initial validation: checks the phase against the plan, PRD/spec, repo conventions, security, tenancy/data ownership, migrations, and test coverage, and patches bounded low-risk issues directly. Never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.

hraness Bundle

Writes or restructures an implementation plan in the format the phase-orchestrator skill consumes: dependency-ordered phases with explicit scope, acceptance criteria, validation commands, and status/log conventions. Use when the user asks to write a plan for phase orchestration, prepare a plan or PRD for delegated multi-agent implementation, or convert a spec, checklist, or design doc into implementable phases.

hraness Bundle

Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and phase-final-reviewer skills and consumes plans in the write-phase-plan format. Use when the user provides a plan, checklist, PRD, or phase document and asks for delegated multi-agent execution across phases.

hraness Bundle

End-to-end reviewer for a completed multi-phase feature at the end of a phase-orchestrator run. Use after all requested phases are finalized: inspects the whole feature against the plan and PRD/spec, hunting integration bugs across phase boundaries, missing acceptance criteria, stale plan state, and validation gaps. Patches only safe concrete issues; never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.

tyrchen Bundle

Implement one phase of ./specs/91-impl-plan.md end-to-end with high quality bars (correctness, elegance, performance), then run an independent code review against the relevant specs and fix every valid finding before declaring done. Use whenever the user says "build phase N", "implement the next phase", "land M0/M1/M2/M3", "follow the impl plan", "ship phase X entirely", "based on @specs/91-impl-plan.md think ultra hard and build phase X", or asks for a phase-shaped slice of the spec set. Trigger even when the user does not say "impl" if they reference an impl plan / roadmap milestone and ask Codex to build it.

tyrchen Bundle

Turn a feature idea or rough requirement into a complete, dependency-ordered spec set under ./specs — PRD, component designs, glossary, security/perf/test cross-cuts, key-decisions log, stakeholder roadmap, and engineer-facing implementation plan — cross-referenced with prior-art memos in ./docs/research and vendored code in ./vendors. Use whenever the user says "write the spec", "design this", "let's plan X", "produce a PRD / impl plan / roadmap", "restructure the specs", "review and re-organise the design", "think ultra hard and split this into phases", or describes a non-trivial system that needs a written design before code. Trigger even when the user does not say "spec" if they ask for phased delivery, milestone exit criteria, or a build-order graph.

tyrchen Skill

Implement one phase of ./specs/91-impl-plan.md end-to-end with high quality bars (correctness, elegance, performance), then run an independent code review against the relevant specs and fix every valid finding before declaring done. Use whenever the user says "build phase N", "implement the next phase", "land M0/M1/M2/M3", "follow the impl plan", "ship phase X entirely", "based on @specs/91-impl-plan.md think ultra hard and build phase X", or asks for a phase-shaped slice of the spec set. Trigger even when the user does not say "impl" if they reference an impl plan / roadmap milestone and ask Claude to build it.

tyrchen Skill

Turn a feature idea or rough requirement into a complete, dependency-ordered spec set under ./specs — PRD, component designs, glossary, security/perf/test cross-cuts, key-decisions log, stakeholder roadmap, and engineer-facing implementation plan — cross-referenced with prior-art memos in ./docs/research and vendored code in ./vendors. Use whenever the user says "write the spec", "design this", "let's plan X", "produce a PRD / impl plan / roadmap", "restructure the specs", "review and re-organise the design", "think ultra hard and split this into phases", or describes a non-trivial system that needs a written design before code. Trigger even when the user does not say "spec" if they ask for phased delivery, milestone exit criteria, or a build-order graph.

equinor Bundle

Creates or modernizes repository skills with clear activation cues, purposeful support files, and practical review loops. USE FOR: creating a new skill, tightening an existing skill, improving discovery wording, and structuring references/assets/optional helper agents when they genuinely add value. DO NOT USE FOR: product-code changes, routine copy edits outside skills/, or documentation that should not become an installable skill.

frankhildebrandt Bundle

Creates Jira Epics, Stories, and Tasks from an implementation plan with architecture, interfaces, and dependencies. Use when turning a plan into a Jira backlog (jirafy, Epic, Story, Task).

linkupplatform Bundle

Use to pull many structured records from ONE known listing page — team directories, product/pricing catalogs, job listings, conference speakers, paginated lists. ALSO read this when writing code that integrates the /v1/extract endpoint (schema, async polling, NDJSON results). Uses Linkup's async /v1/extract REST endpoint and returns NDJSON rows. Requires LINKUP_API_KEY. For a single page's prose use linkup-fetch; for web discovery use linkup-search.

lithqube Bundle

Use this skill whenever users are building AI agents that communicate, register, or coordinate over NATS using the Synadia Agent Protocol or the Synadia Agents SDK — including exposing an agent as a discoverable NATS service, building a meta-agent/orchestrator that discovers and prompts other agents, fanning a prompt out to a fleet of agents and merging replies, streaming agent responses over NATS, human-in-the-loop mid-stream queries, agent heartbeats/liveness, or making a Go/other-language agent protocol-compliant. Triggers on the npm packages @synadia-ai/agents and @synadia-ai/agent-service, the PyPI packages synadia-ai-agents and synadia-ai-agent-service, the `agents.*` subject namespace, or phrases like "agent fabric", "agent discovery over NATS", "orchestrate a fleet of agents", "A2A on NATS", or "register my agent as a NATS service". Use this even when the user doesn't name Synadia — if they want heterogeneous AI agents to find and talk to each other over NATS, this skill applies. Do NOT use for plain

maskshell Bundle

blueprint-crafting: Produces convergence-checked upstream artifacts — product spec (PRD), architecture design (arch-design), iteration plan, executable summary, and research — that parallel-development consumes as authoritative references. Use it whenever the user wants to author, rewrite, research, or convergence-check an upstream artifact: "author a spec", "write an arch-design", "produce an iteration-plan", "research X for the spec", "spec-driven", "write a PRD", "author a roadmap", "write a design doc", "decision log". Each artifact converges on its constraints-profile (process axis: anchors + authority-chain + sources); content correctness stays human (outcome axis). NOT for implementing code — feature implementation, bug fixes, and refactors route to parallel-development. Specifier half of the specify then implement pipeline.

martinplarsen Bundle

Use when you want to find and remove dead/legacy code, unused endpoints, orphaned data-streams, stale config, or unbuilt proposed-nodes that bloat a repo — a static debloat/cleanup pass over an existing architecture-map. Findings arrive as plain-language cards a non-developer can decide on, and approved findings convert to PRD-ready tracker issues. Triggers — "architecture cleanup", "find dead code from the map", "what can I delete", "debloat this repo", "remove unused endpoints", "clean up the architecture". Default is advisory-only; it touches no source code until you explicitly approve a removal.

space-software-ltda Bundle

Atua como PO, Tech Lead sênior e Scrum Master para criar descrições de tarefas no ClickUp (Esteira PBI ou Tarefas IMEDIATAS via API apos aprovacao local). Pipeline: Objetivo → regra de negócio → DB → rotas no Apidog → task. Specs SEMPRE no tom professor para devs juniors (tintim por tintim: glossário, colunas, DBML, payloads, exemplos). SuperAgente Scrum Ritter ou direto pro dev. Use em planejamento, backlog, user stories, PBIs, ClickUp ou Apidog.

caoxicheng Bundle

Discover, compare, and compose existing open-source GitHub repositories for a user's goal, using read-only GitHub tools for live discovery and verification plus Context7 for semantic retrieval over repository code and official documentation. Use when a user asks for GitHub repository recommendations, open-source alternatives, a multi-repository solution stack, project comparison, or help choosing an implementation to adopt.

cnoles1980 Bundle

Expert product management review for product planning, feature prioritization, roadmap decisions, PRD critique, launch readiness, onboarding and UX evaluation, metric selection, and tradeoff analysis. Use when Codex should act like a strong product manager to evaluate a product, recommend changes, challenge assumptions, weigh options, define success criteria, or advise on what to build next.

rickbauer327-cell Skill

Use when the user has meeting notes, a call transcript, or a voice-memo dump and wants decisions, action items, and a follow-up email out of it. Works for client calls, discovery calls, and internal check-ins.

zaks-io Bundle

Use for script-guided issue tracker triage when managing the current project backlog, making issues ready for Orchestrator by running workflow scripts, inspecting their outputs, and fixing labels, statuses, dependencies, body contracts, estimates, stale tracker state, and explicit human questions without ad hoc exploration.

zaks-io Bundle

Use to turn a spec, PRD, or epic ticket into dependency-ordered one-PR implementation tickets, adopting any hand-created tickets, applying the agent-ready body contract, configured estimates, and kind labels, and emitting a dependency graph and predicted file footprint.

zaks-io Bundle

Use to orchestrate a specific ticket set, issue tracker filter, project, delivery scope, or Linear Backlog clear run by selecting startable issues, delegating workers, calling review and integrate steps, updating tracker state, and stopping when no safe workflow action remains.

udecode Bundle

Run a scoped Linear backlog autonomously as a sequence of maximal safe parallel batches by composing orchestrator, autogoal, and task. Use when the user wants Codex to execute ordered Linear issues without prompting for each next batch while parallelizing every dependency-ready ticket that lacks a hard conflict.

agentworkforce Skill

Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a local mount. Covers `relayfile setup`, dynamic integration discovery with `relayfile integration available/search`, Nango and Composio backend selection, Atlassian site selection and metadata, cloud login, OAuth/connect flows, mount verification, `RELAYFILE_LOCAL_DIR` handoff, writeback status and retry commands, and key May 2026 cloud-mount gotchas.

gengjie007 Bundle

为 Web 产品、SaaS 和内部平台撰写、修订并评审产品需求文档（PRD）。当用户只需粘贴原型截图和简单描述，快速生成标准格式PRD文档。

aws-samples Bundle

Security and compliance guidance for Amazon ECS — "ECS was unable to assume the role", task role vs execution role, iam:PassRole, confused-deputy aws:SourceArn trust, Fargate vs EC2 shared responsibility, injecting Secrets Manager/SSM secrets (trailing-colon JSON-key gotcha), readonlyRootFilesystem / non-root / drop capabilities, ECS Exec governance, security-group-per-task, VPC endpoint policies, GuardDuty ECS Runtime Monitoring, ECR Inspector scanning, image signing, Fargate FIPS, or PCI/HIPAA/FedRAMP. Walks a discovery-driven 7-layer stack plus the AWS-canonical baseline and a 30/60/90 roadmap. Trigger even if "compliance" is never said — any ECS hardening, task-trust fix, or secrets-injection qualifies. Skip for EKS/Kubernetes (eks-security), GenAI/GPU security (ecs-genai), App Runner/Lambda, auditing a live estate's operational posture (ecs-operation-review — "audit my ECS security posture" matches both), or account-level security with no ECS angle.

jfrog Bundle

Use this skill when the user asks to set up, configure, bind, or connect a package manager (npm, pip, uv, pipenv, maven, gradle, go, docker, helm, ...) to JFrog Artifactory via `jf setup` and `.jfrog/local/package-resolution.json`; when a workspace manifest exists with no matching binding entry; or when a session hook reports package-manager config missing. Skip when the binding already has the same repo key. Never pick a repo by discovery; use resolver output only (unless the user names or asks to browse repos). On unresolved or failed setup, ask with the failure verbatim — never switch servers.

yusifeng Bundle

Use after receiving WebGPT or other LLM feedback on an agent-infra roadmap/todo and before sending the todo back for another review. Produce a concise handoff response that says what we adopted, what we reject or question, and what WebGPT should specifically re-evaluate in the todo.

jwilger Skill

Use this skill to discover workflows, map events, commands, read models, automations, and Given/When/Then scenarios before implementation. It keeps discovery separate from architecture and implementation decisions.

t3chnaztea Skill

Use when reading a PlayStation player's taste from their local export: "what does my PSN library say about me", "read my gaming taste", "what should I play next", "recommend a game from my library", "analyze my play style", "did my taste change", "compare my profile to last month". Reads preferences.json (the taste profile psnstats produces) and turns it into a palette read plus recommendations that cite the specific signal behind each pick. Also owns --compare drift interpretation (how taste shifted between two exports). Not for return-vs-drop verdicts on unfinished games (psn-backlog-triage), ranking a store wishlist (psn-wishlist-advisor), or producing the export itself (psn-export).

t3chnaztea Skill

Use when deciding what to do with started-but-unfinished PlayStation games: "triage my backlog", "what should I go back and finish", "what should I drop", "which games am I never finishing", "clear my pile of shame", "should I give up on X". Reads the local export and returns a return-to vs officially-drop verdict per unfinished game, driven by enjoyment score, the early/late abandonment flags, completion ratio, and the player's friction tolerance. Not for picking something fresh to play (psn-taste-profile RECOMMEND), ranking a store wishlist (psn-wishlist-advisor), or producing the export (psn-export).

t3chnaztea Skill

Use when deciding what to actually buy off a PlayStation Store wishlist: "rank my wishlist", "what should I buy next", "is this sale worth it", "what on my wishlist will I actually finish", "clean up my wishlist", "should I grab X while it's discounted". Reads the local wishlist export plus the taste profile and ranks each item by play-and-finish likelihood (not hype), flags items that match the player's avoid-signals, makes buy-next and quietly-remove calls, and factors current discounts into timing. Not for recommending from games already owned (psn-taste-profile), triaging the unfinished backlog (psn-backlog-triage), or producing the export (psn-export).