Product & Planning

rm2thaddeus Bundle

Generate per-sprint perspectives (narrative + cards) by mining git history for documents and files co-updated alongside sprint anchor docs. Use when the user asks for sprint perspectives, evidence linking, research doc discovery, or sprint retrospectives with code-change metrics.

tt-a1i Bundle

Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Hermes rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.

alibaba Bundle

Builds, edits or analyzes Agent Skills through conversational discovery. Use when the user requests to "Create an Agent", "Analyze an Agent" or "Edit an Agent".

clearmeasurelabs Skill

Analyzes work-item flow, decomposition, and throughput -- Pillar 4 of The Five Pillars. Use for sprint or backlog reviews, or when leadership asks "when will this be done" and the team is still estimating instead of forecasting. Only meaningful once Clarity, Quality, and Stability are in reasonable shape.

clearmeasurelabs Skill

Reviews code, pull requests, or a defect backlog for escaped-defect risk -- Pillar 2 of The Five Pillars. Use when reviewing a PR or batch of recently merged PRs, after a production defect to find the process gap, or when setting up quality gates for a new team or repo.

coffeecheese Bundle

Use when PRD or prototype based module self-testing needs a complete Codex workflow for intake, clarification, planning documents, optional native XMind test-case export, execution gates, priority-based execution, evidence, aggregation, regression testing, or a safe update of the complete Easy PRD Testing installation.

coffeecheese Bundle

Use when the user provides PRD documents, prototype images, field baselines, or product notes that need analysis and clarification before test planning.

coffeecheese Bundle

Check and safely upgrade the complete Easy PRD Testing Skill or Plugin installation to the latest stable release. Use when the user expresses an intent to upgrade, update, sync, or check the version of Easy PRD Testing, its Skills, or its Plugin, even without an exact command. Do not treat test-case updates, test-environment upgrades, negated requests, hypothetical questions, or general upgrade advice as authorization to run an update.

coffeecheese Bundle

Convert standard or legacy Markdown test-case tables into an optional native XMind file. Use when the user asks to generate, supplement, refresh, or overwrite an XMind view of Easy PRD Testing or other existing Markdown test cases. Supports arbitrary directories, relative paths, non-standard filenames, multiple tables, legacy columns, and incomplete rows. Do not use for generic mind maps or arbitrary XMind editing.

coffeecheese Bundle

Use after PRD/prototype intake when generating or updating module testing planning artifacts 01-04 before any browser execution.

danmcinerney Skill

Use when decomposing a hardened spec into tracker issues: cutting tracer-bullet vertical slices through every layer, ordering structural work first with blocking edges, maximizing the disjoint parallel frontier, publishing producer/consumer interface contracts, and attaching a compact change-skeleton to each issue. Invoked only from an explicit architect dispatch — by the harden strategist subagent in `/architect`, or directly by the orchestrator in `/architect-fast` — after the spec is written; never left to description-trigger discovery.

danmcinerney Bundle

Use when the user asks for discovery-scale research that informs a decision: brainstorming a project or feature, choosing a technology, or requests like "research X", "what's the state of the art", or "deep research". Use this skill to turn broad, uncertain questions into sourced decision evidence and a reusable research handoff. For narrow slice-level fact checks inside the build loop, /architect handles those inline.

kwakseongjae Skill

Translates between engineering and non-engineering vocabularies. When a vague sensory request comes from a PM, designer, ops team, client, or non-developer stakeholder, this skill converts it into precise intent through a short clarifying exchange; when reporting results back, it strips library/function names and speaks in outcomes the requester actually cares about. 실무자·기획자·디자이너·비개발자 요청자와 주고받을 때 개발 용어를 걷어내고 일상어로 묻고 답하는 엔지니어링 철학 스킬.

l-yifan Bundle

从个人技能索引中推荐或定位可安装技能。用于用户询问某任务适合什么技能、是否已有技能，或如何安装相关技能。

romiluz13 Bundle

Pi terminal agent workspace — install, /commands, sessions, compaction, settings.json, AGENTS.md, skill discovery, precedence, session JSONL, /tree, providers/auth, models.json, credential resolution, platform setup, editor (@file, Tab, images, !bash), message queue (steering, follow-up), built-in tools (read/bash/edit/write/grep/find/ls, --tools, --no-tools), print mode (-p, piped stdin), SYSTEM.md/APPEND_SYSTEM.md, CLI flags (-c, -r, --session, --fork, --no-session), @files args, resource flags (--no-extensions, --no-skills), model shorthand (provider/id, name:thinking), all slash commands, env vars, philosophy (no MCP/sub-agents/plan-mode by design). Use for pi config, skills, sessions, compaction, providers, models, tmux, Termux, Windows, tools, modes, system prompt, message queue, or "does pi support X".

symph0nia Bundle

Create an authorized CyberEdge scope, run passive asset discovery, follow task events, and retrieve evidence-backed results through the CyberEdge Agent Protocol. Use when an AI agent must inventory domains or IP space that has an explicit authorization reference; never use for active probing or targets outside that scope.

symph0nia Bundle

Run controlled TCP connect service discovery through the CyberEdge Agent Protocol for an explicitly authorized Scope. Use when an AI agent must identify exposed baseline services on approved domain or IP targets; never use for ambiguous targets, vulnerability exploitation, arbitrary port ranges, or targets without a human-provided authorization reference.

symph0nia Bundle

Collect and inspect TLS leaf certificates for an explicitly authorized CyberEdge scope. Use only when an authorization reference already exists and active service discovery is permitted.

tamasbege Skill

Adversarial, persona-driven usability review of an existing UI or flow — a live URL, screenshots, a Figma link, or a described user flow — reviewed through four user archetypes plus Nielsen's usability heuristics to surface friction, confusion, and accessibility gaps before they ship. Use when reviewing a design or flow before dev handoff, auditing a shipped screen for usability problems, or asked to "review the UX," "critique this flow," or "find usability issues." This is a critique gate against a design that already exists — not generative user research (personas or journey maps built from real user data), which is discovery work outside this skill's scope.

vinilana Skill

Enforce Open Fusion specification governance when Codex changes PRD, specs, ADRs, AGENTS.md, or introduces behavior that needs documentation; use to decide whether to update the active spec, create a new spec, or avoid changing implemented specs.

vinilana Bundle

Maintain Open Fusion product and architecture documentation. Use when Codex needs to create, update, review, or reconcile the PRD, specs, ADRs, architecture decisions, roadmap scope, API contracts, configuration requirements, provider strategy, or development plans for the Open Fusion LLM gateway.

andysolomon Skill

Creates development plans with user stories and GitHub issues. Use when asked to plan features, create stories, write issues, build a backlog, or create a development roadmap.

andysolomon Bundle

Create or update highly specific implementation plans and aligned progress trackers for software projects. Use when a user asks for an implementation plan, roadmap, phased delivery plan, gap analysis against an idea/spec, or asks to create/update `progress.txt` with actionable checklist items mapped to milestones.

orfi Skill

The user-facing front door for Trackbed — plan and orchestrate a roadmap of phases for either a Jira EPIC or a standalone PROJECT (a small app with no epic). Use whenever the user wants to plan, roadmap, orchestrate, or work through an epic or a project with Trackbed — phrases like "trackbed DEMO-100", "trackbed this app", "plan this epic", "start a roadmap for acme-app", or any request to roadmap/orchestrate a body of work. This is the only Trackbed skill invoked directly; it determines the anchor (epic vs project) and dispatches to trackbed-init and trackbed-orchestrate. A single Jira story has no roadmap — Trackbed does not apply to it.

orfi Skill

Internal + shared ADR intake/create for Trackbed. Resolve the ADR location, scan and read existing Architecture Decision Records so planning respects them, and gap-fill a new ADR only when there is a genuine uncovered decision. Invoked inside trackbed-init (step 2, for an epic or project) and usable standalone — by a story flow, OR directly on an epic or project when you only need ADRs surfaced or created and do NOT want a roadmap. No manifest, roadmap, or caller is required to run it standalone. Reading existing ADRs is the common case; creating one is the rare exception. Trigger whenever an epic, project, or story needs its recorded architecture decisions surfaced — with or without a roadmap.

orfi Skill

Internal one-time planning pipeline for Trackbed. Turns a Jira epic — or a standalone project — into an optional PRD, optional ADRs, an ordered roadmap, and (optionally) tickets, then locks the storage format in the manifest. Invoked by trackbed when no roadmap exists. Skippable when a roadmap already exists. Never user-invoked directly; never drives execution.

orfi Skill

Create or update the persisted plan for a Trackbed phase. Writes the phase's plan file in the tracked planning layer so a phase is never executed planless. Default simple mode drafts from the roadmap's scope/done; naming a tool in the prompt ("using superpowers") runs that tool's planning flow and adopts its output. User-invocable.

orfi Skill

Reconcile the Trackbed planning layer to the live roadmap — refresh the state file, roadmap, phase↔ticket mapping, and regenerate the viewer, then check every phase has a persisted plan and notify if one is missing. Read-reconcile only; never advances a phase, authors a plan, or writes Jira. Callable directly, and invoked by trackbed-orchestrate on any material change. User-invocable.

orfi Bundle

Open the Trackbed roadmap viewer in the browser — a single self-contained HTML page that draws the roadmap three ways (phase board with color-coded status + Jira keys, rail strip, and dependency graph). Use whenever the user wants to see, open, visualize, or "show me" the roadmap for an epic or project. Regenerates the viewer from the live roadmap first so it always matches current state, then opens it. User-invocable.

orfi Skill

Internal Trackbed skill (invoked by trackbed, not by the user). Drive the ongoing orchestration loop for a Jira epic or a standalone project — read the manifest, compute the next unblocked phase, show the rail view, hand each phase to an executor (Superpowers or vanilla), record progress and per-phase notes, and absorb runtime roadmap changes. Use whenever a roadmap already exists and work needs to advance, resume, or be re-checked. The roadmap is the single source of truth — always re-read it.

kenryu42 Bundle

Find and verify potential sponsors for a GitHub repository by mining GitHub README sponsorship placements. Use when the user provides a target GitHub repo URL and wants sponsor leads, README sponsor discovery, sponsor verification, contact URLs, or a verified-leads.csv for outreach planning. The skill expects exactly one user-facing input: the target repo URL.

kenryu42 Bundle

Use when the user asks for Codex Security workflows: repository-wide or scoped-path security scans, security reviews of pull requests, commits, branch diffs, or working-tree patches, deep exhaustive repository scans, fixing validated or plausible security findings, or individual threat-modeling, finding-discovery, validation, and attack-path-analysis phases.

classroomio Skill

Write a product PRD for ClassroomIO the house way — clarify all features with the user first, research the codebase, write the PRD under prd/<feature>/, then build clickable HTML prototypes under prototypes/<feature>/ that become the UX source of truth. Use when the user asks to "write a PRD", "spec a feature", "plan a new product/feature", or "prototype a feature end to end".

nevenincs Skill

Semantic codebase and architecture-decision discovery with vaultspec-rag - find code and the ADRs that govern it by meaning, then narrow with advanced filters and noise controls. Use to locate where or how something is done, or the decision behind it, instead of guessing identifiers or sweeping with keyword/grep search.

kbravh Bundle

Brand discovery and logo concept development. Use when brainstorming logo ideas, exploring visual directions, analyzing competitor logos, or developing logo concepts before creation. Triggers on "logo ideas," "logo concept," "brand identity," "logo brainstorm," "competitor logos," "visual identity exploration," or any pre-design logo planning.

khangnhoang Bundle

End-to-end frontend engineering workflow for non-trivial React and Next.js tasks: repository discovery, contract inspection, UI/UX planning, implementation, state and async behavior, tests, manual validation, performance review, and final audit.