Product & Planning

donnfelker Bundle

(beta/experimental) Host-agnostic, N-model variant of multi-llm-convergence: drive any artifact (plan, PRD, design doc, spec, or implementation diff) to cross-model consensus from Claude, Codex, Gemini, or another capable host by rotating multiple built-in reviewer families through one uniform read-only reviewer protocol, hard preflight, local-only source grounding, per-round commits, and a full clean-cycle convergence rule. Use for 'beta convergence', 'N-model convergence', 'run convergence from Codex/Gemini/Claude', or 'converge with multiple models'. For the stable Claude Code loop, use multi-llm-convergence instead.

dotnet Bundle

Run the dotnet/machinelearning repository health check locally, covering issue backlog, pull requests, GitHub Actions, and Azure DevOps pipelines, then draft a dashboard update and prioritized investigations. Use when asked for ML.NET repository health, maintenance status, stale work, or CI trends.

fredhead88 Skill

Boot a session into the THINKER role for the DO-IT pipeline. Use when the user says 'think', '/think', 'thinker session', 'let's spec something out', 'brainstorm X', 'triage these ideas', 'sort this dump', 'collect some bugs', or 'process the done work' — any session whose job is discovery, intake, capture, or review that ends in a spec (or a closed review), not code. A thinker is READ-ONLY on code: never edits files, never touches git. It has four shapes (brainstorm / review / intake-triage / collect) and performs its own handoffs (hand a spec to the orchestrator, send a memo). Stage 2 of the DO-IT pipeline. Invoke at the START of a thinking session.

full-stack-skills Skill

Provides comprehensive guidance for Spring Cloud microservices including service discovery, configuration management, load balancing, circuit breakers, API gateways, and distributed tracing. Use when the user asks about Spring Cloud, needs to build microservices, implement service discovery, or work with Spring Cloud components.

full-stack-skills Skill

Provides comprehensive guidance for Spring Cloud Alibaba including Nacos, Sentinel, RocketMQ, and Alibaba Cloud integration. Use when the user asks about Spring Cloud Alibaba, needs to use Alibaba Cloud services, implement service discovery with Nacos, or work with Spring Cloud Alibaba components.

gaoscode Skill

Create a PlanWeave package-shaped plan draft from a fuzzy goal, sparse requirements, codebase context, or a user idea before a formal Plan Package exists. Use when the user asks to make, draft, design, break down, or plan PlanWeave work without an existing PRD, roadmap, issue set, or strong source plan. Materialize a Plan Package only when the user explicitly asks.

ghostwright Skill

List the agent's current skills, memory files, plugins, subagents, hooks, and a settings summary plus dashboard URLs. The user-facing discovery path for everything the operator can edit.

gravitational Bundle

Configure and troubleshoot Teleport auto-discovery for AWS EC2 instances, AWS EKS clusters, and Azure VMs via the Teleport discovery Terraform module. Use to set up or extend auto-discovery, add a region, tag, or subscription, apply the discovery Terraform, check enrollment status, or diagnose why cloud resources are not enrolling. Not for GCP, AWS RDS or database discovery, static or manual join-token enrollment, or Teleport configuration unrelated to discovery.

jason904 Bundle

This skill should be used when the user asks to convert a PRD, OpenSpec change, or product idea into a structured GPT Image 2 UI prompt pack for generating high-fidelity flat UI reference images. It produces prompt materials, UI type decisions, variants, negative prompts, and reference selection checklists, not frontend code.

m31uk3 Bundle

Global/continuous sync of your private Grok conversations from both grok.com and x.com into a clean Obsidian vault. Uses Playwright for reliable discovery across surfaces, supports bookmarklet capture, requires Defuddle, and produces 6-stream maximized Markdown with surface origin in frontmatter. Default target: ~/.grok/conversations/

auldsyababua Bundle

This skill should be used when creating, validating, or converting Product Requirements Documents (PRDs) to LLM-native format. Use this skill when the user asks to write a PRD, review a PRD for compliance, convert an existing PRD to machine-readable format, or ensure PRD quality for AI agent consumption. This skill is optimized for users working with agentic coding frameworks who need strict requirement specifications to prevent context poisoning, hallucination, and mesa-optimization.

0xdarkmatter Skill

Decompose a spec document (architecture, roadmap, wave plan) into a ranked list of candidate parcels ready for parcel-generate. Given a goal and a spec, produce parcel IDs with scope, dependencies, estimated duration, and parallel-safe groupings — the upstream half of the parcel-generate pipeline. Triggers on: plan parcels, decompose spec, parcel breakdown, wave plan, parcel sequencing, what parcels do we need, spec to parcels, parcel decomposition, fleet wave plan.

6551team Skill

Use for token discovery and token analytics: search tokens by name, symbol, or contract address; look up PEPE or other tokens; find trending tokens, top tokens, token rankings, token metadata, token info, token market cap, liquidity, volume, price-info, holder distribution, holders, and token research across XLayer, Solana, Ethereum, Base, BSC, Arbitrum, Polygon, and other chains. Trigger on find/search/look up token, what's trending, top tokens, holder analysis, who holds this token, token liquidity, or research a token. For simple price, K-line/chart, or public on-chain trade logs use opentrade-market. For personal holdings, orders, positions, or trade history use opentrade-cex first, then fall back to DEX/on-chain skills only if CEX has no relevant data. Do not trigger for a lone generic word like tokens or crypto, or for meme safety/rug/bundle/sniper checks.

pugyy Skill

数仓需求分析流程，适用于 PRD 解读、字段口径梳理、上游表结构探索和待确认问题清单输出。直接调用命令：/dw-requirement-analysis。

ragnar-pwninskjold Bundle

Use when the user hands you a vague or half-formed feature ask and wants it turned into a lightweight PRD, or asks to "write a PRD", "spec this feature", "flesh this out", or invokes /lite-prd. Interviews the user by traversing a design tree of clarifying questions, persists every Q&A round to the repo, and emits a lite-prd.md.

ragnar-pwninskjold Bundle

Use when translating a PRD, feature spec, or raw product idea into screen-level prompts for web UX generators (Google Stitch, Figma AI, Pencil.dev, Claude Design, v0, or similar). Use before creating visual mockups or wireframes.

ragnar-pwninskjold Skill

Review React/Next.js code against the real vercel-react-best-practices skill, backlog the performance findings keyed to actual rule ids + impact tiers, rank the most over-subscribed tiers, then fix + test the top N in isolated worktrees. Use when the user wants to systematically harvest and fix React/Next.js PERFORMANCE refactors (waterfalls, bundle size, RSC fetching, re-renders, JS perf), or says "react refactor tournament", "find React performance refactors", "/react-refactor-tournament".

revosai Bundle

Answer business questions about the org's RevOS data directly in chat by querying its live semantic model over MCP — "how many orders…", "revenue by…", "top N…", "trend over time…", "compare X to Y…" — and schema-discovery questions like "what's in my semantic model", "what can I query", "list cubes/datasets/fields", "describe a cube" — or when explicitly asked to "query the semantic model", "run a cube query", "show me a chart", "plot…", "graph…". Use this whenever you would otherwise call the RevOS api_read tool against the `cubes` resource directly — this skill is what turns its raw JSON into a rendered table, a chart when the shape fits, a safe choice of join path when a query spans multiple cubes, and a plain-English explanation, instead of a dumped tool result. This applies even when the question names a specific source system (HubSpot, Zammad, Exact Online, …) — answer aggregate/analytical questions from the semantic model, not a direct source connector.

romainsimon Bundle

Turns a vague "what should we do about X" into a scored decision - explicit actions, an explicit unknown, an explicit prior, and one utility scale - then picks by maximum expected utility and checks the result for framing effects. Use when facing a choice between options under uncertainty, when a decision has stalled in circular debate, when someone asks "should we do A or B", or before writing any decision record, strategy memo, or roadmap commitment.

romainsimon Bundle

Decides how far ahead to plan, what to discount future payoffs by, and which backlog items can be dropped without analysis - using receding-horizon planning, an explicit discount factor, and branch-and-bound pruning against the incumbent. Use when building a roadmap, prioritising a backlog, arguing about short-term versus long-term, setting quarterly or annual plans, or when planning has become an end in itself.

romiluz13 Skill

THE ONLY ENTRY POINT FOR CC-P4P. This skill MUST be activated for ANY product management task - never skip. Use this skill when: writing specs, synthesizing research, planning roadmaps, drafting stakeholder updates, defining metrics, or ANY PM request. Triggers: spec, prd, feature, requirement, user story, acceptance criteria, research, interview, feedback, survey, competitive, persona, insight, roadmap, priority, plan, timeline, rice, moscow, okr, quarter, update, status, stakeholder, announcement, launch, report, metric, kpi, dashboard, retention, conversion, north star, product, pm, brainstorm. CRITICAL: Execute workflow immediately. Never just describe capabilities.

romiluz13 Skill

Internal skill. Use cc-p4p-router for all PM tasks.

christopherswarup Skill

Map content, CTAs, and sales discovery questions to the specific stage of buyer commitment they serve, using a six-stage arc across three phases (Recognize, Explore, Decide). Use whenever a user is planning a content calendar, auditing a website or nurture flow, building sales discovery questions, or asks why "good content" isn't converting. Trigger this whenever content or a CTA is proposed without a stated buying stage — an asset with no assigned stage is decorative, not functional, and this skill exists to catch that before budget is spent producing it.

ctex-org Skill

评审需求(PRD), 从业务价值和技术可行性角度回答问题, 给出评估。

hegu-1 Skill

Translate raw founder or system-level thinking into externally usable outputs without erasing the original judgment, structure, or landing point. Use when nonlinear cognition must become a memo, email, PRD, note, pitch, or operational instruction.

hint-shu Bundle

OSINT recon skill — passive entity discovery for domain / IP / email / person / company / github user. Builds a hybrid findings/dossier/graph report from free public sources (Whois, DNS, crt.sh, Wayback, Shodan InternetDB, GitHub code search, Tavily/Firecrawl/Exa/Perplexity dorks, optional theHarvester/subfinder). No subscription dependencies. Disclaimer is non-removable; secrets are redacted; blocklisted dump sites are filtered at outbound and inbound levels.

jlindley Skill

Setup worktree(s) and generate autonomous execution prompt for backlog item

jlindley Skill

Full session of documentation cleanup, archiving, and backlog mining

duvoai Skill

Run the guided, end-to-end loop that makes one Duvo Queue — and the producer→consumer workflow around it — better. Use when the user wants to "improve this Queue", "this Queue keeps backing up, fix it", or take a Queue to a concrete, applied improvement — not just a read-only audit. You drive the conversation: pin the Queue, survey its whole shape (producers and consumers, backlog and case state, both Agents' AOPs at the seam, triggers and concurrency, the Runs flowing through), agree what to base the improvement on (the user's feedback or the evidence in the Runs/backlog), propose a Run/case range and confirm it, get grounded findings from the workflow-debugger / run-debugger skills, propose concrete changes, and — on the user's yes — apply them (AOPs via aop-writer as new Builds, topology and triggers with your tools). The boundary vs workflow-debugger: that skill is the read-only audit; this is the interactive loop that ends in an applied change. For a single standalone Agent, use improve-agent instead.

duvoai Skill

Audit a Duvo Agent — or a multi-Agent workflow connected by a Queue — across many Runs to find systemic inefficiencies and quality issues, then recommend concrete AOP and architecture changes. Use when the user asks to "analyze this workflow", "audit my Agent", "why is this Agent slow / inconsistent / low quality across runs", "why does my queue keep backing up", or wants a health check over an Agent's recent Runs — as opposed to debugging one failed Run (that's run-debugger). Reads recent Runs, eval scores, the producer/consumer queue topology, and the AOPs those Runs actually ran against via the Duvo public API — leading with the queue topology and backlog and sizing the run sample to the question; hands off to aop-writer for any AOP rewrite.

everyinc Bundle

Process recent Monologue voice notes into a private, sourced inbox of decisions, tasks, ideas, questions, and people follow-ups. Use when a user wants to review recent recordings, clear a voice-note backlog, find commitments, or organize captured thoughts across work and personal contexts.

expoli Skill

Connect an Android phone to WSL2 via adb over WiFi (Android 11+ wireless debugging), including LAN discovery with nmap, pairing, troubleshooting, and the usbipd USB-passthrough fallback path. Use when the user needs adb access to a phone from WSL, phone not visible in adb devices, or USB passthrough issues.

fightzy Skill

Use when scope is unstable or requirements are unclear, before creating OpenSpec artifacts. Covers codebase investigation, requirement clarification, option comparison, and decision convergence.

firetiger-oss Bundle

Use when onboarding a project to Firetiger end-to-end — authenticate, subscribe, detect the stack, wire telemetry from any source (OTLP SDK, platform log/trace drains, Datadog Agent, Prometheus, Vector, or a generic HTTP sink), connect integrations (GitHub, Slack, databases, cloud, observability backends), register deployments, let discovery map services, and create a monitoring agent. Always use this skill for first-time setup — it carries the gotchas (credentials auto-provision, Basic-auth ingest, connect GitHub + telemetry to unlock discovery) that finish onboarding in one pass.

iusztinpaul Bundle

Build, extend, AND query a persistent LLM-maintained wiki for any research topic. Conversational entry point that routes between four modes - query (fast read-only answer from existing wiki), append (ingest the sources the user provided, no discovery), deep (explicit discovery/deep research at a fast/light/deep depth preset), and init (create a new research directory). Ingests from your knowledge sources (Obsidian vault + Readwise + NotebookLM + GitHub repos + YouTube videos + web seeds + user-dropped PDFs) and maintains a wiki layer (per-source pages, entities, concepts, comparisons, overview, synthesis, open questions, contradictions). Use for any research interaction - first-time research on a topic, "what do I have on X", "load my research on Y", "add this PDF to my research", "deep dive on Z", "pull together my notes on Y", "extend my research with this file". Trigger on the phrases above plus "search my research", "use my research", "find sources about X".

jackchuka Skill

Query GitHub Project items by named view or ad-hoc filter. Shows items in board, table, or roadmap format.