Product & Planning

leonmelamud-inspector-agents Bundle

This skill should be used when the user asks to "audit for AI visibility", "optimize for ChatGPT", "check GEO readiness", "analyze hedge density", "generate agentfacts", "check if my site works with AI search", "test LLM crawlability", "check discovery gap", or mentions Generative Engine Optimization, AI crawlers, Perplexity discoverability, or NANDA protocol.

iamjcabalejo Skill

Structure requirements discovery and produce PRDs, user stories, and acceptance criteria. Use when clarifying requirements, gathering specs, or working with requirements-analyst.

abivan-tech Skill

Fast broad-to-narrow read-only discovery for planning, routing, and review preparation.

clyra-ai Bundle

Convert user-provided recommendations into a timestamped, execution-ready backlog plan using the active repo profile. Use when a repo needs a one-off plan that should not overwrite PLAN_NEXT.

clyra-ai Bundle

Convert repo-owned strategic ideas into a timestamped, execution-ready backlog plan using the active repo profile.

sergebulaev Skill

Read your Instagram niche and profile from real data via Apify, no login. Scan a hashtag for the posts traveling now (likes, comments, owner) to see the format and hook that works. Pull profile stats for any handle, yours or a competitor's: followers, posts, bio, category. Instagram hides who liked or commented on other accounts, so this is discovery plus profiles, not engagers. Triggers on "what works in my niche", "scan the hashtag", "competitor stats". Not for writing captions (use ig-caption-writer).

helius-labs Bundle

Build Solana trading and intelligence applications combining OKX DEX aggregation with Helius infrastructure. Integration-only layer — describes when and how to compose OKX tools with Helius tools for swaps, token discovery, smart money signals, meme token analysis, and portfolio intelligence.

helius-labs Bundle

Build Solana trading and intelligence applications combining OKX DEX aggregation with Helius infrastructure. Integration-only layer — describes when and how to compose OKX tools with Helius tools for swaps, token discovery, smart money signals, meme token analysis, and portfolio intelligence.

evolv3-ai Bundle

Operator skill for driving the Agentic Coding Flywheel (ACFS) fleet from outside. Use when the user wants to provision, connect to, inspect, deploy PRDs to, or recover Flywheel VPS instances; spawn or tend multi-agent swarms on a flywheel; mirror the local skills bundle to flywheels; or troubleshoot fleet-wide issues. Works for both Claude Code (Windows host) and Hermes agents (WSL/Linux). Triggers: "deploy to flywheel", "spawn a swarm on flywheel-N", "check flywheel health", "provision a new flywheel", "send PRD to flywheel", "what's running on the fleet", "sync skills to flywheels", "flywheel doctor".

staruhub Bundle

资深产品经理助手，提供 PRD/MRD/BRD 创作与评审、产品策略、留存增长、竞品分析、功能优先级，以及 grill-me-to-doc 逐轮访谈。用户要求“逐个问我”“先把需求问清楚”“grill me”“把想法变成产品文档”时进入 grill-me-to-doc：先读仓库证据，每轮只问一个决策，给推荐答案与理由，记录决策和未决项，支持 resume，产出结构化 PRODUCT-DOC；文档完成且用户批准前硬停止，任何时候都不写实现代码。即使未提“产品”，讨论 App 功能、增长或商业模式也应触发。不用于：单纯代码实现、系统架构深设（用 solution-architect）、需多源引用的市场调研（用 deep-research）、纯营销文案。

studiogadget Bundle

Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.

studiogadget Bundle

Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.

lennetech Skill

Single source of truth for running the package.json `check` script. Defines discovery (multi-package monorepo aware), the iterate-until-green auto-fix loop, the mandatory audit-finding escalation ladder, residual classification (Accepted vs Critical), and report formatting. Activates on "check laufen lassen", "pnpm run check", "läuft das noch", and whenever an agent or command must prove runnability before shipping. NOT for general npm package maintenance (use maintaining-npm-packages). NOT for reproducing the CI pipeline (use validating-ci-pipelines-locally).

0x0pointer Skill

Systematic fuzzing across two dimensions: (1) content discovery — hidden directories, files, backup/source leaks, HTTP verb enumeration, 401/403 bypass via path manipulation; (2) input validation — auth/token stripping, type confusion, boundary value analysis, HTTP parameter pollution, header fuzzing, cookie fuzzing, mass assignment discovery, and entropy/predictability analysis of any generated value. Works on any domain. Chains from /web-exploit or /pentester; chains into /business-logic when boundary violations, predictable IDs, or mass assignment are confirmed.

ottawacloudconsulting Bundle

Generates a linked Epic, Feature, and Story work item document set for Jira, Azure DevOps, or any tracker, in an Epic > Feature > Story > Task hierarchy. Maps a project to an Epic, each milestone to a Feature, and each milestone feature to a Story, with parent references and source-artifact traceability in every document. Use this whenever the user mentions writing a feature, epic, or story, filing or drafting work items, a Jira ticket or issue, an Azure DevOps or ADO work item, a backlog or backlog item, an epic breakdown, or asks to turn a plan, PRD, or milestone set into something a delivery team can pick up, even when they do not name a tracker or say the words "Epic", "Feature", or "Story".

ottawacloudconsulting Bundle

Create a PRD, architecture document, and progress file for a new project through guided interview. Use when starting a new project, planning a new feature, writing requirements, scoping a project, or creating project documentation from scratch. Phrases like "I want to plan a new project" or "help me write requirements for" are good triggers. Do NOT use for updating an existing PRD, documenting changes to an existing system, writing a technical design doc for an in-progress change, or starting implementation.

lennetech Skill

Executes GitLab CI/CD pipelines locally with the same image, env vars, and service containers as the real runner, so pipeline failures surface before the push. Covers pipeline discovery, per-job execution via gitlab-runner exec, service-container orchestration, env injection without secrets, and a job-by-job verdict report. Also covers the GitHub Actions equivalent via act. Activates on "Pipeline lokal testen", "warum failt die CI", .gitlab-ci.yml changes, or before a push that must not break CI. NOT for the local check script (use running-check-script). NOT for authoring CI configs (use the devops agent).

rajbos Skill

Find all model IDs referenced in local AI-coding session log files and debug logs, then compare them against the keys in src/modelPricing.json. Reports models found in logs that have no pricing entry (unknown — informational only) and pricing entries never observed locally (unused). Use after adding a new model to modelPricing.json, after seeing unexpected cost attributions, or to discover which new models have appeared in recent sessions. Depends on file discovery patterns from the validate-session-schemas skill.

coreindustries Skill

Full-cycle feature development: PRD creation, implementation, testing, and PR creation in an isolated worktree.

coreindustries Skill

Capture knowledge from solved problems to prevent re-discovery. Creates searchable solution documents after non-trivial debugging, fixes, or investigations.

u9401066-pubmed-search-mcp Skill

Orchestrate pre-commit workflow including Memory Bank sync, README/CHANGELOG/ROADMAP updates, and MCP tool count sync. Triggers: GIT, gc, push, commit, 提交, 準備 commit, 要提交了, git commit, pre-commit, 推送.

gapfdev Skill

How to prioritize backlog tickets and organize them into sprints using MoSCoW

gapfdev Bundle

How to convert product requirements into executable backlog tickets with DoD

gapfdev Skill

Produce concise operational status reports for multi-agent delivery including done/open/blocked counts, dependency bottlenecks, and immediate next actions. Use for periodic stakeholder updates during milestone execution.

gapfdev Bundle

How to conduct a product discovery interview and produce a Product Vision document

gapfdev Bundle

Write execution-ready GitHub tickets with clear scope, acceptance criteria, test plan, metadata, and dependencies. Use when creating new issues from requirements, refining vague backlog items, or standardizing issue quality.

gapfdev Bundle

Run recurring backlog triage for GitHub issues and projects to keep priorities, scope, and blockers current. Use during weekly planning, release risk review, or backlog cleanup sessions.

agile-v Skill

Manages financial planning, OKRs, team resources, vendor relationships, and operational compliance with full traceability. Use for budgeting, OKR tracking, resource planning, vendor management, or operational risk assessment.

agile-v Skill

REQ-aware Product Owner for backlog and sprint management with full traceability. Use for sprint planning, backlog prioritization, or converting REQs to INVEST stories.

agile-v Skill

Converts high-level product intent into traceable PRDs and User Stories. Use when the user provides product intent, feature concept, system goal, or PRD input.

aeyeops Skill

Use when eliciting requirements, interviewing stakeholders, running a contextual inquiry or focus group, writing user stories, building a story map, prioritizing features, defining acceptance criteria, or building a requirements document. Covers structured interview and reverse-engineering techniques, functional and non-functional requirement types and constraints, MoSCoW, RICE, and Kano prioritization, story splitting patterns, Given-When-Then Gherkin, checklist and rule-based acceptance criteria, and requirements traceability. For discovery and specification; for the buy-or-build call, use build-vs-buy.

arcblock Skill

Scan recently merged (and optionally open) GitHub PRs for unhandled chatgpt-codex-connector[bot] review comments, re-validate each finding against current main, fix OPEN_EASY items in domain-split PRs, track OPEN_HARD, and stop when nothing actionable remains. Designed for a daily cron/routine or manual /agentloop:codex-review-backlog. Use when the user asks to "scan Codex reviews", "codex backlog", "unhandled codex after merge", or after a merge wave where Codex often arrives late.

closedloop-technologies Bundle

Turn a raw product or service idea into an evidence-backed, economically plausible service through JTBD discovery, competing bets, experiments, value-path design, outcome measurement, and falsification. Use when deciding whether an idea deserves investment, what evidence to gather next, or whether to continue, revise, return, or stop.

closedloop-technologies Bundle

Run Exa-backed deep research, neural search, and page-content retrieval with bounded result and page-read counts. Use when a task needs Exa Search, Exa Contents, or Exa Research inside a source-discovery or benchmark workflow.

closedloop-technologies Bundle

Use Tavily Search API for bounded deep research retrieval, RAG-ready snippets, and low-cost web search. Use when a workflow needs search grounding, source discovery, or benchmarkable retrieval rather than full report-writing.

closedloop-technologies Bundle

Run xAI Grok research with optional web and X search tools for current-event, social, market, or news-oriented research. Use when a task needs Grok-backed synthesis, X-aware source discovery, or provider comparison.