Product & Planning

jazz1x Bundle

Decision-forcing skill. Reduces a problem to a binary fork via role decomposition (Decision / Execution / Validation / Recovery), surfaces trade-offs, forces a single choice. Triggers: "forki", "결정", "선택", "어느 쪽", "두 길", "갈피", "trade-off", "둘 중 뭐", "이전에 결정한", "다시 결정", "결정 기록", "decide", "decision", "choose between", "fork", "torn between", "past decision", "decided before", "record decision". Scope: any domain. Pre-PRD, pre-implementation.

jeffallan Bundle

Use when brainstorming ideas, generating raw material, or starting the creative phase of a writing project. Invoke for topic exploration, idea generation, angle discovery, or producing abundant raw content before organizing.

jek-bao-choo Bundle

Transforms raw sales notes into a structured lead qualification document using BANT, MEDDICC, and 3 WHYs frameworks with mermaid org charts, timeline diagrams, and discovery questions — output follows a mandatory template defined in reference files that CANNOT be reproduced without loading this skill. IMPORTANT: Always consult this skill before responding to ANY request involving prospect notes, account intel, deal info, or sales call summaries. The sales team requires output in the exact template format this skill provides. Attempting to qualify or analyze prospect/deal notes without this skill will produce incorrect output. Triggers: user has prospect notes from multiple people; wants to qualify a lead; mentions BANT, MEDDICC, or discovery call prep; pastes sales conversations, Slack threads, emails, or CRM data about a potential customer; wants to organize scattered sales intel; asks what questions to ask next for a deal; mentions pipeline review with account notes.

jek-bao-choo Bundle

Design an end-to-end Datadog monitoring architecture diagram and render it in Excalidraw, from sales discovery notes and technical plans. Use when the user asks to "design a Datadog architecture diagram", "map out our monitoring architecture", "turn these discovery notes into an Excalidraw diagram", "draw the data flow for metrics/traces/logs", "sketch how this customer's stack maps to Datadog", or wants a layered infra/app/UI blueprint showing collection methods (Agent, Cluster Agent, OpenTelemetry Collector, API integrations) and data flow to the Datadog SaaS intake (EU/US/AP). Also trigger this whenever the user provides discovery notes (markdown/Google Docs) or technical plans (CSV/Excel) and wants a visual architecture output, even if they don't say "Excalidraw" or "diagram" explicitly — e.g. "help me plan how we'd monitor this customer's environment" or "what would the observability setup look like for this account".

jesse-black Bundle

Create or revise repository `AGENTS.md` files using a progressive-disclosure, dispatcher-style structure. Use when an agent needs to author or edit a top-level or directory-local `AGENTS.md`, convert a long instruction file into task-oriented "Start Here for ..." sections, add a concise "Must Follow" section with Always/Never rules, improve skill-discovery cues, or decide whether guidance belongs in root `AGENTS.md`, deeper docs, local `AGENTS.md`, or a repository-local skill.

jesse-black Skill

Create or revise Markdown `description` frontmatter so `docgarden match` routes agents to the right repository documents. Use when adding a new routed Markdown document, updating existing frontmatter, fixing noisy or missing match results, tuning skills or docs discovery, or making descriptions more query-aligned without loading document bodies.

jjfroehlich Bundle

Use only when the current decision changes which scientific question, hypothesis, project direction, experimental program, or portfolio bet to pursue, pause, pivot, or stop. Do not use for updating an analysis plan, implementation roadmap, or work sequence inside a fixed project. Reassess every turn; earlier strategy work does not retain this skill. Exclude selecting datasets, annotations, predictors, features, models, statistical settings, analysis units, windows, thresholds, contrasts, estimands, controls, diagnostics, plots, or code—even when called a roadmap, strategy, next step, pivot, or go/no-go. Trigger for candidate ideas, new hypotheses, novelty/feasibility tradeoffs, decisive scientific uncertainties, de-risking experiments, kill criteria, and choices that materially change the scientific program or whether the project continues. Prefer scientific-feedback for holistic critique of an audience-facing research plan.

jmech-pepa Skill

Z neuspořádaných poznámek připraví projektové zadání „tak akorát" — promyslí téma, doplní nedomyšlené (označené k ověření), krátký interview (stack, repo, umístění, vystavení na web), volitelná základní rešerše, plán testování (testy, které ověří funkčnost a odhalí chyby). Výstup jako nový soubor zadani-final.md vedle poznámek. Lehčí než PRD. Trigger: "/zadani", "připrav zadání", "zpracuj zadání", "udělej z poznámek zadání".

jonfazzaro Bundle

Render a concise, color-coded text Discovery Tree whenever communicating a coding plan, specification, plan adjustment, newly discovered work, or completion of a planned task. Use it proactively during implementation to make the current state, dependencies, and viable next tasks easy for a human to assess and choose between. Do not use it for a simple isolated answer or task with no meaningful plan.

jordanhubbard Skill

Plan and execute repository product work through docs/ROADMAP.md. Use this before starting features, refactors, optimization programs, or other work with multiple deliverables. Add ordered checkboxes first, execute from top to bottom, and mark only verified work complete.

jordanhubbard Bundle

Bring README, CONTRIBUTING, the user guide and the roadmap current before a NanoLang release is tagged. Use when make release-docs-check names one of them, or when preparing a release by hand.

cdeistopened Skill

Prioritize a feature, project, or initiative using stacked PM frameworks. Use when someone says 'should I build this feature', 'how should I prioritize my roadmap', 'is this worth building', 'help me decide what to work on next', 'what should I cut from my roadmap', 'RICE vs ICE', or 'how do I say no to this request'. Walks through multiple prioritization lenses and outputs a scored recommendation.

conorluddy Bundle

Convert any subject matter — rough feature ideas, brain-dumps, meeting notes, loose PRDs, existing docs — into a rigorous, testable spec written to industry requirements standards (EARS templates, RFC 2119 keywords, INCOSE/ISO 29148 rules, Gherkin acceptance criteria). Use this skill whenever the user wants to write, rewrite, tighten, or formalize a PRD, technical spec, requirements document, or acceptance criteria, or says things like "spec this out", "formalize this", "turn these notes into a spec", "write requirements for", "make this testable", "tighten this doc", or shares loose product thinking that needs to become an unambiguous document. Also use it to audit an existing spec for ambiguity, weak words, and untestable requirements.

jcosta33 Skill

Fact-check claims and prove completed implementation against direct evidence. Use when claims need validation, cross-examination, or hardening, or completed work needs decisive command proof. Do not use as the owner of broad risk discovery, requirement conformance, or one-sided advocacy.

jovd83 Skill

Use when Codex needs to summarize JUnit 5 test execution results for non-technical stakeholders in clear business-oriented language instead of raw runner output.

joyco-studio Bundle

ALWAYS check the live JOYCO Studio library index at hub.joyco.studio/toolbox/libraries.md before planning or implementing any non-trivial feature, refactor, architecture change, or performance-sensitive work, in any repo. Run this discovery proactively, before choosing dependencies or writing code, to find a specialized JOYCO library that may provide a faster implementation or enforce the studio's preferred architecture. Read the matched library's linked documentation before using it. Skip only typos, renames, formatting, one-line tweaks, and pure questions that will not lead to implementation. When a library informs the work, tell the user and link its specific toolbox page.

jpoindexter Bundle

Explain and defend pivotal design decisions in a case study using stakeholder context, user and business evidence, alternatives, constraints, trade-offs, consequences, limitations, and follow-up. Use when a portfolio draft shows screens without rationale, lists activities instead of decisions, needs executive credibility, must explain rejected options, or must communicate complex enterprise, platform, system, or AI-agent design choices.

b12consulting Bundle

Spec-driven project methodology reference. Use when a project has a specs/ folder for managing product requirements, vision, architecture, success measures, decision records (ADR), glossary, changelog, and ticket-based work tracking. Loaded when: working on a project with specs/; reading or updating PRD, vision, architecture, glossary, or changelog; detecting drift between code and specs; reviewing project methodology or document formats. Triggers on: 'specs', 'PRD', 'vision', 'success metrics', 'milestones', 'architecture', 'ADR', 'decision record', 'glossary', 'changelog', 'ticket', 'project methodology', 'ground truth'.

b12consulting Skill

Initialize the spec-driven project methodology. Use when: no specs/ folder exists; critical files like PRD.md, Vision.md, or Architecture/ are missing; setting up a new project for structured requirements and ticket management. Triggers on: 'setup specs', 'initialize specs', 'create PRD', 'start project methodology', 'missing specs', 'init specs', 'no specs folder'.

b12consulting Skill

Review the health of a spec-driven project. Use when: checking if specs are up to date; detecting drift between code and specs; finding stale or incomplete tickets; auditing consistency across Vision, PRD, Architecture, and tickets. Triggers on: 'specs review', 'spec health', 'check specs', 'audit specs', 'are specs up to date', 'drift check', 'stale tickets', 'spec consistency'.

bonnguyenitc Bundle

Read and fully understand a spec, ticket, PRD, or feature request before any planning or coding. Use when given requirements to implement, when asked to "understand this spec", "what does this ticket mean", or as the first step of a feature. Extracts goals, requirements, acceptance criteria, edge cases, and open questions. First stage of the specship pipeline.

bookwormsuf Skill

Capture screenshots of a running prototype or web app using Playwright MCP, then save locally, upload to Figma, or embed in a markdown file. Use when the user says 'take screenshots', 'capture screenshots', 'screenshot the prototype', 'capture sprint', 'visual changelog', 'screenshot this for the PRD', 'record what the UI looks like', or mentions documenting prototype state for UTs, portfolio, PRDs, or design review. Also use when the user finishes a sprint or feature and wants to save the current state of the UI. Covers any web app on localhost or a URL.

sadiksaifi Bundle

Turn current context, source references, and repo understanding into a complete product-grade PRD published as a GitHub issue. Use when the user wants to spec a feature, formalize requirements, or create an implementation-ready product document.

sadiksaifi Bundle

Turn current context, source references, and repo understanding into independently grabbable GitHub issues. Use when the user wants to break down a PRD, plan, spec, idea discussion, or implementation conversation into vertical issues agents can pick up.

scottrbk Skill

Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding). Also covers the machine contract: --json output, exit codes, and the discovery ladder.

emmanuelrtm Skill

Run (or re-run) Stage 2 only — Discovery: Ideator plus Parallel Explore-Exploit branches (Solve → Evaluate → Audit → Rank+Select → distilled feedback), for the configured number of iterations. Requires brief.md from /investigate.

far-200 Skill

Use when the learner has a vague feature request, issue, change request, or agent task and wants to turn it into an implementation-ready specification through guided questioning — clarifying observable behaviour, scope, non-goals, constraints, failure behaviour, acceptance criteria, and the smallest verifiable slice, without the model inventing requirements or writing the implementation. Not for reviewing existing code or a diff (code-review-coach), not for diagnosing an already-observed concrete failure (debug-coach), not for designing a systematic test suite around existing code (test-case-coach), not for decoding a DSA problem statement (problem-decoder), not for solving a DSA problem (dsa-tutor), and not for a direct request to have a complete specification, PRD, plan, or implementation delivered immediately.

gusen1453 Skill

Use after design alignment (grill), or when the user asks for a design/spec/PRD doc, or when locking scope before an implementation plan, or when handing work off to someone who was not in the design discussion.

hktitan Bundle

Model discovery and selection on Cursor SDK — Cursor.models.list, ModelSelection, parameters (e.g. thinking levels), per-run sticky overrides.

joonghyun-lee-frieren Skill

Purpose

luciole-studio Skill

对著作的深度理解。当用户交来著作、长文、全集要求真正读懂，或说深度阅读、深读、细读、逐句精读、重读、隐微阅读、读懂这本书、"未写而必须"时使用；对象为承重文本（指定文本、哲学/理论专著、隐微写作、被低估之作）时必须加载。Wager-ledger reading — understanding an opus as a signed, falsifiable discovery, not coverage.

davidvujic Skill

Use when a user asks for ROI, stakeholder justification, delivery impact, or defect-risk reduction from improving Code Health in a file.

echosell Bundle

Analyze TikTok creators, TikTok Shop commerce, content, live streams, trends, ads, products, shops, categories, videos, hashtags, music, comments, and audience signals through the KeyAPI REST API using live official docs. Use for influencer discovery, product and seller research, video intelligence, live commerce, trend monitoring, and multi-endpoint reports.

fabio-barboza Bundle

Initializes the project, identifies relevant skills, and updates the project configuration file (CLAUDE.md, .github/copilot-instructions.md, .cursor/rules/project.mdc, or .cursorrules) with project summary, conventions, and available skills. Accepts an optional argument "agents" to only install orchestration agents and commands without running the full setup. Use when the user asks to initialize the project, configure the agent-assisted development environment, or install agents with "/do-setup agents". Do not use for PRD creation, task implementation, code review, or QA testing.

fabio-barboza Bundle

Shared resources and dependencies used by other do-* skills. Not a user-invocable skill. Contains MCP capability registry and discovery instructions referenced by do-execute-task, do-execute-qa, do-execute-review, and do-execute-qa-bugfix.

fabio-barboza Skill

Shows current progress of a PRD — completed tasks, next pending task, completion percentage, and missing artifacts. Use when the user asks for status, progress, what's next, or wants to resume work on a feature. Read-only skill — does not modify any files. Do not use for task implementation, review, or QA.