Product & Planning

jmagly Bundle

AUTO-INVOKE when user mentions media curation, discography, archive, music collection, source acquisition, metadata tagging, Plex, Jellyfin, MPD. Media-curator framework quick reference — discovery phrases for discography analysis, source discovery, acquisition, quality filtering, metadata, archive integrity.

jmagly Bundle

AUTO-INVOKE when user mentions knowledge base, wiki, KB, semantic memory, llm-wiki, knowledge ingest, document corpus. Knowledge-base framework quick reference — discovery phrases for KB ingest/health, semantic-memory kernel skills, llm-wiki profiles.

freecodecamp-universe Skill

Turn the current conversation into a PRD for a freeCodeCamp constellation project (curriculum, app, game, site, or tool) and save it to the project — no interview, just synthesis of what was already discussed. Typically follows an fcc-refine-idea session.

gagip Bundle

GitHub 이슈 또는 자연어 주제를 받아 논의·QA 자료를 준비한 뒤, 현재 하네스의 Plan Mode로 진입할 수 있으면 즉시 진입해 의사결정자가 읽는 PRD 포맷(배경/문제 정의 → 목표/비목표 → 요구사항 → 성공 지표/검증 방법 → 리스크/오픈 이슈)을 적용하는 스킬. 사람은 방향성·설계·리뷰 위주로 일하고 실행 디테일은 구현 단계에서 정해지므로, 파일별 작업 순서표나 진행 추적 장치는 담지 않는다. Plan Mode를 대체하지 않고 그 위에 얹는 "계획서 포맷 애드온"이다 — 계획과 구현을 세션 단위로 분리하지 않으며, `ExitPlanMode` 승인 직후 같은 세션에서 바로 구현으로 이어간다. Plan Mode 도구가 없으면 완결 계획서를 파일에 보존하고 현재 하네스의 승인·핸드오프 방식으로 이어간다. 사용자가 "구현 계획서 작성해줘", "플랜 작성해줘", "계획서 만들어줘", "이슈 #N 계획서", "이슈 가져와서 계획", "이슈 기반 plan", "issue plan", "/draft-plan", "플랜 세워줘", "상세 계획 세우고 진행해줘" 같은 표현을 쓰면 반드시 이 스킬을 사용한다. 인자가 이슈 번호이면 gh로 본문을 가져와 분석 자료로 활용하고, 코드베이스와 이슈 내용 간 괴리가 있거나 모호한 부분이 있으면 구조화 질문 도구 또는 대화로 사용자에게 확인한 뒤 진행한다. 필요하면 현재 제공된 웹 검색·페이지 읽기 도구로 외부 근거를 적극 조사하되 출처를 반드시 남긴다.

greenpau Bundle

Maintain upstream OAuth identity-provider directive parsers, shared configuration dispatch, OAuth/OIDC discovery, JWKS and static public PEM verification, EdDSA/Ed25519 token validation, key refresh, and real portal OAuth E2E tests. Excludes portal signing-key publication.

greenpau Bundle

Maintain portal public signing-key discovery at .well-known/jwks.json, reusable admin API directive parsing, opt-in admin private-key export, KMS key serialization, asymmetric issuer selection, base-path routing, and JWT verification tests. Excludes upstream OAuth provider JWKS consumption.

greenpau Bundle

Maintain the reusable pkg/oidc OpenID Provider, its public interfaces and methods, and the local-user authentication portal adapter, including client registration, discovery, code/PKCE, consent, ID-token keys, UserInfo, revocation, and conformance tests. Excludes upstream OAuth identity providers and portal refresh-token transport.

haaaiawd Bundle

genesis Step 2：将模糊或高层需求转化为严格的产品需求文档（PRD）；含 craft 脚手架、PRD spec 契约、可选子代理分片编排与 Step 完成信号。适用于需求含糊、范围过大或表达停留在概念层的场景。

haaaiawd Skill

纯静态「契约忠实度 / 实现侧证据」审查：对照 PRD、ADR、系统设计、05A_TASKS 与 05B_VERIFICATION_PLAN，围绕契约闭合、任务兑现、架构健康、安全边界、验证证据与回流一致性产出可追溯结论；供 /challenge（CODE/FULL）与 /forge（Step 3 §3.6 波末）共用。

haaaiawd Skill

规定面向真人的 E2E / 手动验证《测试指南》与《E2E Verification》报告骨架（PRD 可追溯、人机走查顺序、评测列仅能 PASS/PARTIAL_PASS/FAIL）；**不含实机浏览器编排**——先后顺序与回填义务由宿主 **`/forge` §3.7**（及 `/forge` 对应条文）统一写死。

hackerfish Skill

Convert a public portable SKILL.md into a DSH-compatible skill with verified discovery paths, tool mapping, provenance checks, and safe fallbacks.

adityahegde712 Skill

Principal and Staff Software Architect methodology for interactive requirements discovery, System Design, RFCs, ADRs, non-functional requirements (NFRs), trade-off analysis, and phased execution planning. Use during the initial design phase, when evaluating major architectural changes, or structuring RFC documents.

jzkk720 Skill

Design first-run flows, empty states, and activation paths that get users to value as fast as possible. Use when building onboarding experiences, feature discovery, guided tours, interactive tutorials, or empty state design for a product interface.

cdxgen Skill

Generates a CycloneDX Cryptographic Bill of Materials (CBOM) with the cdxgen cbom command, inventorying cryptographic algorithms, certificates, keys, and protocol usage from source code and hosts, and auditing them for weak or deprecated primitives. Use when asked for a CBOM, a cryptographic inventory, post-quantum readiness assessment, crypto algorithm discovery, or a review of certificates and key material in a codebase.

mralaminahamed Bundle

Use when adding a guided onboarding or feature-discovery tour to a WordPress admin plugin using Driver.js v1 — setting up the IIFE bundle (window.driver.js.driver), PHP backend tour config arrays (autoStart, pages, steps, element, popover), JS scope detection from URL pathname + hash (getCurrentScope, hashchange listener), localStorage-based completion tracking, CSS selector rules for WP admin elements including Tailwind bracket-notation escaping, testing selectors in browser console, and generating/updating the POT file for tour strings. Triggers: "add a guided tour to my plugin", "onboarding walkthrough in WP admin", "Driver.js setup", "highlight this admin element", "step-by-step tutorial in WP admin", "tour not starting", "tour completion not saving", "scope detection for admin pages", "add tooltips to my settings page", "first-run wizard", "window.driver.js.driver", "getCurrentScope()", "hashchange listener for tour", "localStorage tour tracking", "Tailwind selector escaping in PHP", "Driver.js popover",

oyusypenko Bundle

Full-stack performance optimization with measured proof. Six-layer audit (database, API, edge proxy, client data layer, rendering, browser resources), immutable labeled baselines, deterministic before/after captures via the perf-harness extension (EXPLAIN medians, p50/p95 loops, wire bytes, ETag replay, Lighthouse, Playwright interaction probes, pg_stat_statements discovery), an auto-built dashboard, and a one-concern-per-commit fix loop. /creo perf init scaffolds everything for a project. Trigger keywords: performance, slow page, latency, benchmark, baseline, EXPLAIN, query plan, index, N+1, bundle size, Lighthouse, Core Web Vitals, p95, payload, compression, ETag, profiling.

oyusypenko Bundle

Tooling for the creo-perf skill: deterministic benchmark scripts (scenario captures with EXPLAIN medians and p50/p95 HTTP loops, Lighthouse initial-load audit, platform and schema audits, pg_stat_statements workload discovery, auto-rebuilt before/after dashboard) plus the project scaffolder used by /creo perf init. Not invoked directly; creo-perf routes to it.

wanghaisheng Skill

Discovers and compiles lists of relevant influencers across platforms based on niche, audience demographics, content style, and brand fit. The foundation of any successful influencer marketing program.

dayvisonassis Skill

Generate complete PRDs (Product Requirements Documents) through iterative clarification. Use when: (1) Starting a new project and need structured requirements, (2) Creating product specifications with 9-section PRD format, (3) Defining product scope from a description or context files. Keywords: "prd", "product requirements", "create PRD", "generate PRD", "new product", "requirements document".

dayvisonassis Bundle

Generates technical implementation spec, plan, AND an operational contract for one or more features based on PRD, codebase analysis, and iterative clarification. Produces contract.md (environment contract, quality gates, coverage manifest, observable criteria) consumed by implement-feature and evaluator. Supports batch mode for generating multiple features from the same wave in parallel.

platformplatform Skill

Create PRD Workflow

zby Skill

Write one KB note whose intended contribution is already determined, under its collection and type contracts; validate it and hand broader graph discovery to cp-skill-connect.

zby Skill

Diagnose Commonplace project layout, promoted-skill discovery, user-level uv tool installation, command PATH ownership, and launch-environment failures.

az9713 Bundle

Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /aiception command, (2) 'save this as a skill' or 'extract a skill from this', (3) 'what did we learn?', (4) after non-obvious debugging or trial-and-error discovery. Creates new skills when valuable reusable knowledge is identified. Integrates with Open Brain to prevent duplicates.

cdeistopened Skill

Mine the MFM/MoneyWise archive for content opportunities — gap analysis, revisit-worthy takes, guest callbacks, and clip discovery. Use when someone says 'what should I talk about,' 'find me content ideas,' 'what's in my archive about X,' 'which guests should I bring back,' or wants to turn trending topics into content using existing material.

gabelul Bundle

Conversational design ideation agent that researches trends, explores visual directions, and refines ideas through adaptive questioning — then produces a rich PRD document and auto-generates Stitch screens. Your design buddy that thinks deeply before designing.

gabelul Bundle

Translates a user request or PRD document into a structured Design Spec JSON — theme, color, typography, density, and device type. Call this before building Stitch generation prompts.

rweisssieker-xp Bundle

Use when the current repository needs discovery and autonomous prioritization of evidence-labelled AI-native USP opportunities.

benjaminshoemaker Bundle

Guide discovery and discussion to determine how an AI coding agent can autonomously run and verify a specific user flow end to end. Use when the user asks what would be needed to test a flow, prove an app works, create an E2E/self-test harness, make agent verification repeatable, or evaluate whether an existing test setup lets the agent verify behavior. This skill is for shaping the verification approach before implementation: read the repo's product docs and existing verification contracts, identify the real user flow and channel under test, uncover missing controllable state or external dependencies, ask focused questions, and produce a concrete agent-runnable verification plan only after the flow is understood.

spillwavesolutions Bundle

This skill should be used when the user asks to "configure LLM", "change summarizer provider", "test API connection", "estimate LLM costs", "discover models", or "tune summarization quality". Provides interactive wizard for LLM provider configuration with model discovery and API testing.

suibianqugenichenghaole Bundle

Write page-oriented, development-readable Chinese PRD / requirement documents from already discussed product requirements. Use when the user asks to write or rewrite a 需求文档 / PRD, make requirements developer-readable, follow a fixed demand-document format, or organize page structure, interactions, field rules, key logic, and out-of-scope scope without scattering information.

suibianqugenichenghaole Bundle

Manage PM project assets, versions, snapshots, baselines, and storage layout for requirement skeletons, demos, embedded PRDs, and related artifacts. Use when structured outputs from pm-requirement-intake, pm-demo-design, or pm-embedded-prd need to be saved, versioned, frozen, related to each other, or organized for review, continuation, migration, and downstream memory extraction.

suibianqugenichenghaole Bundle

Generate embedded PRD deliverables that combine structured requirement documentation with linked demo preview, rule/state/config mappings, and bidirectional navigation between document blocks and demo areas. Use when requirement rules and demo outputs are relatively stable enough to assemble into a reviewable or deliverable "left document / right demo" experience, and when a product manager needs PRD + demo linkage rather than separate artifacts.

suibianqugenichenghaole Skill

Audit whether a linked PRD / embedded PRD output is a real document-demo delivery artifact with truthful structure, mapping, and stability labeling instead of a fake split-screen or weak side-by-side review page. Use when Codex needs to review embedded-PRD quality, linkage completeness, navigation truthfulness, or readiness for review/delivery.

suibianqugenichenghaole Skill

Compress a PM workflow project's current state into a concise memory-safe summary with continuation pointers instead of copying full project assets into memory. Use when Codex needs to write durable memory notes, export project status for later continuation, or summarize the current baseline/version/stage without duplicating the full requirement/demo/PRD asset set.

suibianqugenichenghaole Bundle

Structure product-requirement intake, classify requirement types, actively confirm missing dimensions, and judge whether a request is ready for structure draft, prototype draft, or formal PRD. Use when discussing a new requirement, refining an existing requirement, checking whether requirement information is complete enough to proceed, or helping a product manager narrow options and identify risks before prototype or PRD work.