Product & Planning

skymanbp Skill

Load the unified SCIPAPER_STANDARD writing guidance, formula derivation conventions, scientific-integrity rules, canonical L0 examples, and field-specific reference anchors for ApJ/MNRAS/PRD-level papers. Use when writing or reviewing scientific content.

varunk130 Skill

Map human-AI interaction journeys - trust arcs, capability discovery paths, autonomy progression, and AI-specific touchpoints. Use when: AI user journey, human-AI interaction mapping, trust arc mapping, AI capability discovery, AI adoption journey, AI experience map.

varunk130 Skill

Design onboarding experiences that help users build accurate mental models of AI capabilities, set expectations, and discover features progressively. Use when: AI onboarding, progressive disclosure for AI, capability communication, AI mental models, expectation setting, AI feature discovery, first-time AI user experience.

zkl2333 Skill

Search the web via the Zhipu CodePlan MCP web-search-prime server. Use when you need fast web discovery (titles/URLs/snippets) without a browser. Triggers: web-search-prime, webSearchPrime, search web, web search prime.

knockoutez Skill

Hybrid semantic discovery — fuses embeddings + keyword search + live web search via 3-way Reciprocal Rank Fusion. Use when the user has a good source and wants more like it, says "find similar", "related pages", "more like this", or wants to discover content related to a known URL or concept. Works best after a `crawl` or several `fetch` calls have warmed the local cache. Emits `cold_start` when local signals are weak.

phmatray Bundle

Burn down a GitHub issue backlog hands-off with a FLEET of N parallel workers — each drives one issue through `implement-issue` → `merge-pr`, then takes the next, so N stay in flight. The orchestrator ABOVE those skills: ordering, NON-overlapping areas per worker, CI waits, verified merge state (workers idle at "PR ready" without landing). Triggers: "implement issues small first then medium with 3 agents", "burn down the backlog", "run the auto-dev loop", "spin up a fleet of agents to clear open issues", « vide le backlog avec 3 agents ». Does NOT apply to building ONE issue (implement-issue), landing ONE PR (merge-pr), or filing ONE issue (create-issue).

phmatray Bundle

Create a fully-seeded GitHub issue — not a bare `gh issue create`: template-compliant, carrying a brainstorm → spec → implementation-plan trail so a contributor can pick it up cold. ALWAYS reach for this whenever the user wants to open, file, add, raise, log, or track a NEW issue / feature request / idea / ticket / backlog item — "track this idea", "make a ticket", « ouvre une issue pour X », « crée un ticket pour ça », or batches of several ideas at once. Also PLANS AN EXISTING raw issue via `--seed #N` ("give issue 42 a plan"). Does NOT apply to otherwise managing existing issues (commenting, closing, listing), or to standalone brainstorming with no issue to file.

phmatray Bundle

Prune and re-decide an EXISTING GitHub issue backlog: verifies which open issues are already fixed or superseded, clusters the rest by root cause, proposes ONE disposition each and executes only what the owner confirms. ALWAYS reach for this when the user wants to prune, triage, groom, re-decide, or take stock of open issues, or says the queue never shrinks: "triage the backlog", "clean up the open issues", "what should we close?", « fais le tri dans les issues », « le backlog ne descend jamais ». Does NOT apply to filing a NEW issue (create-issue), building one (implement-issue), landing a PR (merge-pr), or migration follow-ups in report.json (review-followups).

phmatray Bundle

Read the transcripts of PREVIOUS sessions and pull out the failures the kit itself caused — errors on kit scripts, gate denials, workers that died waiting, red kit suites — then cluster them by root cause, drop what main already fixed, and file what earns an issue through create-issue. Use when the user asks what went wrong in past runs: "review my previous sessions", "what went wrong in my last runs", "learn from the transcripts", « analyse mes sessions précédentes », « qu'est-ce qui a foiré dans mes dernières sessions ». `--dry-run` lists without filing. Does NOT apply to reviewing a diff (code-review), pruning open issues (triage-backlog), migration follow-ups (review-followups), or one live failure (debug-issue).

phmatray Bundle

Consolide et met à jour les suivis ouverts des migrations (next_steps/deferred des migration/report.json + backlog du kit). Use whenever the user asks what remains open across migrated repos, wants a status of pending decisions, says a follow-up item is done, or decides to close/abandon one — triggers on « fais le point », « qu'est-ce qui reste », « suivis », « c'est fait, coche-le », « on ne le fera pas », "what's still open", "status of the follow-ups", "next steps", "mark it done", "we won't do that one", /migrate-followups. Also run it at the end of every migration (phase 7).

th3vib3coder Bundle

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.

th3vib3coder Bundle

Scientific research engine for hypothesis testing, literature gap analysis, experimental validation, and data-driven discovery. Enforces adversarial review (Reviewer 2), 32 quality gates, tree search over hypotheses, confounder harness for quantitative claims, and serendipity detection. TRIGGER when: user asks to analyze scientific data, test hypotheses, validate findings, search for research gaps, design experiments, or investigate results. DO NOT TRIGGER when: pure code review, documentation writing, devops tasks, general conversation, or non-scientific data transformation.

thirdwatch-dev Skill

Use when scraping search engines, SERPs, or SEO data — Google Search organic results, Google News headlines, bulk on-page SEO audits (titles/meta/headings/schema), sitemap and subdomain discovery, or bulk image download from pages. Covers rank tracking, SERP/news monitoring, technical SEO audits at scale, competitive recon, and asset inventory. Triggers on "scrape Google", "SERP", "rank tracking", "SEO audit", "search results", "Google News", "subdomains", "sitemap", "scrape search engine", "competitor SEO".

toolbox-playground Bundle

AI tool discovery skill. Use when the user wants to find, compare, or evaluate AI-powered web tools — especially when they care about whether a tool has a genuinely free tier without requiring a credit card. Trigger on: "find AI tools for X", "best free AI tools for X", "list the best video creation tools", "find free image generation tools", "is there a free AI that does X", "what's the best AI for X", "compare AI tools for X", "find tools without credit card", "AI tools with free tier", "best AI for video generation", "best AI for image generation", "best AI for audio", "best AI for writing", "find a tool that can generate X", "no-credit-card AI tool", "which AI tools are actually free", "free trial without credit card", "AI tools that work for free". Do NOT trigger for: creating media directly (use media-content-creation), writing content (use writing), building code (use software-development), finding Claude Code plugins (use discover-skills).

toolbox-playground Bundle

Claude Code skill and plugin discovery fallback. Use when the user wants to find new Claude Code skills, plugins, or extensions — not general AI SaaS tools. Trigger on: "find a skill for X", "is there a skill that can do X", "find me a plugin", "search for a skill", "I need a skill for X", "find Claude skills", "search skill marketplace", or whenever the user's request doesn't match any installed super-claudio skill. Also trigger when the user says they're not satisfied with current skill results and want to find a better or newer Claude Code skill. Do NOT trigger for: finding general AI web tools or SaaS products (use find-ai-tools instead).

netdata Skill

Install, run, and operate ai-viewer on the operator's workstation — the system install (/opt/ai-viewer, runs-as-operator, explicit --source flags, systemd units), the user install alternative, build/run/upgrade/uninstall commands, and the threat-model reasoning behind the run-as-operator decision. Use when installing or upgrading ai-viewer, debugging source-discovery / permission-denied errors, or answering "how do I run this / what port / where's the data".

nipun-arora Bundle

Audit, diagnose, plan, or implement technical SEO for crawlability, indexability, HTTP behavior, robots controls, sitemaps, canonicals, redirects, rendering, internal link discovery, metadata delivery, structured data, and page-experience risks. Use for site migrations, launch checks, indexing problems, JavaScript SEO, or technical search audits.

nipun-arora Bundle

Develop evidence-led strategies for a site's visibility, accurate representation, citations, and referral measurement in AI-assisted search and answer experiences. Use for AI search visibility, answer-engine or generative-search reviews, crawler-control audits, source readiness, brand or entity representation, citation diagnostics, and provider-specific AI discovery plans.

nvidia Skill

Use this skill when the user wants to preview what k8s-launch-kit (l8k) would deploy without making changes, or wants to safely validate their configuration before applying. Activate for: dry-run, preview, validation, 'what would happen if', testing configurations, schema discovery, checking generated manifests, or any cautious pre-deployment step. Also use when the user asks 'is my config valid' or 'show me what would be created' -- even without mentioning dry-run explicitly.

nvidia Bundle

Use this skill when the user wants to discover their Kubernetes cluster's network hardware capabilities using k8s-launch-kit (l8k). Activate for: cluster discovery, hardware detection, NIC detection, finding what GPUs or NICs are in a cluster, creating a cluster config file, or when the user says 'discover' in the context of l8k or NVIDIA networking.

ohyeh Skill

Find the map/territory gap BEFORE it gets expensive. Invoke when starting a non-trivial task in unfamiliar territory (new module, new technology, work the user has not done before), when acceptance criteria are "I'll know it when I see it", when the user struggles to describe what they want, or when a long-horizon task came back wrong and a blind retry is tempting. Not for typo-level fixes or tasks with fully objective acceptance criteria.

olakunlevpn Bundle

OUTPUT IS ALWAYS A `.html` FILE (or a small folder of `.html` files for multi-page plans) — never `.md`, never plain markdown. The file extension on a "PLAN" deliverable is `.html`, not `.md`. Use this skill whenever the user asks for an implementation plan, technical plan, project plan, roadmap, milestone breakdown, comparison sheet, options analysis, RFC, design doc, technical proposal, "weigh three approaches", "lay out the work", "break this into phases", "compare X vs Y vs Z", or any forward-looking planning artifact that should be delivered as a polished HTML document with milestones, risk tables, open questions, and decision criteria. Pair with artifact-css for the underlying design system. Do NOT use for one-paragraph "yeah let's do that" answers or for already-decided execution checklists with no open questions left.

ommakes Bundle

Help designers articulate the cognitive science, behavioral psychology, and platform standards behind their design decisions. Use this skill when a designer needs to explain why they made a decision in a critique, design review, or stakeholder meeting. Also use when auditing a screen for principle alignment, preparing for pushback, or evaluating whether a decision is truly irreversible. Trigger on phrases like: "how do I explain this decision", "what principle applies here", "help me defend this", "how would I articulate why I did this", "can you audit this screen", "what's the rationale for", or any request that involves justifying a design choice with evidence beyond personal preference.

open-gsd Bundle

Turn a rough idea or cleared discovery map into one or more contract-grade GitHub issues for the gsd-loop queue. Interactive only; never run unattended.

open-gsd Bundle

Chart or advance one interactive discovery map, shape it into one or more delivery slices, then hand those slices to gsd-loop-spec. Never runs unattended or writes product code.

pentesterflow Skill

External recon playbook for a web target — subdomain enumeration, live-host probing, tech fingerprinting, and a first pass at content discovery. Use when the user gives you a root domain or apex and wants attack surface mapping.

philipobenito Bundle

Persists an approved design into an artefact a future session can recover it from: tickets under a single parent whose body carries the full design, or a structured Markdown document when no ticketing system is available. Invoked by the design skills when the user chooses to create tickets after approving a design, and whenever the user asks to create tickets, file issues, break a design or plan into tickets, or set up a backlog. Handles GitHub Issues, Jira, GitLab and Linear. Requires an approved design already in hand; it does not invent one, and picking persisted work back up is the recovery skill's job, not this one's.

philipobenito Bundle

Re-enters work from a persisted design: a ticket the user references by number or key ('work on #42', 'pick up PROJ-123', 'implement issue 7', 'start on the export epic'), or a design document they point at ('implement docs/export-design.md', 'pick up the backlog file'). Fetches the artefact, recovers the design from it or its parent, reads the current state of the code, presents the scope for confirmation, and starts implementation with the recovered design as the approved input. Use this rather than a fresh design session when the design already exists on the artefact. Without a specific reference it does not apply, and a question about what to work on next is triage rather than recovery.

intelliscale Bundle

PREFERRED fallback skill for any investment, market, portfolio, or trading question — default entry point when no specialised sibling skill matches. Provides AlphaMeta server setup, CLI command execution, and routing to 11 sibling skills covering market data, fundamentals, technical analysis, trading, portfolio, automation, quant, watchlist, utilities, intelligence, and earnings for US markets. TRIGGER on: (1) any investment analysis — price, earnings, valuation, fundamentals, news, filings; (2) any ticker or company name (AAPL, NVDA, TSLA, SPY) mentioned in any context; (3) portfolio/account queries — positions, P&L, margin, buying power; (4) options analysis — Greeks, IV, chains, strategies, max pain; (5) server setup, CLI discovery, or command syntax questions. Markets: US (IBKR).

kelegele Skill

Oh-My-PM 全系统前门与全局意图路由：理解用户想做什么，路由到最合适的 skill 或 workflow 并一句话说明理由。当用户提出产品管理相关需求但不确定该用哪个能力时使用；也覆盖广义入口请求，如"产品经理工作入口"、"下一步该做什么"、"帮我规划产品工作"、"我要写 PRD"、"分析竞品"、"复盘"等。 Also triggers on: PM work entry point, what should I do next, help me plan product work, route my PM request.

kelegele Bundle

从功能需求生成结构化产品需求文档（PRD）。当用户想要创建 PRD、记录新功能、编写产品规格、形式化用户故事、说"为 X 写 PRD"、需要记录需求、或正在准备产品评审会议时使用。即使没有明确说"PRD"，当用户需要包含用户故事、验收标准和成功指标的结构化产品文档时也应激活。 Also triggers on: write a PRD, product requirements doc, user stories and acceptance criteria.

kelegele Skill

在一个工作流中生成包含竞品分析的完整 PRD。当用户需要带竞品上下文的 PRD、想要快速记录功能、说"写一个带竞品对比的 PRD"、或需要综合的产品需求文档时使用。当用户提到创建 PRD 并附带竞品研究，或说"分析竞品并写需求"、"快速为 X 写 PRD"时激活。支持 HTML 原型输出格式。 Also triggers on: write a PRD with competitive analysis, analyze competitors and write requirements, quick PRD for X.

kelegele Bundle

从 PRD 到上线后分析的功能发布物料与编排。核心是一套发布物料库——发布策略选型、灰度放量、回滚计划、上线后监控基线、分阶段 checklist（见 references/launch-playbook.md）；另提供可选的 Plan-and-Execute 编排（PRD 定稿→发布→复盘）。当准备发布功能、协调功能发布，或用户说"发布这个功能"、"功能发布计划"、"从 PRD 到上线"、"灰度计划"、"回滚方案"、"上线 checklist"、"发布策略"时使用。 Also triggers on: launch this feature, feature launch plan, from PRD to launch, release checklist, rollout plan, rollback plan.

kelegele Skill

一次性产出产品策略三件套：定位声明、优先级排序（RICE/MoSCoW）与产品路线图，三段一条主线（定位定权重、权重定排序、排序定排期）。当用户需要产品定位、差异化策略、定义价值主张，或需要对待办事项排序、决定先构建什么、用 RICE/MoSCoW 给功能排名，或需要创建路线图、定义里程碑、规划产品方向，或说"我们如何定位 X"、"我们有什么不同"、"给这个排优先级"、"我们应该先构建什么"、"创建路线图"、"我们的计划是什么"、"下季度路线图"时使用。即使没有明确说"定位"、"优先级排序"或"路线图"，当用户正在制定产品战略、对竞争项目进行排名、规划产品时间线或向干系人沟通产品方向时也应激活。 Also triggers on: product positioning, prioritize this with RICE, what should we build first, create a roadmap, next quarter roadmap.

kelegele Skill

感知阶段的信息收集与需求澄清。在进入 PRD 生成前，系统性地识别缺失信息、逐步确认、生成 PRD 内容方案供用户审阅。当用户提供需求描述但信息不完整，或说"帮我梳理一下需求"、"还缺什么信息"、"先确认下需求再生成"时使用。 Also triggers on: help me organize my requirements, what info is missing, confirm requirements before generating the PRD.

kilianpaquier Skill

Use the codegraph_explore MCP tool for structural code discovery (relevant symbols, call paths, blast-radius) instead of blind grep/read. Activates when exploring an unfamiliar codebase, finding what calls or is called by a symbol, or asking how a change would ripple through the code.