Product & Planning

hector-ha Bundle

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

hector-ha Skill

Finish ready-for-agent issues in one prepared GitHub repo after PRD/issues/setup exist: triage queue, deep-review each issue, implement with TDD, prove, autoreview, commit, and repeat.

lth0 Bundle

Use when the user wants a reusable local workflow to search scholarly APIs for topic keywords, build a candidate table, rapidly download accessible PDFs into a PDF-only folder, optionally cache HTML/XML outside that folder for second-pass PDF discovery, and deduplicate the PDF files.

jimmyhoran Bundle

Prepare a new, changed, moved, or deleted website URL for discovery by search engines and AI answer engines. Use when the user asks to get a site or page indexed, request a recrawl or refetch, submit a URL to Brave, Google, or Bing, set up IndexNow, update or validate a sitemap, diagnose a page missing from search, or launch a newly published website. Check indexability and sitemap integrity before acting, follow each engine's current official discovery or submission guidance, and report submissions as requests rather than guaranteed indexing.

jkm-4314 Skill

Use when setting up a new project with the full opinionated workflow — session memory, commit hooks, copyright headers, ROADMAP, and CLAUDE.md. Invoke with "bootstrap project", "setup project", "new project setup", or /bootstrap-project

joshrotenberg Skill

Set up and configure Skillet skill discovery. Use when the user wants to set up skillet, configure repos, or customize server behavior.

joshrotenberg Skill

Authoring skills for skillet. Covers the skill format, discovery via suggest, and project manifests.

terryso Bundle

Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD.

bridgelogicsprojects Bundle

Use this skill whenever someone wants to write, build, review, stress-test, or improve OKRs (Objectives and Key Results). Triggers include any mention of OKRs, objectives, key results, goal setting, quarterly planning, strategy execution, or when someone says their goals feel too vague, too ambitious, or not connected to outcomes. Also use when someone wants to distinguish between outputs and outcomes, or when they feel their team is busy but not making progress. This skill coaches the user through writing doable OKRs, validates them for value delivery, and helps align strategy to measurable outcomes — not just activity. Use this skill proactively whenever planning, goal-setting, or strategy execution comes up, even if OKRs are not explicitly mentioned.

bridgelogicsprojects Skill

Use this skill whenever someone wants to facilitate a group OKR planning session, run an OKR workshop with a team or leadership group, prepare pre-work for an OKR planning meeting, or produce a post-session OKR output document. Triggers include any mention of OKR workshop, OKR planning session, facilitating OKR writing with a group, team goal setting, quarterly planning meeting, or when someone is preparing to lead a room through OKR creation. Also use when a previous OKR workshop failed or produced weak OKRs and the team needs to understand why. This skill prepares the facilitator, runs the session, and captures the output.

bridgelogicsprojects Skill

Use this skill whenever someone wants to run a mid-cycle OKR check-in, update confidence levels on active OKRs, triage blockers, or adjust key results that are off track. Triggers include any mention of checking in on OKRs, updating progress, weekly or bi-weekly OKR reviews, team confidence updates, or when someone feels their OKRs are going stale or no one is looking at them anymore. Also use when a team is debating whether to change a key result mid-cycle. This skill runs the check-in, surfaces what matters, and keeps the cycle alive without adding overhead.

bridgelogicsprojects Skill

Use this skill whenever someone is setting OKRs for an AI product team, an AI-enabled product, or any initiative where the output is non-deterministic — meaning the system learns, adapts, or produces results that cannot be fully predicted in advance. Triggers include any mention of AI product OKRs, machine learning metrics, model performance goals, trust metrics, responsible AI, AI feature adoption, or when someone is struggling to write Key Results for work where outcomes are probabilistic rather than guaranteed. Also use when a team is treating AI features like any other feature and missing the unique measurement challenges. This skill coaches AI-specific OKR writing and connects goal-setting to responsible AI practice.

bridgelogicsprojects Skill

Use this skill whenever someone wants to run an end-of-cycle OKR retrospective, score completed OKRs, extract learning from the cycle, or carry forward work into the next cycle. Triggers include any mention of OKR scoring, end-of-quarter review, what did we learn, grading OKRs, or planning the next cycle based on what just happened. Also use when someone feels like their OKR cycle ended without any real reflection, or when the same problems are showing up cycle after cycle. This skill runs the retrospective, extracts the real learning, and sets up the next cycle with better inputs.

gaddev Skill

Turns a raw feature brainstorm (usually a messy dump pasted from ChatGPT or notes) into three grounded planning artifacts — a constitution, a roadmap, and a techstack — without inventing scope, decisions, or technology the user never stated. Use this whenever the user pastes brainstorm/ideation content and asks to structure, formalize, or "clean up" it into a spec, constitution, roadmap, or tech-stack doc — e.g. "turn this brainstorm into a spec," "make a constitution/roadmap/techstack from this," "structure my idea dump," "format this into planning docs." Compatible with Spec Kit (.specify/) and OpenSpec (openspec/) if the project uses them. For evaluating an AI product/release instead, use ai-release-triage.

hhfinai Skill

Map listed-equity beneficiaries of a secular trend across the supply chain, then substantiate each with earnings call evidence (backlog, book-to-bill, guide raises, Q&A admissions, mix shifts). Decomposes multi-mechanism themes into sub-themes, flags cost-bearer nodes, subtracts captive capacity, and classifies each node as value captor, volume taker, optionality, or cost bearer. Use when asked "who benefits from X", "supply chain beneficiaries", "pass-through analysis", "thematic basket", "pick and shovel", "trace this trend", "map the value chain", "which companies are exposed to", or any request starting from a macro driver and asking for downstream equity beneficiaries. Also triggers on "substantiate with earnings calls" or checking whether a company actually captures benefit vs merely transits volume. Pairs with bg-lens for single-name deep dives and earnings-analysis for individual prints.

skillmedev Skill

Produces a rigorous, honest evaluation report for an ML model - real baselines, business-matched metrics with confidence intervals, slice-level error analysis, calibration checks, and a go/no-go recommendation. Use when someone asks "is this model good enough to ship", "write up the eval for this model", "did we actually beat the old model", or before any model promotion, stakeholder demo, or retraining decision. Do NOT use for evaluating LLM or prompt outputs - use llm-evaluation instead; for analyzing randomized product experiments use ab-test-analyzer; for documenting a shipped model for consumers use model-card-writer.

bymaxone Bundle

Loop-engineering executor — autonomously drive an APPROVED roadmap from first phase to done, one phase per PR, with zero human interaction after launch. An orchestrator session spawns one isolated implementer sub-agent per phase, waits for CI + the review bot via background signals, fixes findings, merges after a grace window, updates dashboards, and chains the next phase. Reads its per-project parameters from docs/AUTOPILOT.md. Modes: init (generate the config from the roadmap — stops for review), run (drive the chain), status (report chain state). Requires the /bymax-workflow:roadmap + /bymax-workflow:phase-tasks docs and an authenticated gh CLI. Triggers: "autopilot", "run the roadmap", "execute all phases", "autonomous execution", "rodar o roadmap inteiro", "executar todas as fases".

tractorjuice Bundle

Generate a Wardley Map from a scenario description using a formal mathematical model. Produces OWM-format output (with an optional Mermaid wardley-beta block for GitHub rendering) and strategic analysis grounded in Wardley's cheat sheet, 61 gameplays, and 40 doctrine principles. Use this skill whenever the user asks for strategic reasoning about the components of a business, product, or system — specifically when they mention any of value chain, strategic positioning, competitive landscape, strategic moat, component evolution, genesis-to-commodity spectrum, build-vs-buy across multiple components, where to invest engineering effort, what to commoditise or outsource, mapping a business or platform or marketplace strategically, or explicitly "Wardley map". Always trigger when "Wardley" appears in the request. Also trigger when the user describes a business or system and asks about strategic roadmap, moats, or board-level positioning — even without naming the framework. Skip for flowcharts, UX journey maps, proc

zhanghandong Skill

Use when converting PRD or issue prose into KLL requirements, running the intent compiler plan, or reverse-interviewing a human to resolve requirement ambiguity before task spec generation.

englandtong Bundle

Keep a drifting or half-finished project under control with one compact, conflict-checked delivery state, right-sized scope, bounded autonomy, and independent QA acceptance. Use for non-technical requirement guidance, Legacy Bootstrap, Small/Medium/Large sizing, Lite/Standard/Full governance, Controller-Developer-QC routing, Milestones, Work Orders, QA acceptance, drift recovery, target rebaseline, roadmap review, or reducing token and document overhead. Typical triggers include 项目做了一半 / 不知道该不该继续 / 范围蔓延 / 想加新方向 / 想重开一个项目, scope creep, we keep adding features, too many documents and no working code, docs outweigh code, governance overhead is too high, 治理内卷, which project should I kill, should I archive this, redefine done, change the target, rebaseline, is this really accepted, and we accepted it but never shipped. Also use for anti-involution doc budgets, archive discipline, stop-loss rules, Active Packet bootstrap, and accepted-but-never-released risk. For already-authorized ordinary coding loops, use agent-

paldom Bundle

Implements MCP server authorization - OAuth 2.1 resource server role, RFC 9728/8414 discovery, PKCE, RFC 8707 audience validation, scopes, client registration. Use when adding auth, OAuth, tokens, or credentials to an MCP server, or debugging 401/403/discovery failures. Not for general threat hardening, transport wiring, or non-MCP app login.

skillmedev Skill

Rolls up engineering team status into an exec-ready written update with exactly three sections - progress in outcomes, risks with likelihood and mitigation, and asks with owners and deadlines - scannable in under 90 seconds. Use when someone asks "write my weekly eng update", "summarize team status for leadership", "turn these standup notes into an exec update", or is prepping for a leadership sync. Do NOT use for updates to external or cross-functional stakeholders on a project - use stakeholder-update instead - for public incident communication - use status-page-update - or for monthly investor letters - use investor-update-writer instead.

skillmedev Skill

Inventories tech debt and ranks it economically - scoring each item 1-3 on cost of delay (the interest rate) and leverage (the principal unblocked), multiplying into a priority index, and packaging the winners into a leadership proposal framed on business impact. Use when someone asks "which tech debt should we tackle first", "help me build a case for refactoring to leadership", "our backlog of debt is huge, where do we start", or is preparing quarterly planning. Do NOT use for finding and removing unused code - use dead-code-eliminator instead - for auditing third-party dependency risk - use dependency-risk-audit - or for planning the sprint the work lands in - use sprint-planning instead.

itechmeat Skill

Append-only operational event logging for Open Second Brain. Daily Markdown notes are the default backend. INVOKE this skill (and call `event_log_append`) immediately after producing any durable artifact in the current turn — code shipped, bug fixed, refactor merged, config or deployment change, instruction-file edit (CLAUDE.md / AGENTS.md / plugin docs / system prompts), content artifact created (post, draft, documentation, marketing copy, release notes), research or investigation that produced a concrete finding or decision worth recalling later, or discovery of an external fact (CLI behaviour change, API quirk, undocumented edge case) that future sessions should know. SKIP for pure discussion, exploration, read-only queries, and planning that has not yet produced an artifact. If unsure, ask "would future-me want to find this in the log by searching for it later?" — if yes, log it. WRITE the `message` in the same natural language the user has been speaking with you in this session — never default to English

liorvainer Bundle

This skill should be used when the user asks to 'add to backlog', 'create a backlog item', 'show backlog', 'list backlog tasks', 'what's in the backlog', 'move to backlog', 'check backlog', 'backlog status', 'fetch backlog', 'get all backlog items', or mentions managing future work items, ideas, or deferred tasks in the project's Notion task board.

pax-k Bundle

Maintain Build Right feature planning after preflight and before execution. Use when the user wants to explore a desired feature, groom or reprioritize backlog/sprint work, run bounded product or technical research, use subagents for planning review, create or split execution-ready tasks, update planning evidence, or hand off a ready task to build-right-execution without implementing product code.

peterfile Bundle

Create a Kiro spec for a feature in .kiro/specs create/update feature spec/PRD/RFC—requirements, design doc, and implementation tasks checklist.Trigger on spec/specification/PRD/RFC/tech spec, requirements/user story/acceptance criteria/EARS, design doc/architecture, task breakdown/implementation plan/checklist; 需求/验收/设计/任务.

hades-hy-li Bundle

Validate an AI-native startup idea before building. Use when a founder has a problem hypothesis, customer segment, early market thesis, or product idea and needs customer discovery, opportunity filtering, wedge selection, market mapping, risk identification, or an evidence plan before starting an MVP.

joaovyttorfelix Skill

Flag possible documentation duplication, misplacement, or verbosity. Use when drafting or reviewing docs, backlog items, ADRs, or explanatory text to steer toward a single source of truth.

joaovyttorfelix Bundle

Create or refine well-formed backlog work items for AI-assisted development. Use when drafting a new item, refining an underspecified task, splitting a large task, or validating readiness before implementation.

joaovyttorfelix Skill

Execute a single, well-formed work item with minimal, verified changes. Use when a backlog item is ready for implementation and work must proceed safely without scope creep.

maxbase91 Bundle

Apply an honest, plain-English tone to procurement outputs. Use as a tone overlay whenever generating procurement content — contract reviews, RFP documents, spend analyses, supplier communications, category strategies, executive summaries, negotiation briefs, board updates, or any deliverable that will be read by a human procurement professional or business stakeholder. Trigger on phrases like "make this less corporate", "rewrite in plain English", "less jargon", "humanise this", "more direct", or whenever the other procurement skills (redline-sentry, spend-prism, bid-compass, supplier-truthcheck) produce content. The skill removes consultancy clichés, performative formality, and corporate filler, replacing them with direct, useful, professional prose that respects the reader's time.

mcgrass-ops Bundle

Product planning, retention, and Android-platform discovery. Use BEFORE the android-compose-design skill - whenever the user wants to build a new app, add a major feature, or scope a product from a one-sentence prompt. Asks 5-11 questions covering loop, Jobs-to-be-Done, win/lose state, retention targets, primary screen, monetization, activation event, and (conditional) hook and pre-mortem. Detects product, retention, and platform contradictions (viral-vs-accountability, weak Investment phase, monetization mismatched with retention curve, notification timing, missing offline fallback). Surfaces the 11 Android-platform decisions (notifications, permissions, deep links, widgets, offline, form factors, AI cost, Vitals, Material 3 Expressive, Data Safety, ASO) that anchor what the design skill builds. Produces a one-page spec the design skill consumes. Use proactively - most one-sentence prompts hide product incoherence the user hasn't noticed yet.

nightnzh Bundle

Use when the task is to place a natural-language order on the Taiwan Cashier online ordering site through protocol discovery and direct HTTP/background requests.

oqiodev Skill

Livre la prochaine tranche du BACKLOG de bout en bout — plan, test, implémentation, vérification réelle, commit. Conçu pour tourner en boucle sans intervention.

oqiodev Skill

Transforme une idée d'outil en SPEC.md, BACKLOG.md et CONTEXT.md, par dialogue. À lancer une fois au début d'un projet, avant d'écrire du code.