Product & Planning

mishankov Bundle

Continuously process available GitHub Project items by preparing project context once and then implementing linked issues in a loop via the gh-issue-to-pr skill. Use when asked to clear backlog from a GitHub Project board, batch-deliver project issues, or repeatedly pick and implement open project issues with gh CLI.

nardovibecoding Skill

Adaptive summarization — output length scales with input length for comfortable reading. Triggers: "summarize", "summarize this", "tldr", "too long", "sum up", "key points", "give me summary", "eli5", "explain like I'm 5", "explain simply". NOT FOR: translation (just ask), content creation (use content-humanizer). Produces: summary at optimal compression ratio based on input length.

nardovibecoding Skill

Evaluate a shared AI skill or skill repository before installing or copying patterns.

lazuardytech Bundle

Activates Hive Mind mode — spawns the Main Agent as a Senior Lead Software Engineer who orchestrates subagents for discovery, planning, implementation, review, and verification. Use when the user says "/hive", "/hive on", or when Hive mode is active. Deactivate with "/hive off". Run "/hive setup" to verify all required subagents are available.

linkupplatform Bundle

Use to pull many structured records from ONE known listing page — team directories, product/pricing catalogs, job listings, conference speakers, paginated lists. Uses Linkup's async /v1/extract REST endpoint and returns NDJSON rows. Requires LINKUP_API_KEY. For a single page's prose use linkup-fetch; for web discovery use linkup-search.

loocor Bundle

Use this skill whenever work needs to be aligned with the MCPMate GitHub Project, including roadmap slicing, draft-item planning, PR scoping, worktree setup, or task-status updates. Trigger on requests about planning, roadmap, project board, task center, worktree discipline, or how to split work into reviewable slices.

loocor Skill

Use this skill for MCPMate pre-release or post-release documentation alignment, including GitHub Release Notes, website changelog entries, README release-facing copy, roadmap positioning, localized website docs, and release-description/changelog consistency checks.

lumifyai Skill

Use Lumify's hosted sports MCP/REST API for schedules, live scores, and event discovery across MLB, NFL, NBA, NHL, tennis, soccer, NCAAF, and NCAAB. Use when the user needs today's slate, a live score, a natural-language sports search, or a team/player lookup — no odds or AI judgment involved.

pokgak Bundle

Interact with Linear issue tracking — list, create, update issues and projects, manage cycles, add comments, and query team data. Use this skill whenever the user asks about Linear tickets, issues, sprints/cycles, project management in Linear, or wants to create/update/triage issues. Triggers include "create a Linear issue", "update ticket", "show me issues in cycle", "what's in the backlog", "assign this to me", "add a comment to", "create a project in Linear".

ponylang Skill

Load when adding a new Linux distro/version (e.g. Ubuntu 26.04, Alpine 3.24) as a ponyc release target. Covers builder Dockerfile creation, image build dispatch and tag discovery, workflow updates, docs, release notes, and the post-merge Last Week in Pony announcement.

popmechanic Bundle

Use when the operator has a backlog rather than a single idea — triage open issues into a ranked docket, sweep the accepted queue into engine-tagged plans, and drain that queue through an autonomous build. Optional; the single-feature superpowers flow is unchanged when not summoned.

qkitzero Skill

Research-backed comprehensive project planning. Use when planning a new project or initiative. Triggered by "make a plan", "I want to start a project", "break down tasks", or "create a roadmap".

ravihammond Bundle

Implement one GitHub issue in the current checkout using the issue, comments, linked PRD, existing branch work, TDD, repo validation rules, and a local commit. User-invoked only; require an explicit issue number.

raychang Bundle

Scaffold or incrementally repair a project's harness structure (AGENTS.md/CLAUDE.md routers, gated task pipeline, roadmap/lessons with indexes, constitution, domain-agent template) following the unified layout spec. Use when starting a new project, when asked to 初始化專案 harness / 建立專案骨架 / harness-init, or when auditing an existing project against the layout spec. Additive-only — never overwrites existing files.

joelhooks Skill

Discovery skill for the Native SDK, the complete toolkit for building native desktop applications - views are declarative Native markup (.native), logic is plain Zig, and the toolkit's own engine renders every pixel, with WebView surfaces as the optional web-content path. Use when the user asks what the Native SDK is, how to build a Native SDK app, author native UI, scaffold an app, configure app.zon, add bridge commands, embed web content, package an app, test a running app, or automate a Native SDK app.

shenxianpeng Bundle

Use when the user asks to inspect a GitHub repository and find missing pieces, product gaps, contribution opportunities, roadmap ideas, quality issues, documentation gaps, or issue ideas. This skill analyzes the repository like a senior open source contributor and product manager, lists actionable gaps first, requires explicit user approval, and only then creates GitHub issues for selected ideas.

solvapay Bundle

Router and disambiguation entry point for the SolvaPay skill family. Use only when the user's intent is vague ("add solvapay to my project", "where do I start with solvapay", "what can solvapay do") and no specific surface skill has triggered. Owns the shared documentation-discovery preference and the cross-skill guardrails; routes the agent to exactly one of `create-mcp-app`, `sdk-integration`, `website-checkout`, or `lovable-checkout`. For specific intents (paywall, checkout, paid MCP, Lovable, SDK, webhooks, usage metering), the surface skills should auto-trigger -- use them directly.

spm1001 Bundle

Orchestrates estate-wide backlog review — load FIRST, before any backlog triage. 5 phases (survey, verify, summarize, act, snapshot): opens at the top of the pyramid — jobs-grouped repo headlines, then lane-aware queue alignment and lane population where the operator runs a dispatch queue — then subagents verify briefs against code and nothing closes without approval. Invoke on '/review', 'review my bons', 'backlog review', 'queue reconciliation', 'weekly reconciliation', 'what needs closing', 'clean up bons', 'triage my backlog'. Requires bon skill loaded first.

spm1001 Skill

Use Bon for opening, planning, closing, backlog review, or work on an existing Bon board. Runs the maintained Bon rites with explicit Codex runtime substitutions, preserving their reflection, user review, personal routing and durable follow-through.

sswconsulting Bundle

Use this skill when the user is working with an Aspire distributed application and needs to operate the AppHost or its resources through the Aspire CLI: start, restart, stop, or wait on the app; inspect resources, logs, traces, docs, or health; add integrations; manage secrets or config; publish, deploy, or rerun a named pipeline step; initialize Aspire in an existing app; recover missing `.modules` files in a TypeScript AppHost; discover the right frontend URL for Playwright from Aspire state; expose custom dashboard/resource commands; or understand unfamiliar Aspire AppHost APIs in C# or TypeScript. Use it even if they describe the task in terms of an AppHost, resources, dashboard, existing app bootstrap, missing generated modules, Playwright URL discovery, C# API understanding, or local distributed app workflow without explicitly naming Aspire. Do not use it for non-Aspire .NET apps, container-only repos with no AppHost, or ordinary build and test tasks.

sumitake Bundle

Prepare, structure, role-play, or debrief a sales discovery conversation for a named buyer or opportunity. Use for discovery-call plans, neutral needs-assessment questions, transcript analysis, call coaching, or deciding what must be learned before a demo or proposal. Do not use for prospect-list building, broad customer research, or reusable sales collateral; use a prospecting, customer-research, or sales-enablement skill for those when available.

mary-ext Bundle

Use when writing or revising any instruction Claude will read - skills, CLAUDE.md files, agent prompts, system prompts, hook output. Covers token efficiency, compliance techniques, discovery, and per-format templates.

maskshell Bundle

blueprint-crafting: Produces convergence-checked upstream artifacts — product spec (PRD), architecture design (arch-design), iteration plan, executable summary, and research — that parallel-development consumes as authoritative references. Use it whenever the user wants to author, rewrite, research, or convergence-check an upstream artifact: "author a spec", "write an arch-design", "produce an iteration-plan", "research X for the spec", "spec-driven", "write a PRD", "author a roadmap", "write a design doc", "decision log". Each artifact converges on its constraints-profile (process axis: anchors + authority-chain + sources); content correctness stays human (outcome axis). NOT for implementing code — feature implementation, bug fixes, and refactors route to parallel-development. Specifier half of the specify then implement pipeline.

maxim-saplin Bundle

Test-driven development with red-green-refactor loop, vertical tracer-bullet slices, and an unattended mode for delegated work. Use when the user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development. Implementation method of the backlog-native pipeline — used directly, or attached to issue workers by `orchestrate-issues` or `orchestrate-issues-watchdog`.

maxim-saplin Bundle

Grilling session that interrogates your plan one question at a time, challenges it against the existing domain model and codebase, sharpens terminology, and updates the CONTEXT.md glossary inline as decisions crystallise. Use when the user says "grill me", asks to stress-test or poke holes in a plan, wants to settle requirements, or wants vocabulary pinned down before building. First stage of the backlog-native pipeline — when the plan is settled, hand off to the `to-issues` skill.

maxim-saplin Bundle

Break a plan or spec into independently-grabbable issues as repo-local markdown files using tracer-bullet vertical slices, tracked in an issues/BACKLOG.md queue with no external issue tracker. Also the entry point for filing a single follow-up issue or a regression. Use when the user wants to convert a plan into issues, create implementation tickets, file a follow-up or bug, or break down work into issues. Second stage of the backlog-native pipeline — consumes what the `grill-me` skill settled, produces the queue `orchestrate-issues` or `orchestrate-issues-watchdog` delivers.

maxim-saplin Skill

Orchestrate serial end-to-end delivery of an issue backlog using a parent orchestrator, unattended issue-worker subagents, a per-issue acceptance gate, a drift log, and a final adversarial QA pass. Use when the user wants MVP or backlog delivery via issues, wants to work through issues/BACKLOG.md, or asks to deliver a queue of issues. Third stage of the backlog-native pipeline — delivers the queue the `to-issues` skill produced, dispatching workers that follow the `tdd` skill.

maxim-saplin Bundle

Orchestrate unattended serial delivery of an issue backlog using a parent orchestrator, issue-worker subagents, per-issue adversarial QA, an independent product-intent watchdog, a drift log, and a final integration QA pass. Use when the user wants watchdog-gated AFK delivery, named qa/watchdog gates, or COURSE-CORRECT/STOP trajectory checks. Alternative third stage of the backlog-native pipeline — same queue as `orchestrate-issues`, stricter gates.

microsoft Bundle

MatterGen workflows for property-conditioned inorganic crystal generation, MatterSim triage, adapter fine-tuning, and Azure AI Foundry hosted deployment. Use when users ask about MatterGen, materials discovery, crystal generation, property-conditioned diffusion (bulk modulus, band gap, magnetic density, HHI), MatterSim evaluation, or Azure AI Foundry materials deployment.

pacho-h Skill

Use at the start of every conversation that touches a non-trivial code or design task. Establishes the ssep skill-matching matrix (4 specialized skills — reviewing-spec-and-policy, reviewing-design-fidelity, improving-feature-completeness, running-integration-tests) and requires the matrix to be evaluated BEFORE any other action, including clarifying questions, file reads, or implementation. Triggers on any of these signals — Figma URL shared, PRD/RFC/spec text shared, "review", "구현", "검토", "implement", "ship", "production-ready", "polish", "verify", "e2e", "staging" — even when each individual word looks routine, because ssep's most common failure mode is "the task looks small, just do it" rationalization that skips the spec/design/completeness/integration checks the matrix would have flagged. Distinct from superpowers:using-superpowers which sets up generic skill discipline; this one specifically enforces ssep's four-skill matrix so domain-specific reviews are not silently skipped.

pacho-h Bundle

Reviews product specs, requirements docs, RFCs, PRDs, and policy documents from text, markdown, or Figma. Use for completeness, consistency, edge-case coverage, ambiguity, policy conflicts, or compliance gaps. Triggers on "이 기획서 검토해줘", "스펙 리뷰", "정책 검토", "review this PRD", "is this complete?", "이 기획대로 구현하면 빠진게 뭐가 있을까", "스펙 갭", "요구사항 누락", or whenever a Figma URL is shared in a planning context. Triggers even when the requirement reads as a single concise sentence (e.g. "X should default to inactive and be activatable from detail"); concise requirements hide unstated questions about default values for existing data, role/permission interactions, and state-transition edges that a structured audit surfaces in minutes. Reads sources, runs a multi-dimensional review, returns a prioritized gap report. Distinct from brainstorming (generates new designs) and reviewing-design-fidelity (compares impl vs design); this audits an existing artifact.

philchen00 Skill

Explore a running app with agent-browser and record verified selectors (test-id attribute, role, text) into discovery.md — including identifying which test-id attribute the app actually uses. Use when the user wants to verify a test plan's assumed selectors actually exist before writing test code, or continue the Verefi pipeline after /verefi:testplan.

philchen00 Skill

Generate a reviewable test-plan.md (test cases + acceptance criteria) from a feature description or test-detail file. Use when the user wants to start the Verefi pipeline, kick off spec-driven test generation, or turn a PRD/user story/feature description into a test plan before writing any test code.

philchen00 Skill

Generate Playwright TypeScript test code from a test-plan.md (and discovery.md/audit.md if present). Use when the user wants to turn an approved test plan into runnable Playwright tests, or continue the Verefi pipeline after /verefi:testplan, /verefi:audit, or /verefi:discover.

lncrawl Skill

Work the GitHub tracker's source backlog — classify requests against the corpus, find duplicates, probe hosts in bulk safely, and close in one pass. Use when asked to reduce open source issues, add requested sources at scale, or survey whether a batch of hosts is still alive.

luongnv89 Bundle

Run an autonomous triage-resolve-review-merge loop to auto-pilot the GitHub issue backlog, resolving everything until done with zero prompts. Don't use for single-issue work (/issue-resolver), triage (/issue-triage), or PR review (/issue-pr-review).