Productivity

joeczar Skill

Checkpoint Workflow Skill

gittools Skill

Guided GitVersion release workflow — analyzes unreleased changes, checks release readiness (milestone, labels), creates the GitHub release, verifies published artifacts, and monitors downstream PRs (Homebrew, winget, GitTools Actions).

mrrobertkent Bundle

Extract frames from video files using ffmpeg and analyze them with Claude's multimodal vision. Supports animation timing analysis, page load performance review, and user workflow progression. Automatically detects annotations drawn with the record-browser skill. Use when working with video files, screen recordings, animation validation, or visual analysis of UI behavior.

nomcopter Bundle

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

wuji-labs Bundle

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.

wuji-labs Skill

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.

azusachino Skill

Use Asobi's persistent SQLite knowledge graph for session continuity, durable task dispatch, keyword recall, and reusable skills.

bitrouter Bundle

Use when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely uncategorized evaluator sources.

blackstone2333 Bundle

Use only when installing, upgrading, or repairing the Goldilocks Skill and Codex native-host pack. Never invoke for ordinary task execution, routing, planning, or delivery.

blokadaorg Bundle

Use for dynamic inspection and navigation of the Blokada app through the repo-local Appium machine session. Trigger when Codex needs to explore the live native UI on a real device, inspect labels or structure, tap through screens, capture screenshots or XML on demand, or verify interactive behavior without writing a static WDIO spec. The current workflow is implemented for iOS, but the skill name stays generic so it can later cover other Appium-backed platforms too.

blokadaorg Skill

Use for pulling recent Blokada app logs from a connected device, using the same share-log file exposed in Settings. Trigger when Codex needs the most recent app log lines for debugging, wants logs from the last hour or today, or needs a manual operator workflow for recent device logs without going through Appium UI automation.

bluerock-io Skill

Drafts a meeting recap email from call notes, in my voice — the recap I send the people I met with. Use when I say "recap that meeting", "draft a follow-up", "follow-up email from this call", "send them a summary", or paste meeting notes or a transcript. Reads today's notes file (or the file I name) if I don't paste anything.

blyatiful1 Skill

Run a task in hard mode — the staged discipline protocol (frame → explore → plan + adversarial critique → implement in verified increments → independent verify → review → bank lessons). Use for hard, multi-file, or high-stakes tasks; whenever the user invokes /hardmode, says "hard mode", or asks for maximum quality/thoroughness/rigor. Not for trivial edits or questions.

bmad-code-org Skill

Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev/review session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as /bmad-loop-resolve <story-key>. Unlike the automated dev/review sessions this session is interactive — a human is present and you SHOULD ask.

bohorquezandrea Skill

Convierte una lista de tareas en un día estructurado por bloques de energía (Trabajo Profundo, Shallow, Salud, Recuperación) basado en cronotipo del usuario, ciclo hormonal si aplica, calidad de sueño, y filtro de propósito personal. Genera el calendario listo para pegar en Google Calendar o cualquier agenda. Activa este skill cuando el usuario diga "organizame el día", "arma mi calendario", "planea mi día", "hazme el plan de mañana", "necesito bloques de tiempo", o cuando comparta una lista ya organizada y pida agendarla.

boojack Bundle

Manually invoked rewriting capability that restructures and tightens supplied prose or notes so their purpose, reasoning, and decisions are clear, direct, and precise without changing meaning or claim status. Use only when the user explicitly invokes the skill. It rewrites supplied content; do not activate it for ordinary requests whose only task is rewriting, summarization, translation, fact-checking, or writing from scratch.

bwitlin Skill

Run multiple skills on the same task in parallel and compare outputs side by side. A creative pitch room -- give it a brief, and it finds skills (local + trusted community repos) to work on it independently, then presents all outputs for comparison. Use when asked to "skill battle", "compare skills", "run multiple skills", "pitch room", "get different takes", "split test this", "give me options", or any request to see how different skills handle the same task. Great for generating variants for split testing -- headlines, email copy, ad creative. Best for subjective work where different perspectives add real value. Not useful for tasks with one right answer (bug fixes, migrations, config changes). Always use this skill instead of manually running skills one at a time when the user wants to compare outputs.

capawesome-team Bundle

Core principles, workflow, and maintenance for using Firebase. Use this for all Firebase CLI tasks, building, service setup, and REFRESHING or UPDATING an existing environment. Make sure to ALWAYS use this skill whenever you are trying to use Firebase, even if not explicitly asked.

apollographql Skill

Use when the user asks to "publish a release", "create a release", "cut a release", "prepare a release", "do a patch release", or "set up a release". Covers the full Apollo iOS release workflow including GitHub Actions, CHANGELOG updates, PR management, and draft release publishing across apollo-ios and apollo-ios-codegen repos.

arcadeai-labs Skill

List, disconnect, reconnect, and fix the apps Arcade is connected to for the user, including switching accounts, expired sign-ins, and missing permissions, plus the one-time sign-in when a task needs an app that isn't connected yet. Use when the user asks which apps are connected, wants to disconnect, reconnect, or switch the account for an app, or a tool returns a sign-in link. Not for performing tasks inside apps.

arcreel Bundle

当用户要求创建视频、新建或继续项目、推进下一步、检查进度、完成或导出时，编排 ArcReel 视频项目。用于端到端工作流请求，不用于仅编辑某个现有产物。

axoniq Bundle

Create well-structured GitHub issues from any source: meeting notes, transcriptions, conversation context, informal descriptions, or direct requests. Use when the user says "create a github issue", "create issue from notes", "write up an issue", "turn these notes into an issue", "file a bug", "file a bug from meeting notes", "create enhancement from discussion", "make an issue for", "open an issue about", "create a follow-up issue", or any variation of creating a structured GitHub issue — whether the input comes from notes, conversation context, or a direct description.

molefrog Skill

Release moi-computer to npm — verify locally, hand off to the gated GitHub Actions workflow, then verify the published package. Defaults to a `next` preview; pass `stable` for a `latest` release. Use when the user asks to publish, release, ship a version, or cut a dev preview.

mudrii Skill

Applies a rigorous JavaScript and TypeScript development workflow focused on clean project structure, strict single responsibility, DRY design, TDD and ATDD, dependency injection, strict typing, readable error handling, and lint or static-analysis discipline. Use when implementing or repairing JS/TS business logic, tightening tests around behavior changes, removing weak types such as any, replacing hidden dependencies, cleaning up hardcoded values, or enforcing stronger code quality guardrails.

mudrii Skill

<objective>

n0an Skill

Find a past transcription by natural-language query or keyword and rewrite it with an AI preset using vivadicta. Use when the user wants to turn existing dictation into action items, an email, a summary, or any other preset output.

nasa Skill

Update AGENTS.md to reflect recent repository workflow, architecture, and policy changes while preserving existing project constraints.

neonwatty Bundle

Manage Job Apply's local profile, reusable answers, application history, and resumable sessions. Use whenever a Job Apply workflow needs to initialize, migrate, read, or update persistent applicant data.

nibzard Skill

Prepare and publish a GitHub release with semantic versioning, updating PROJECT_VER and CHANGELOG, tagging, and using GH CLI to publish. Use after major changes or when asked to cut a release.

nibzard Skill

Work on a new feature or fix by creating a branch, implementing changes, and submitting a PR with GH CLI. Use when picking up a new todo item.

nickyjacobs Skill

Start de rapport_reviewen workflow. Gebruik dit wanneer de gebruiker een rapport of sectie wil laten nakijken op taal, APA, humanisering en structuur. Activeer proactief bij vragen als "check dit rapport", "nakijken", "review", "klaar voor inlevering?", "controleer mijn tekst".

nickyjacobs Skill

Start de rapport_schrijven workflow. Gebruik dit wanneer de gebruiker nieuwe academische tekst wil schrijven (inleiding, methode, resultaten, discussie, conclusie of volledig rapport). Activeer proactief bij vragen als "schrijf een...", "maak een sectie over...", "stel een inleiding op...".

nickyjacobs Skill

Start de rapport_herschrijven workflow. Gebruik dit wanneer de gebruiker bestaande tekst wil verbeteren, humaniseren, parafraseren, formaliseren of inkorten. Activeer proactief bij vragen als "verbeter deze tekst", "herschrijf...", "maak dit academischer", "parafraseer...".

nodatime Skill

GitHub workflow conventions: writing clear conventional commits, opening detailed issues and PRs via the `gh` CLI, and choosing trunk-based vs short-lived branch flow based on the size of the change. Use whenever the user wants to commit, branch, push, open an issue, open a PR, or asks how to structure any of those. Keep it light — direct, detailed messages, no ceremony.

nord342 Skill

Review and maintain the cross-meeting action ledger (ACTIONS.md) — show what's open, overdue, or due soon, filter by owner, and mark items done. Use when the user asks "what are my open action items", "what's overdue", "what does Sarah owe me", or wants to check off completed tasks.

cdmorozov Bundle

Teach any subject the way an excellent human tutor does — with direct explanations for questions and guided practice for work the learner must do. Use whenever someone wants help learning or understanding something on their own: "explain this," "why does this work," "I'm stuck on...," "help me understand...," "is my reasoning right," "check my solution," "I want to learn X." For a standalone concept or information question, answer directly rather than turning it into a quiz. For an active learning task, guide the learner's thinking. Do NOT use for purely transactional information needs where the person clearly has no learning goal (e.g., "what's the capital of France for my quiz app"). If a subject-specific tutor skill fits, prefer it; this is the fallback.