Productivity

thedotmack Skill

Execute a plan using subagents for implementation. Use after /make-plan has created a structured plan, or for any multi-phase task execution.

themattberman Bundle

Domain intelligence for writing recovery strategy, offers, cadence, and customer-facing copy in Found Money. Use when generating or reviewing a Recovery Play, an offer ladder, a win-back email sequence, or the cadence and stop conditions for a pile. Covers what to offer, how long the sequence runs, what the first message may contain, and which framings are forbidden per pile. Do NOT use to send anything, to value a pile, or to decide publication.

prime-radiant-inc Skill

Use when monitoring an in-progress toil run, checking if a run is stuck, or observing live workflow execution

prime-radiant-inc Skill

Use when writing, editing, validating, or debugging toil workflow YAML — node/edge structure, ForEach, decision tags, expression syntax (${workflow_input.X} vs ${input.X}, supported node fields, required ! refs), or analyzing why a run misbehaved

processcube-io Skill

Erstellt Releases (Stable, Insiders, Development) mit Single-Branch-Workflow (nur main). Nutze diesen Skill wenn der Benutzer eine Version erstellen oder releasen möchte.

profsynapse Bundle

Use when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.

prometheas-labs Skill

Use when creating or modifying moon.yml project configs, adding tasks, defining file groups, or configuring task options

promptmechanic Bundle

Rewrite AI-sounding prose so it reads as considered human writing — cut the tells (em-dash pile-ups, "it's not X, it's Y" antitheses, inflated vocabulary, uniform rhythm, empty uplift) while preserving every fact, claim, and the author's own voice. Use when the user says "make this not sound like AI", "de-AI this", "humanize/humanise this", "this reads like ChatGPT", "remove the AI tells", "it sounds robotic/generic", or shares a draft (post, email, essay, docs, cover letter) to sharpen into a more human voice. Ships a stdlib scanner that flags the mechanical tells.

purewhiter Skill

Use when adding or modifying offline judge tests for bench_env tasks — specifically entries in `OFFLINE_JUDGE_POSITIVE_CASES` / `OFFLINE_JUDGE_NEGATIVE_CASES` in `bench_env/tests/<suite>/test_tasks.py`, or writing live tests. Triggers after a new task is added, or when tightening judge coverage.

purewhiter Skill

Use when designing a new bench_env task suite, adding several new tasks to an existing suite, or critiquing a task-set proposal for a mobile-gym App — before any `class FooTask(...)` is written under `bench_env/task/`.

purewhiter Skill

Use when writing or modifying `check_goals()` / `get_answer()` / App `check_*` methods in `bench_env/task/`, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.

pwrdrvr Bundle

Plan and publish a GitHub Release in a tag-driven repository. Use when a user asks to cut, prepare, or publish a software release, propose the next vX.Y.Z tag, support prerelease tags like vX.Y.Z-beta.N, draft better release notes from PRs and direct commits since the last release, update CHANGELOG.md, create the tag pinned to an exact commit, and watch the publish workflow.

qiaeru Skill

Cut a new version of one of the owner's public GitHub repos. Use whenever the owner asks to publish, ship, tag, bump, or release a version (patch/minor/major, CHANGELOG promotion, tag, GitHub Release). Adapts the steps to the repo lock (PR workflow vs direct-to-main) and docs language.

qiaeru Skill

Pre-commit and pre-push checklist for the owner's public GitHub repos. Run before every commit, push, or PR, even a one-line change or a plain "push this". Covers the Git workflow (branch/PR or direct-to-main per the lock, conventional commits), comment pruning, and docs/CLAUDE.md/CHANGELOG upkeep.

raelli Skill

Octowiz AI coding workflow coordinator. Reads IntegraHub memory doctrine at runtime, detects where you are in the development lifecycle, and routes to the right skill combination from superpowers + mattpocock-skills. Use this skill at the START of any development work — whether you have a fresh idea, an existing plan to stress-test, code ready to implement, or work ready for review. Invoke when the user types /octowiz, starts a new feature, asks how to begin a coding task, or says something like "let's build X", "I want to work on Y", "I have a plan", or "can you review my code".

ricocc Skill

Resource recommendation article generator with multi-turn workflow and domain adaptation. Creates structured articles with verifiable data, proper formatting, and professional style. Use when user explicitly requests to generate/write/create a recommendation article (生成/写/创建 + 推荐文章/资源列表). Must include both action + article intent. Don't trigger on simple questions like "推荐几个工具".

ronanpinho-ipt Bundle

Acts as a bilingual (English/Spanish) fundraising copy lead for US nonprofits. Use this skill whenever someone needs a donor-facing appeal, email, letter, or social post produced in both EN and ES — where the Spanish version is a cultural transcreation aimed at US Latino philanthropy, not a literal translation, and the two versions are checked for ask/CTA parity. Triggers on phrases like "bilingual appeal", "EN/ES appeal", "Spanish donor letter", "translate this appeal to Spanish", "transcreate to Spanish", "Latino philanthropy outreach", "Hispanic donor email", "bilingual fundraising email", "Spanish version of our year-end appeal", "make this appeal bilingual", "español para donantes", "carta de donación en español", "campaña bilingüe", "bilingual newsletter blurb", "Spanish social post for donors", "bilingual giving Tuesday", "EN/ES parity check", "cultural fluency review", "usted vs tú for donors", "neutral Spanish for a national audience", "bilingual CTA", "Spanish-language major gift letter", "dual-lang

neuralblitz Bundle

Guide for performing Node.js version upgrades in the Electron project. Use when working on the roller/node/main branch to fix patch conflicts during `e sync --3`. Covers the patch application workflow, conflict resolution, analyzing upstream Node.js changes, building, running the Node.js test suite, and proper commit formatting for patch fixes.

neuralblitz Bundle

Guide for performing Chromium version upgrades in the Electron project. Use when working on the roller/chromium/main branch to fix patch conflicts during `e sync --3`. Covers the patch application workflow, conflict resolution, analyzing upstream Chromium changes, and proper commit formatting for patch fixes.

nikiforovall Bundle

Use when user explicitly requests planning with files, or asks for persistent tracking of a complex task.

nikiforovall Bundle

Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the `scratch` CLI so a pad's files are registered and viewable.

oaustegard Bundle

Cross-session memory operations against the Turso store — the advanced half; plain profile loading and simple recall/remember are already in project instructions. Use for "store this correction so future sessions have it", "what did we decide about X", "supersede or forget a memory that is now wrong", "search my long-term notes", "write a memory with tags and priority", "consolidate or prune the store", "save a checkpoint and resume it next session", or any question about a remember/recall/config/journal signature and its edge cases. Covers background writes, supersede chains, time-windowed and multi-tag queries, batch APIs, session scoping, retention and curation, episodic scoring, decision traces, and task discipline. Not for notes about the session currently in progress (use session-memory) and not for ranking documents or code by relevance (bm25).

osick Bundle

Accurate time, date, duration, and stopwatch operations. USE THIS instead of guessing — Claude has no wall clock and makes calendar arithmetic mistakes (off-by-one on days, wrong weekday, leap years, DST, timezone conversion). Triggers include "what time is it", "what's today's date", "how long did X take", "how many days until/since Y", "what weekday was Z", "start/stop a timer", "what's N weeks from now".

sap-samples Bundle

Use for end-to-end CAP change workflows: modify CDS/handlers, regenerate artifacts, and run a short verification checklist for this repository.

swc-project Bundle

One-shot repair workflow for SWC pull requests. Use when asked to repair a PR by resolving merge conflicts, applying unresolved actionable reviews from chatgpt-codex-connector[bot], resolving those review threads, fixing failing CI, committing the repair work in coherent chunks, and pushing once at the end.

thedotmack Bundle

Generic automated semantic versioning and release workflow. Handles version increments, git tagging, GitHub releases, and automated changelog generation for any repository.

xano-inc Skill

Discover and profile a Xano workspace to understand how to develop safely with it using the sandbox workflow

zhu327 Skill

Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building workflows across tools, setting up triggers and actions, or optimizing existing automations. Covers automation opportunity identification, workflow design, tool selection (Zapier, Make, n8n), testing, and maintenance. Trigger on "automate", "automation", "workflow automation", "save time", "reduce manual work", "automate my business", "no-code automation".

vibeknow Bundle

Generate videos from documents/URLs/files, track video task progress, download results, list voice templates. Use when: user wants to create a video, check task status, download video, or browse voices.

vitaliikapliuk Skill

Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.

neptunehub Skill

Fast, project-specific review of a target - the working tree (default), a commit, a range, a branch, or a PR - against the head of remote main. Hunts regressions in callers, task-queue and multi-server contract breaks, build-matrix breaks, 1M-song scale and idle-RAM defects, and breaches of this project's hard rules. Output is ONE table - change requested, priority, risk of regression. Use when the user wants a commit, branch, PR, or work in progress reviewed.

nimblebraininc Bundle

Generates a comprehensive activity digest for a JSONPlaceholder user by aggregating their posts, comments, and todo status. Use when you need a summary of what a specific user has been doing, including their content output and task completion rate.

notjoon Skill

Rules for writing and revising code comments. Use whenever you write a new comment, review or rewrite existing comments, or a task asks you to clean up, tidy, or refine comments. Follows the Linux kernel commenting guidance for prose and intent, while leaving comment delimiters and layout to the host language or project.

nvidia Bundle

Execute equivariant polynomials in JAX using segmented_polynomial (naive/uniform_1d), the ir_dict workflow with IrDictPolynomial and dict[Irrep, Array], and Flax NNX layers (IrrepsLinear, SphericalHarmonics, IrrepsIndexedLinear). Use when writing JAX code with cuequivariance.

oalangomes Skill

Analyze GitHub Actions workflow architecture and performance without changing workflow files by default. Use when the user asks about CI speed, queue time, critical path, parallelism, needs dependencies, matrices, caching, artifact reuse, runner capacity, duplicated workflows, or GitHub Actions optimization. Combine static workflow evidence with observed GitHub run/job history when available, and label recommendations as STATIC, OBSERVED, or ESTIMATED.

ob-labs Skill

运行预定义的 AI coding workflow。当用户提到 /workflow、工作流、workflow 或类似语义时触发。