Productivity

latias94 Bundle

Prepare and validate a focused Merman pull request with change-scoped Rust, FFI, feature/dependency, generated-license, workflow, platform, and performance checks. Use when opening, updating, reviewing, or repairing a PR, deciding whether a CI gate is redundant, or handing off a branch for review.

leancodepl Skill

Workflow for fixing a reported bug in the Patrol monorepo — reproduce, locate the right package, fix without regressions, verify, and open a PR. Use when asked to fix a GitHub issue (e.g. "fix issue

liustack Bundle

Task-state snapshots for session handoff. Write a resumable snapshot when wrapping up, restore from it when picking the work back up, trusting its decisions and re-checking its facts. Use when the user says 打个快照 / 交接 / 收尾下次接着做 / 换个会话继续 / 上次做到哪了 / 快没上下文了先记下进度 / snapshot this task / handoff / wrap up this session / pick up where we left off. Do not trigger for jest/vitest test snapshots, VM/database/filesystem snapshots, compressing the current conversation (that is /compact), remembering long-term preferences (that is platform memory), or deliverables addressed to humans (design docs, onboarding docs).

luizsiqueira-eng Skill

Configura e opera o fluxo de trabalho no board do time em Jira ou Trello: na primeira execução entrevista a pessoa para mapear projeto/quadro, colunas, tipos de item, campos (ou custom fields do Trello) e em que momento cada um é preenchido, e grava o mapa em .claude/board-workflow.md; depois usa esse mapa para criar, refinar, mover, comentar e consultar cards. Para quem ainda não tem fluxo definido, sugere um quadro padrão (Aguardando → Em Desenvolvimento → Code Review → Qualidade → Validação → Pronto). Invocar quando pedirem para configurar o Jira ou o Trello, criar/mover/atualizar/comentar card, ver o que está em cada coluna do board, ou quando não souberem qual fluxo adotar.

lza6 Skill

This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.

primeline-ai Bundle

Use when you have a multi-step task, before touching code. Creates bite-sized implementation plans with TDD emphasis, then executes them in batches with review checkpoints. Prevents the "just start coding" trap.

pszypowicz Bundle

Go development with toolchain-first verification workflow. Use whenever the user (1) writes, modifies, debugs, or reviews Go code, (2) works with go.mod, go.sum, or Go module dependencies, (3) writes or runs Go tests, benchmarks, or fuzz tests, (4) mentions go doc, go vet, go fix, go test, go build, go mod, gofmt, staticcheck, golangci-lint, govulncheck, or pprof, (5) asks about Go error handling (errors.Is/As/AsType/Join), concurrency (goroutines, channels, sync, context), interfaces, or package design, (6) encounters Go compiler errors, test failures, or race conditions, (7) profiles Go code for performance or works with PGO, (8) asks about Go best practices, code review, or idiomatic Go, (9) works with files ending in .go or _test.go, (10) wants to modernize Go code to 1.21-1.26 features. Trigger this skill proactively when the user is working in a Go codebase even if they do not explicitly ask for Go help - the toolchain-first workflow (verify APIs with go doc before coding, run go vet after) catches bugs

pudap Bundle

Discover PUDA experiment workflows for bears and choose the right experiment for the task. Use when you need to run, set up, or understand a PUDA experiment such as colour mixing optimization.

r6410418 Skill

Repository-level wrapper for the canonical Qwen MTP or nextn GGUF release workflow. Use when Codex needs to prepare, validate, convert, quantize, smoke-test, or optionally release Qwen-family GGUF artifacts from this repository while preserving the canonical implementation under qwen-mtp-gguf/.

joeyave Bundle

Entry-point router for Go architecture and refactoring tasks focused on DDD-style services. Use when working on a Go service and you want one skill to decide whether the task is primarily about architecture boundaries, domain-first refactoring, pragmatic CQRS, or delivery and test support. This skill should select one or more companion skills and apply them in the right order.

jorgenosberg Skill

Inflate a memory file (CLAUDE.md, AGENTS.md, notes, todo lists) from plain English into ornate Early Modern English prose, while keeping every code block, URL, path, command, identifier, heading, date, and table untouched. A human-readable backup is written to `<file>.original.md`. Trigger: /shakespeare-expand <filepath> or "expand memory file".

jv-vogler Skill

Use when reviewing a pull request or branch locally without posting to GitHub — the user says "review PR #N", "review this PR locally", "check this branch's changes", "review my diff", asks whether a PR matches its ticket or does what the task asked, or wants review comments written to a file to read, filter, and copy before publishing anything.

kestra-io Skill

Migrate an Airflow DAG to a production-ready Kestra flow. Extracts Python task logic into namespace files, maps DAG dependencies to Kestra tasks, and preserves parallel execution structure.

kevintsengtw Bundle

This skill should be used when running .NET tests selectively with a build-first, test-targeted workflow. Use it for running tests with xUnit focus.

kubeflow Bundle

Scaffold a new catalog plugin: run catalog-gen, replace all panic("TODO") stubs with minimal working implementations, generate OpenAPI server stubs, and verify the build compiles. Produces a plugin that starts without crashes.

lackeyjb Bundle

Test-Driven Development guidance. Use when writing code, implementing features, or fixing bugs in projects that follow TDD methodology. Provides the Red-Green-Refactor cycle structure.

lackeyjb Skill

Auto-load Conductor project context when conductor/ directory exists. Use for any development task in a Conductor-managed project to ensure alignment with product goals, tech stack, and workflow methodology.

shenxianpeng Bundle

Analyze GitHub issues, implement fixes or features, and create pull requests. Use this skill when the user says something like "fix this issue", "create a PR", "submit a pull request", "draft a PR", "fix bug", "can you help with issue #123", "let's fix this problem", or any request to analyze and resolve a GitHub issue followed by creating a PR. This skill handles the full workflow: understanding the issue, writing code, committing with conventional commits, and opening a PR. Make sure to use this skill whenever the user wants to fix, resolve, or address a GitHub issue, bug, feature request, or task, especially when they want a PR to be created as the final deliverable.

solana-foundation Skill

Reviewer workflow for completing a Kora mainline release after the release PR is merged. Squash-merges the PR, detects whether Rust and/or TypeScript changed, then triggers the correct publish workflows on main. For hotfix releases, publish from hotfix/* before merging back. Use when the user says 'complete the release' or 'merge and publish' (mainline only).

spatie Bundle

Write and review Bloom Swift concurrency code for actor isolation, task lifetime, cancellation and stream correctness.

speakeasy-api Skill

Set up granary in a new project. Use when asked to initialize granary, install it, or get started with task management.

spm1001 Skill

Activate at session start when .bon/ exists AND before any bon CLI command. Handles session orientation (process contributions, present hierarchy, pick direction), structures draw-down workflow (bon show → bon work → bon step), and covers roaming — orienting against a named repo from a session launched elsewhere. Triggers on: session start with .bon/, /open, '/open REPO' (a path or repo name), /bon, 'bon init', 'bon new', 'bon list', 'bon done', 'what can I work on', 'next action', 'desired outcome', 'file this for later', 'track this work', 'work on that repo from here', or when .bon/ directory exists.

spscream Skill

Orient a fresh session before touching any file — read the current-state file, the relevant half's own guidance, and that half's memory index, then verify live facts with `bash .floppy/run status` instead of trusting the documents. Use at the start of a session, when picking up a new task or branch of work, or when the user asks to start, orient, or "what's next".

stackrox Skill

Pull-request merge

stackrox Skill

Pull request review

starslingdev Bundle

Diagnoses GitHub Actions failures and attributes CI time and cost using StarSling's `sling` CLI. Invoke this BEFORE using `gh` or fetching any logs whenever the user asks why a job or run failed, what made a run slow, about runner minutes or CI cost, asks to re-run or cancel a run, or pastes a GitHub Actions URL — `sling` returns server-classified failure causes and cost attribution that log-grepping misses; state changes route to `gh`. Not for repo-wide audits of workflow files (ci-score, ci-speedup, ci-secure), writing workflow YAML, or non-GitHub-Actions CI.

sumitake Bundle

Prepare or review a commercial negotiation for a specific sales opportunity. Use when the user must evaluate a discount request, scope trade, payment schedule, contract length, concession, renewal term, walk-away point, or package of deal options. Use sales-objection-handling instead when the immediate task is understanding or answering a value, trust, fit, or timing concern without designing a concrete trade. Do not use for company-wide pricing, packaging, or offer strategy; use pricing or offers skills for those when available.

sumitake Bundle

Analyze and respond truthfully to a specific buyer concern in an active sales opportunity. Use for objection diagnosis, response coaching, role-play, call follow-up drafts, or reviewing how a rep handled pushback. Use sales-negotiation instead when the immediate task is to design a numeric concession, scope trade, payment change, contract term, or other commercial exchange. Do not use for a reusable objection playbook or broad sales collateral; use a sales-enablement skill for that when available.

sylviachenxy Bundle

将模糊的学习或生活意图转化为有证据、现实可行且由用户确认的 SMART Goal Contract，通过准入后把完整 Goal 文档写入 Obsidian，并通过本机 EventKit 将近期行动与时间安排投影到 Apple Reminders 和 Apple Calendar，由 iCloud 负责设备传播，持续 check-in 和调整。用于明确目标、核实上下文、诊断基线、制定或修订计划、处理阻塞以及判断继续、暂停、达成或放弃；不用于单条提醒、单纯安排日历、撰写完整周报、管理团队项目或代做目标本身的任务。

sylviachenxy Bundle

基于用户确认范围内的 Obsidian Goals、Apple Reminders/Calendar、Mac 文件与 Git、Apple Notes 和 Gmail/Apple Mail 证据，完成个人周复盘并把经用户确认的成果、进展、学习、阻塞和下周重点写入 Obsidian。适用于“写周报”“复盘本周”“这周完成了什么”和追踪学习生活进展；不用于公司周报、单纯查看日程、建立或修改 SMART Goal、直接安排下周日程，或把设备活动自动评价为成果。

sylviachenxy Bundle

使用 Apple Reminders 和 Apple Calendar 管理已经决定的个人提醒与日程：捕捉单条事项、查看今天或本周、检查冲突、安排一天或一周、改期、完成、删除和对账。适用于个人学习与生活安排；不用于建立 SMART Goal、修改 goal-planner 管理的对象、撰写周报、团队项目管理或代替用户处理会议邀请。

makeplane Skill

Translate or update keys in packages/i18n/src/locales. Use whenever adding, changing, or reviewing strings across any target locale — enforces do-not-translate terminology, CLDR plural forms, placeholder/tag preservation, per-locale punctuation/register, and the AI-translation review workflow. Required reading before touching any *.json under src/locales.

manu-brighter Skill

Breaks any context (a concept, code, an error message, jargon) down into a simple explanation an absolute beginner can follow — friendly "Erklärbär" persona (ʕ•ᴥ•ʔ), everyday analogies, compact, ASCII diagrams where they help, kaomoji instead of emojis. Detects whether the user wants to understand it themselves or needs something forwardable, and answers in the language of the input. Use when the user explicitly asks for something explained simply or for someone with no background knowledge. English signals: "ELI5", "explain like I'm five", "for dummies", "in plain English", "break it down", "dumb it down", "I don't get X", "for my grandma". German signals: "erklärbär", "erklär mir das einfach", "für meine Oma", "auf normal-deutsch", "mach das simpel", "ich raff X nicht". Do NOT use for normal developer-level questions ("what does this function do", "why is the test failing", "make the code simpler") — without an explicit simple/beginner signal the bear does not trigger.

manu-brighter Skill

Shows a compact overview of all available skills with a one-line description each — grouped into Custom (your own), Plugins/Add-ons, and built-in Claude Code skills. Meant as an at-a-glance overview so you don't lose track when you have many skills installed. Use this skill whenever the user wants to know which skills they have — even if they only say "which skills do I have", "skill overview", "list skills", "list custom skills", "show me my skills", "what skills are installed", "which custom skills exist", "short skill list", "overview of skills" or similar. Also triggers on questions about plugin skills or "which plugins/add-ons ship skills". Replaces the long, verbose scrolling through the system skill list with a terse table.

mary-ext Bundle

An independent advisor. Call this before performing or planning any substantive work, when you believe the task is complete, when you believe you are stuck, when you are considering a change of approach, or when you need a second opinion.

mary-ext Bundle

Drives the user's running Chrome via the Playwriter CLI. Use when the task needs their browser identity — cookies, logins, open tabs, profile.