Productivity

tektoncd Skill

Review a pull request or code change in tekton-pruner. Use when asked to review a PR, evaluate a diff, or assess code quality. Applies Tekton community standards, Go best practices, operator patterns, and pruner-specific domain knowledge (reconciler logic, ConfigMap validation, TTL/history semantics).

tektoncd Skill

Run unit tests, linters, and e2e tests for tekton-pruner. Use when verifying a code change, preparing a PR, debugging a test failure, or checking overall project health. Covers `make test-unit`, `make fmt`, `make yamllint`, and the e2e test suite requiring a live cluster.

tektoncd Bundle

Generate a conventional commit message for tekton-pruner. Use when the user asks to "create a commit", "generate commit message", "commit changes", "make a commit", mentions "conventional commits", or discusses commit message formatting. Provides guided workflow for creating properly formatted commit messages with line length validation and required trailers.

tektoncd Skill

Sync reusable workflow digests from tektoncd/plumbing into this repo's .github/workflows. Use when updating pinned SHA digests for workflows sourced from tektoncd/plumbing (e.g. _chatops_retest.yml, _cherry-pick-command.yaml), or when checking whether local workflow pins are behind the current main branch of the plumbing repo.

tenstorrent Bundle

Profile and optimize TT-Lang kernels for performance. Covers auto-profiling, perf summary, signposts, and optimization workflow.

yugabyte Skill

Interactive git rebase workflow with conflict-by-conflict review. Use when the user asks to rebase a branch, rebase onto main, resolve rebase conflicts, or update a branch with upstream changes.

zerx-lab Skill

gettopic 编译期插件机制:以低侵入方式新增后台管理模块(后端 RPC + 表 + 前端动态页 + 菜单 + 授权),不破坏单二进制 / CGO-free / Casbin 唯一授权 / proto 唯一契约。当用户要用插件方式扩展、用 task new-plugin 脚手架、新增/启用/禁用/卸载插件、或排查插件注册/校验/动态前端页问题时使用。Keywords: plugin, 插件, plugin system, 插件机制, task new-plugin, task plugin-pack, 脚手架, scaffold, 上传插件, 安装插件, 卸载插件, install plugin, uninstall plugin, upload, zip, InstallPlugin, UninstallPlugin, internal/plugin, installer, all.go, ValidateAll, RegisterHandlers, 动态路由, import.meta.glob, p.$, pub.$, plugin-components, 编译期插件, compile-time plugin, 插件注册, 插件禁用, 插件卸载, teardown, PLUGIN_UPLOAD_ENABLED

zerx-lab Skill

Run the project's acceptance gate (`task verify`) and fix any typecheck, test, or lint failures it reports. Use before committing, before declaring a task done, or whenever the user asks to "verify", "run checks", or "make sure it passes".

zerx-lab Skill

Diagnose why `task dev` hot-restart isn't picking up Go changes (no sidecar respawn, stale endpoints, renderer hitting old port/token). Use when the user reports "I changed Go code but nothing happened", "the backend didn't reload", or "the watcher seems stuck".

zhangxiansheng-888 Bundle

按船长AI视界规定的01→02→03→04顺序，依次调用中文影视创作、真人感人像提示词、静态图像提示词、分镜与人物情绪融合技能。Use when the user asks for 船长AI视界完整流程、从灵感到分镜、一键工作流、按顺序调用全部技能、部署后生成完整内容，或要求不得跳步、不得打乱技能与产出顺序。

jrswab Skill

Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.

pproenca Skill

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

pproenca Skill

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

pproenca Skill

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

promptingcompany Bundle

End-to-end interactive workflow — pick a product, then either run existing tasks and environments (Path A) or set up new ones from docs, suggested tasks, credentials, and templates (Path B). Builds the experiment, attaches signals, and optionally triggers the first iteration. For high-stakes customer deliverables, Usability Benchmark Design generates a rigorous, demand-ranked, two-arm friction-delta benchmark instead of quick suggestions. For product comparisons, Cross-Product Benchmark creates shared use-case configuration, then one product-scoped TPC experiment per provider. Trigger when users say: "set up an experiment", "create an experiment", "I want to run an experiment", "run my tasks", "setup experiment", "new experiment", "configure an experiment", "experiment setup", "usability benchmark", "friction delta", "skill-off vs skill-on", "does the skill help", "compare products", "benchmark products", "compare providers", "same tasks across products", or "PlanetScale vs Neon vs Supabase".

srombauts Skill

Standard end-to-end workflow for working on a task in this repository: branch naming, implement + tests + style, self-review, commit, `docs/ISSUES.md` cleanup, push the branch, and open a PR with `gh`. Use when starting work on an entry from `docs/ISSUES.md` (or, when one is filed, a GitHub issue).

srombauts Skill

Design and review guidelines for this SDL3 Pong codebase: frame-loop constraints, testable layering, and design patterns. Use when designing new features, populating the ISSUES.md, implementing a task, reviewing a diff or branch, or when the user asks for an architecture or standards check.

tmdgusya Skill

Primary execution workflow for durable /goal runtime. Use when a Goal Contract is active or when the user asks to execute, continue, verify, or complete a goal.

tmdgusya Skill

Rob Pike's 5 Rules of Programming — a decision framework that prevents premature optimization and enforces measurement-driven development. Use when the user says "optimize", "slow", "performance", "bottleneck", "speed up", "make faster", "too slow", or any request to improve code speed/efficiency. Also use when you notice yourself about to suggest a performance optimization without measurement data. This is a thinking discipline, not a tooling workflow.

ethereum-optimism Skill

fix-todo

evomap Skill

Run an evolution checkpoint — recall relevant past outcomes, reflect on the current task, and record what was learned. Use when the user requests an evolution checkpoint or asks to "evolve" or "checkpoint".

factorial-io Skill

Use when working with himalaya CLI for email management - reading, composing, searching, organizing, or scripting email workflows

fairladyz625 Bundle

Start Harness Anything task creation by choosing a software/coding preset first. Use when creating or planning a harness task package.

fhui Bundle

对已生成的 UI DSL 做生产级 selector 补全与校准，支持 dry 候选生成和 probe 受控状态推进两种模式。适用于读取交付目录中的 ui-dsl/ui-test.dsl.yaml，通过 seed selector、安全 click、runtime-confirmed click、reuse-session 和 Playwright locator count 校准 todo selector，并输出 enriched DSL、补全报告和未解决清单；不生成 spec，不运行测试，不做业务断言。

forsonny Skill

Decompose a confirmed contract into an atomic task DAG with wave ordering. Every task cites one or more contract criterion ids.

forsonny Skill

Dispatch one fresh subagent per plan task inside a per-task git worktree. Capture diff and tool output; never carry state across dispatches.

forsonny Skill

On verify or judge fail, append a non-null lesson to the Ledger and re-queue the task. Null lessons are refused; the task escalates instead.

fynnfluegge Skill

One-shot a whole project on an agtx board: decompose the goal, run every task unattended, unblock the workers, and merge each one. Use when the user wants a long autonomous run rather than a single session.

fynnfluegge Skill

Plan a task implementation. Analyze the codebase, create a detailed plan, write it to .agtx/plan.md, then stop and wait for user approval before making any changes.

yournextstore Skill

Rebase all theme-* branches onto main, resolving conflicts while preserving each theme's visual identity. Force-pushes directly to theme branches with backup tags. Run as a scheduled task or one-off.

zebbern Skill

Use when a coding task would benefit from delegating work to Cursor in the background — fast parallel implementation, scaffolding, or an everyday review running while the session continues. Lets Claude drive the cursor companion itself (task, review, status --wait, result) without the user typing /cursor:* commands.

meleantonio Skill

Git workflow and commit conventions. Use when committing code, creating branches, or making pull requests.

pingcap Bundle

Create or update a page-generation workflow in website-docs when the task adds a new Gatsby page type, template-backed route, or build-time page creation rule. Implement the page creator under gatsby/create-pages/, connect the correct template under src/templates/, pass pageContext consistently, and review routing, i18n, and build-type behavior.

pingcap Bundle

Update onsite search behavior in website-docs when the task changes the search page, search box flows, Algolia client wiring, result categorization, external search fallbacks, or search-related routing. Edit the relevant Gatsby page creator, search template or components, and shared search utilities while keeping locale, category, and tracking behavior aligned.

rajnandan1 Bundle

Resize and crop images to exact platform-specific dimensions for social media, app stores, ads, and web. Supports 60+ platform presets including OG images, YouTube thumbnails, App Store screenshots, Play Store graphics, TikTok, Pinterest, Threads, Substack, Chrome Web Store, Notion covers, Instagram, Twitter, Dribbble, Bluesky, Product Hunt, LinkedIn, Facebook, and more. Uses ImageMagick for high-quality Lanczos resampling. Works on macOS, Linux, and Windows. Use this skill whenever the user wants to resize an image for a specific platform, create social media assets, generate app store screenshots, make thumbnails, create OG images, prepare images for upload, or batch-resize to multiple sizes. Also trigger when the user mentions any platform (YouTube, TikTok, Pinterest, App Store, Play Store, Substack, Threads, Chrome Web Store, Notion, etc.) in the context of image sizing, resizing, cropping, or preparation — even if they don't explicitly say "resize".

zaxbysauce Skill

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.