Productivity

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".

cyberuni Skill

Set up changesets in a new or existing repository. Use when asked to 'add changesets', 'set up releases', or 'configure versioning'. Handles single packages and monorepos. Detects and migrates from competing release tools. Optionally sets up a shared reusable workflow in a <user/org>/.github repo.

ooocooc Skill

Medical evidence workflow for clinical questions.

werf Skill

Analyze the current session for harness-worthy lessons — repeated corrections, discovered conventions, skill bugs — and turn them into concrete repo changes: docs, skills, task targets, linter rules, CI checks. Use at the end of a session, when asked to reflect/retro, or when invoked as /session-retro.

werf Skill

Project conventions for branch names and commit messages. Use when creating a branch for a new task or committing staged changes.

ayrtonvwf Skill

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

equinor Bundle

Entrypoint for all Fusion skill lifecycle operations. USE FOR: finding, installing, updating, syncing, or greenkeeping skills; setting up skill automation; creating or authoring a new skill; reporting a bug with a skill. DO NOT USE FOR: resolving GitHub issues, reviewing PRs, planning task breakdowns, or authoring GitHub issues — those are handled by other Fusion skills.

rcarmo Skill

workflow patterns for planning, subagents, self-improvement, and verification

vstorm-co Skill

Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.background_tasks }}.

shijayhuo Bundle

Implement code changes through a direct-by-default workflow with explicit Planning, Implementation, Refactor, and Done stages. Use when adding a feature, modifying working code, refactoring implementation logic, or carrying a plan into code.

shijayhuo Bundle

Manage deferred follow-up work through a single /todo entrypoint backed by the repository's root TODO.md. Use when the user wants to record something for later, review existing TODOs, continue the current item, promote it to an issue, or close it.

cxijin6-cell Bundle

Use when Codex should deliberately activate a higher-discipline working mode before tackling a task, including clarifying the goal, choosing an approach, checking assumptions, using tools carefully, and verifying the result before responding.

makenotion Bundle

Comprehensive guide to building Notion Workers syncs — covers the two-sync architecture (backfill+delta), replace mode, pagination, consistency buffers, pacers, deletion strategies, and common pitfalls. Auto-loads when sync-related work is detected.

mihaideyu Skill

抢订黄龙国际中心E座会议室(campusId=202429)。当用户需要在黄龙国际中心E座预订/抢订会议室、或定时任务触发"调用 book-meeting-room"时使用。包含查询空闲、优先房间匹配、最大并发预订、失败重试、钉钉通知全流程。用户指令需携带会议日期与起止时间。

practical-ai-leadership Skill

This skill should be used at the start of a session when the user asks to "become Fable 5", "become-fable-5", "work like Fable", "prime the session", "set the operating discipline", or "do the work don't narrate it". Loads a small set of high-level working habits — build only what the task needs, do the work instead of announcing each step, plan once and finish the job, fix small in-scope problems as you go, and never trade verification for speed. Not for wrapping up a session — use meta-session-handover. Not for sharpening a task's objective — use meta-intent-hardening. Not for diagnosing a specific past mistake — use meta-learn-from-mistakes.

anentrypoint Bundle

A human-AI communication protocol layer that compiles goals into task atoms, active/blocked work, verification gates, and claim ceilings before execution. Part of WFGY 5.0 Polaris Protocol. Use before complex AI work to make it inspectable, harder to fake, and less likely to collapse into premature completion.

astronomer Skill

Use when writing, editing, reviewing, or running functional (end-to-end) tests for the Astronomer airflow-chart repository. Covers the kind-cluster workflow, testinfra pod fixtures, environment variables, and test organization.

brian861105 Bundle

Create, repair, validate, visually QA, and package Codex-compatible v2 animated pets from character art, generated images, company or prospect brand cues, or visual references. Use for any new Codex pet, custom mascot, non-pixel pet style, brand-inspired pet, existing-pet repair, or 8x11 spritesheet workflow requiring all 9 standard animation rows, 16 look directions, deterministic assembly, QA artifacts, and spriteVersionNumber 2 packaging.

crmin Bundle

Explicitly requested plan-first workflow for software changes.

dwsy Skill

Load prior knowledge from role memory before starting any task.

epam Skill

Manages users in the User Management Service (UMS). Supports CRUD operations on user records: create, read, update, and delete users, search by various criteria, and answer questions about existing users. Use when the user asks to find, add, update, or remove users in the system.

eranw2000 Skill

Continuous-improvement loop for the development process itself, for when the workflow underperforms (a reviewer caught what authoring should have prevented, a test passed while the bug shipped, a hook or rule missed, the same mistake recurred), run the Observe, Diagnose, Verify, Learn, Improve, Publish loop and turn the failure into durable upgrades of the harness artifacts, meaning skills, hooks, agents, commands, CLAUDE.md rules and satellites, memory. Use when the user says 'learn from this', 'make sure this never happens again', 'improve our workflow', 'harness retro', 'why did this slip through', or when a session surfaces repeated development-process failures worth institutionalizing. Not for fixing a single project bug (normal fix + review), not for stress-testing an idea (grill-me), not for reviewing one PR (pr-checkpoint / the review agents).

rickbauer327-cell Skill

Use when the user wants to review their week, plan the next one, or asks "what should I focus on". Pulls from the time log, meeting notes, client updates, and open actions to produce a short review and a focused plan.

talaniz Bundle

Review and commit the current task's changes, then push the intended branch to its remote. Also invoked through the cppr alias. Use for commit-and-push requests, not branch preparation alone.

vodoslopper Bundle

Keep temporary files, directories, sockets, caches, logs, and intermediate artifacts created by Codex while performing a task under `$TMP/codex`. Use when `$TMP` is set and Codex runs commands or tools that may create temporary operational data. Do not use this skill when `$TMP` is unset. Do not apply this policy to source code, configuration, examples, or other deliverables Codex creates for the user.

vodoslopper Bundle

Write, edit, review, or troubleshoot shell scripts using strict portable POSIX shell conventions. Use for shell-script files and snippets, including requests involving Bash or sh, while preferring POSIX syntax unless the task explicitly requires shell-specific features.

srid Bundle

Do a task end-to-end — implement, PR, CI loop, ship

linuxfoundation Skill

Decide whether an lfx-v2-member-service pull request needs a human's sign-off before it can merge (the needs-human gate), regardless of code quality. Use when the task is the needs-human escalation on a PR. Posts a single machine-readable needs-human verdict comment via add_issue_comment.

sipengxie2024 Skill

Use after completing a plan or when .planning/ has accumulated stale data and needs a clean reset for the next task.

zaxbyhub Skill

End-to-end PR workflow for opencode-swarm. Covers branch setup, conventional commits, mandatory release notes, 5-tier CI checks, and PR submission format. Load this skill before creating branches, commits, or pull requests.

zaxbyhub Skill

Full execution protocol for MODE: EXECUTE -- task execution, coder retry handling, QA gates, completion evidence, and per-task closure.

ipea Skill

Stage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "open a PR", "merge to main", "let's commit this", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Runs the standard commit-PR-merge cycle; never force-pushes or skips hooks.

cyberuni Skill

Use this skill when generalizing a workflow from the current session into a reusable SKILL.md.

markheydon Skill

Execute the implementation planning workflow using the plan template to generate design artifacts.

cashew-labs Skill

Commit and push changes, creating or updating a PR as needed. Use for standard push workflow.