Productivity

openvinotoolkit Skill

Standardize GitHub Actions workflows with minimal functional changes.

openxlings Skill

Use for ALL code changes — every modification to pkgs/, tests/, or scripts/ MUST go through a PR with CI verification before merging. No direct pushes to main. Covers branch creation, PR submission, CI monitoring, and merge rules.

owen-dev-6174 Skill

Use when making code changes to prevent scope creep, over-engineering, and unrelated modifications beyond what was asked. Activates on any task involving file edits to enforce strict scope boundaries, flag unnecessary extras, and ensure changes match the request — nothing more, nothing less. Prevents bloat, YAGNI violations, and unsolicited refactoring.

owen-dev-6174 Skill

Use when finishing a task, after completing edits, or when code feels cluttered with unused imports, unreferenced functions, commented-out blocks, orphaned files, or duplicate utilities. Reduces the 41% code churn rate caused by AI agents leaving obsolete artifacts behind.

paulrobello Skill

Generate complete character sprite sheets for the Claude Office Visualizer agents. Creates all animation frames (idle, walking, typing, handoff, coffee) with consistent character design across all sheets. Uses iterative approval workflow and reference-based generation for consistency.

polyipseity Skill

Step-by-step guide for adding a new managed tool to the mediapm crate. Covers spec-first, test-first workflow, provider/preset/workstep implementation, and registration in all dispatchers.

ponylang Skill

Turn a Pony Development Sync meeting summary into a fact-checked comment on the open "Last Week in Pony" issue

posit-dev Skill

Walks through the ship-day site update for a Positron patch release. Bumps versions, copies the new patch entry from next.md into release.md, resets next.md, refreshes _freeze, and opens the PR. Use when the user starts the ship-day PR for a patch (typically invoked as /patch-update). The earlier "Prepare release notes" PR that lands patch content into next.md is a separate workflow and is not part of this skill.

fergus Bundle

Use when the user wants to delegate a task to Kimi Code CLI. Triggered by phrases like 'Kimi, ...', 'Hand this to Kimi', or when the user explicitly asks to send work to Kimi. This skill manages the delegation bridge, task file creation, and result handling.

fergus Skill

Delegate a task to Kimi Code CLI. Usage: /kimi <task description>. Accepts freeform task text as an argument, or prompts if none given.

fiberplane Skill

Create and break down plans into trackable issues. Use when user asks to "create a plan", "break down feature", "design implementation", "structure this work", or pastes a Linear/GitHub/Notion URL to import.

fiberplane Skill

Implement work on issues. Use when user asks to "start working on issue", "what should I work on", "pick up task", "continue work", or "find next task".

flipt-io Skill

Review a pull request — load the team's global review guidance, fetch the diff with gh, analyze it, and return a structured verdict + findings (the workflow posts the review).

flipt-io Skill

Analyze a newly opened GitHub issue for actionability, missing information, privacy concerns, and repository label suggestions. Return structured data only; the workflow handles comments and labels.

frank890417 Skill

Task wrap-up and self-evolution. Review what happened, extract lessons, archive logs, back up with git. The closing ritual for every work session. Triggers: "wrap up", "archive", "AAR", "after action", "收官"

microsoft Bundle

Prepare weekly triage meeting summary for WinAppSDK Needs-Triage issues. Use when preparing for triage meetings, reviewing Needs-Triage issues, generating diff reports since last triage, summarizing new or updated issues, or creating action item recommendations. Triggers on requests involving triage preparation, Needs-Triage review, meeting summary, triage diff, or weekly issue analysis.

mikivujkovic Skill

DDD Playbook (ToDo training)

morphet81 Bundle

Probe skill (code review). Prefer `scrutiny probe` for script-orchestrated runs (headless agents, isolated|team spawn). Or chain Rust eval → map → pack → scan, plan-confirm, optional Task agents, probe-session-write, findings triage, post-comments. Local default; PR URL/number for PR mode.

mozilla Skill

Sync the vendored stmo Claude skill (.claude/skills/stmo/SKILL.md) with a stmo-cli change and prepare delivery to the mozilla-firefox/firefox repo via moz-phab. Use after a stmo-cli change (new command, flag, or workflow behavior) that the firefox-facing skill should reflect, or as part of preparing a stmo-cli release.

mritd Skill

Generate commit messages following the Conventional Commits 1.0.0 spec and commit using gitflow-toolkit (`git ci -F`). Use this skill whenever the user wants to commit changes — phrases like "提交", "帮我提交", "提交变更", "提交一下", "提交代码", "/commit", "commit these changes", "commit this", "create a commit", "help me commit", or any explicit request to create a git commit. Also use when the user finishes a task and asks you to commit the result. This skill auto-stages files — users do not need to stage manually.

mritd Skill

Use when the user requests a new Git worktree or an authorized task needs an isolated checkout, including debugging handoffs into a new worktree.

mukulchugh Bundle

Set up a new piece of work before writing any code — decide a conventional-commit title, cut a short branch, create an isolated git worktree from the correct base, and open a draft pull request seeded with that title. Use when starting a new task, feature, bug fix or spike, when asked to cut a branch or spin up a worktree, or when a draft PR should exist before the work does.

namos2502 Bundle

This skill should be used when a multi-step task can benefit from parallel subtask execution or cross-CLI delegation — decomposing work into independent subtasks, routing them to native subagents or CLI agents in parallel, and synthesizing their structured reports back to the user.

naxandros-pixel Skill

Builds a delivery timeline from an existing task board. Sequences work by dependency, derives a critical path, produces a Gantt or milestone view, and answers "when will this be done" with ranges, avoiding false precision. Use this skill whenever the user asks for a timeline, schedule, Gantt chart, milestone plan, release date, critical path, capacity or velocity estimate, or asks when something will be ready, including casual forms like "how long will this take" or "can we make it by the end of the month". Do not use this skill for what to work on next, what is blocked, or the order of upcoming work, since task-driven-development answers those from the board's queue. The discriminator is whether the answer needs a date, a duration, or a critical path. Pairs with task-driven-development, which produces the board this skill reads.

naxandros-pixel Bundle

Use this skill whenever the user asks to build, implement, fix, refactor, or change anything in a project that has a board in GitHub Projects, Jira, or Notion, including casual phrasings like "add a login button", "fix this bug", or "let's start on the export feature" that never mention a task, ticket, epic, or board. Use it too when the user asks what to work on next, what is blocked, what state the work is in, or in what order upcoming work should happen, since those answers come from the board's queue. Runs a board-first development cycle where every change starts from a tracked task, large work is decomposed into atomic tasks under an epic or parent, board status moves automatically (In progress on start, In review when done), work happens on a per-task branch, and merging or deploying waits for the owner's explicit go-ahead. Hand a question to delivery-planning only when answering it needs a date, a duration, or a critical path.

nchaugen Skill

Clarify behaviour through concrete example tables before or during implementation. Trigger when requirements use vague terms ("eligible customers", "valid input", "appropriate discount"), when behaviour depends on multiple conditions whose combinations aren't fully worked out, when an edge case surfaces mid-implementation, or when the user asks to work through examples of a feature. Do NOT use when the user asks to write tests, convert tests, or create a @TableTest — use the tabletest skill instead, which has its own requirements decomposition workflow and will produce executable @TableTest code directly.

tidymodels Skill

Guide for creating new Claude Code skills. Use when you need to create a new skill to package expertise or workflow into a reusable capability that Claude can automatically invoke.

tmoroney Skill

Use this skill whenever the user wants to prepare/draft a new release of AutoSubs. Trigger on phrases like "prepare for release", "make a release", "release the app", "draft a release", or any mention of publishing a new version. This skill reads commits since the last tag, writes user-facing release notes, recommends a semantic version bump, asks the user to confirm, regenerates the Resolve caption template if the macro changed, updates all version files via the bump-version script, commits, tags, creates a draft GitHub release, and triggers the Mac/Linux packaging workflow.

trapstreet Skill

Install and authorize the trapstreet CLI (tp) -- install uv, install trap-cli, run tp auth login, verify the pairing. Use when the user says "set up trapstreet", "install tp", "install the CLI", "auth failed", "tp isn't working", or trapstreet-solution-scaffold/trapstreet-task-scaffold discover tp is missing or unauthenticated.

tt-a1i Bundle

Invoke this skill when the user asks to use subagents or when a substantial, self-contained task can run independently in the background.

tuki0918 Bundle

Convert rough engineering notes, spoken requirements, architecture memos, issue comments, meeting transcripts, or bullet lists into an ADR or design document. Use when Codex should structure an ambiguous technical decision into background, problem, goals, constraints, assumptions, options, decision, rationale, risks, rollout, migration, and unresolved questions, and when the output may need to fit repository docs, issues, RFCs, or PR descriptions. Trigger on requests such as "ADRを書いて", "設計書にして", "Design Docに落として", "選択肢を整理したい", "設計の背景と判断理由をまとめたい", "口頭メモから設計文書を作りたい", or "雑なメモをADRにしたい".

typedef-ai Skill

Install or verify the ade-bench harness, the Python project that actually runs the benchmark tasks this plugin generates. Use when ade-bench isn't yet on the user's machine, when a generated task fails because the harness is missing, or when the user explicitly asks to set up ade-bench. Also invoked automatically by plan-tasks and create-task when they detect ade-bench is missing.

typedef-ai Skill

Interactively plan and generate ADE-Bench benchmark tasks from a dbt project. Explores the codebase with the user in a pair-planning loop — understanding the domain, reasoning about what makes good benchmarks, and building up a task plan incrementally. Use when you want high-quality, tailored benchmark tasks for your own dbt project.

yfge Bundle

Backend validation workflow for ai-video-studio. Use when changing FastAPI endpoints, services, repositories, models, migrations, prompts, task orchestration, or when diagnosing pytest failures. Chooses between quick, full, targeted, and diagnostic backend checks while treating AGENTS.md, ai-pic-backend/TESTING_GUIDE.md, ai-pic-backend/pytest.ini, and ai-pic-backend/tests/README.md as the source of truth.

yjl9903 Bundle

Anime Garden is an anime torrent resources aggregation platform for 動漫花園, 蜜柑计划, 萌番组, and ANi. Use when required task is searching anime resources.

yoochankim Skill

Manage an ongoing todo list in todos.md. Supports listing open tasks, marking items complete, querying by owner, and scheduled alerts for overdue or upcoming deadlines.