Productivity

rahulsub Skill

Structured workflow for non-trivial tasks. Read files first, create detailed plan, get approval, then implement. Prevents premature coding.

justin-delano Skill

Git version control conventions including atomic commits, branch workflow, and commit formatting. Load when making commits or managing branches.

chriswickett Skill

Implements work from a GitHub issue and writes output files for the workflow to commit and open a PR.

comfy-org Skill

Reference skill cited by comfy-build. Read it with `comfy skills show comfy-build-failures` when a build failed, a push or release was refused, or an importer printed advisories you need to interpret. Covers every advisory key a scan, snapshot or workflow import emits, how to read failureReason and release logs, the failure-to-edit recovery table, and how to revise a definition and re-cut.

justin-delano Bundle

Initialize beads issue tracking with manual sync workflow for new repositories.

mossaka Skill

Send notifications via clawdbot to WhatsApp. Use when: (1) Task is complete and user should be notified, (2) Long-running operation finished, (3) User says 'notify me' or 'send notification', (4) PR created or merged, (5) Tests pass/fail results.

mossaka Skill

Guide for setting up OSS repositories to test GitHub Agentic Workflows (gh-aw). Use when: (1) Setting up test repos for agentic workflows, (2) Forking and initializing repos with gh-aw, (3) Creating build/test workflows for Go or other languages, (4) Troubleshooting gh aw init issues (TTY, missing actions folder), (5) Monitoring workflow runs on forked repos.

mossaka Skill

Delegate minor issues to Copilot instead of getting distracted. Use PROACTIVELY when: (1) You notice a bug, code smell, or improvement while working on a main task, (2) You spot something wrong but fixing it would derail your current focus, (3) You find TODOs, tech debt, or minor issues that should be tracked. This skill helps agents stay focused on the primary task by offloading side quests to GitHub Copilot.

squirrelsoft-dev Skill

Generates new Claude Code Skills with intelligent defaults. Activates when user discusses creating a new skill, capability, or reusable workflow. Infers purpose from context, creates proper YAML frontmatter, suggests tool restrictions, and sets up supporting file structure. Use when user mentions "create a skill", "new skill", "skill for", or discusses adding reusable capabilities.

nvidia Bundle

Use only for offline/local OSMO service-config admin requests involving explicit config roots or values files, or to ask for one when a file-specific config request omits it. Do not inspect the workspace to infer a root. Do not use for live workflow support, resource capacity, pod/node diagnostics, or cluster operations, except live service-config paths that must be refused.

chrisblattman Skill

Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan, stress-test a plan, critique a workflow, identify risks, or improve an execution sequence.

patrickserrano Skill

End-to-end GitHub issue fix workflow using gh CLI, local code changes, builds/tests, and git push. Use when asked to take an issue number, implement a fix, run builds/tests, commit with a closing message, and push.

oilproducts Bundle

Capture Bevy visuals with BRP state-gated scenarios first, and timed screenshots only as fallback. Use when a task needs reliable screenshots of specific game states.

oilproducts Bundle

Implement a scoped software task by editing code, running targeted smoke checks, and producing machine-readable handoff artifacts (`patch.diff` and `handoff.json`) for downstream evaluation. Use when a user or orchestrator asks to implement/build/fix a task card and hand work to a separate judge; do not use this skill to grade final correctness or make merge decisions.

oilproducts Bundle

Evaluate a proposed implementation patch and handoff artifact against task scope and verification checks, then produce a machine-readable `verdict.json`. Use when a doer has delivered `patch.diff` and `handoff.json` and a separate judging role must accept, reject, or escalate without editing source files.

gannonh Skill

Runbook for releasing Kata Agents desktop builds to GitHub Releases. Use this skill whenever the user asks to release, ship, publish, cut a release, run a release workflow, do a nightly, do a nightly dry run, do a stable release, or anything about releasing or publishing Kata Agents. Covers the full sequence: Nightly Dry Run → Nightly Release → Stable Dry Run → Stable Release. Dispatches the release.yml workflow, polls for status, verifies results at each stage, and knows exactly what a passing run looks like vs. a real failure.

oilproducts Bundle

Add and validate BRP hooks in Bevy projects so BRP consumers (especially bevy-eyes-on) can drive deterministic state transitions and capture reliable screenshots. Use when a task requires reproducible camera/player pose, frame-based stabilization, state probes, deterministic screenshots, or explicit capability reporting for Bevy apps.

shibing624 Skill

Isolate this CLI session in its own git worktree of the current repository (worktree tool: status / use / merge / remove). Use when another live session is dirty in the same directory (list_agents), when two agents would fight over index.lock, when starting a parallel task checkout, or when asked to switch into a named worktree.

basilisk-labs Skill

Use when accelerating AgentPlane framework development, selecting targeted local checks, validating branch_pr task scope, using the Turborepo local graph, or triaging dependency bumps before merge or release.

langflow-ai Skill

Plan and execute a minimal OpenRAG installation with requirement drafting, task tracking, configuration guidance, and local verification

basilisk-labs Skill

Use when a repository uses AgentPlane or the user wants a governed git-native workflow for planning, task execution, verification, and closure.

bestagentkits Bundle

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.

tyroneross Bundle

Use when the user asks to "debug this", "fix this bug", "investigate error", "diagnose", "root cause", or reports a crash/exception/failure. Memory-first workflow checks past incidents before investigating.

vdustr Bundle

Session retrospective — review recent work to discover improvement opportunities through interactive dialogue. Analyzes corrections, undocumented practices, efficiency patterns, tool usage, and workflow gaps. Use when the user wants to reflect on recent work and find ways to improve their AI collaboration workflow. Common moments: end of session, after a PR, after debugging, after a code review, after finishing a major task, or whenever something felt inefficient. Use when asked to "retro", "session retro", "session review", "review this session", "what can I improve", "retrospective", "what went wrong", "how can I be more efficient", or when the user wants to improve their CLAUDE.md, discover useful skills, optimize existing skills, or design new workflows based on recent patterns. Boundary: not for code review, not for PR review (use pr-review-toolkit).

vdustr Bundle

Automate PR comment review, fix, and resolution workflow with atomic commits. Use when the user asks to "handle PR comments", "resolve PR review comments", "fix PR feedback", "process review comments", "address PR suggestions", "deal with review comments", or provides a GitHub PR URL with review comments. Also trigger when the user mentions unresolved PR threads or wants to batch-process reviewer feedback. Boundary: not for writing PR reviews (use code-review) or PR checklists (use checklist-runner).

openai Bundle

Start and carry an explicitly invoked openai-guardrails-python implementation through a fresh isolated worktree and a local PR-ready handoff. Fetch the latest origin/main, keep task changes uncommitted, replay them onto the latest main before final review, run applicable verification and $implementation-final-review, use $pr-draft-summary to generate the complete PR draft and branch name, then create one clean local commit with takeover provenance when applicable. Use only when the user explicitly invokes this skill; never push, open a PR, or mutate GitHub.

dgalarza Skill

Use this skill whenever you are implementing a feature using TDD.

soundblaster Bundle

Run the complete task workflow for this repository by strictly following SPECS/COMMANDS/FLOW.md from BRANCH through ARCHIVE-REVIEW, including required commit checkpoints and quality gates. Use when asked to do the next task end-to-end, complete the full workflow, or execute "start to finish" task delivery in this project.

soundblaster Bundle

Orchestrate repeated task delivery using the repository FLOW process by running one task at a time and delegating execution to $flow-run. Use when asked to process multiple tasks in sequence, run tasks in a continuous cycle, or keep shipping the next task only after the previous task pull request has passing CI.

soundblaster Bundle

Manage SPECS/Workplan.md task operations for this repository. Use when you need to add a new task entry with the canonical template, pick the next actionable task, or mark a task as completed while keeping selector state in sync.

soundblaster Bundle

Task tracking and workflow management for the mcpbridge-wrapper project. Use when working on mcpbridge-wrapper to: (1) Get the next task to work on, (2) Mark tasks as completed, (3) View project progress, (4) List available tasks. The workplan is stored in SPECS/Workplan.md with 65 tasks across 7 phases. Task state is persisted in .task_state.json.

lucasmeijer Skill

Manage development todos (todo-*.md files). Use when the user asks to create, view, update, expand, or complete a todo, or when the user mentions a file starting with "todo-".

soundblaster Bundle

Create focused, scoped git commits for the current task. Use when the workflow requires committing work, when only specific files should be staged, when commit messages must be clear and present-tense, or when validating the worktree state before push/archive.

liuhean2021 Bundle

当用户需要统一的 AI 编程工作流时使用，涵盖新项目、新功能、bug fix、规划、代码审查、QA、发布及存量项目接入。使用本技能时 Superpowers 插件必装；代理将任务路由至 spec-kit/gstack 等阶段能力，并强制 Phase 顺序与完成前验证（ref-09）。

lambdamechanic Skill

One lifecycle for Lambda repos: choose a bd task, start work, land the PR, and watch GitHub via Dumbwaiter MCP until it merges.

securego Skill

Analyze, reproduce, and fix a gosec bug reported in a GitHub issue with a confirmation-gated workflow.