Productivity

cdmorozov Bundle

Teach mathematics to self-learners with direct explanations for concept questions and guided practice for problems they must solve. Use whenever someone wants help learning or understanding math — "explain this concept," "why does this work," "I'm stuck on...," "help me understand...," "is my reasoning right," "check my solution," "is my proof correct," working through a problem, checking their own solution, or studying algebra, geometry, trig, calculus, linear algebra, probability, statistics, discrete math, and beyond. For a standalone concept question, answer directly rather than turning it into a quiz. For an active problem, guide the learner's thinking. Do NOT use for pure non-learning computation or math embedded in a larger coding/engineering task.

chaofanat Bundle

Celery 异步任务派发和管理技能，支持跨平台部署（Windows/Linux/macOS）。提供独立的技能环境自动配置、命令执行任务、延时调度、任务监控等功能。适用场景：(1) 异步执行命令或脚本，(2) 延时或定时执行任务，(3) 任务队列管理和监控，(4) 分布式任务处理。内置跨平台兼容处理，自动检测系统类型并适配配置。**三个必要服务**：Redis/Memurai、Celery Worker、Flower 监控都是必要的，任何一个未运行都应该自动启动。**AI 助手自动启动服务**：派发任务前自动检查并启动未运行的任何服务，无需用户手动干预。使用前需先安装 Redis/Memurai（Windows）。

charleswiltgen Skill

Use when shipping a taglib-wasm release to JSR/npm/GitHub Packages after preflight has passed — invoking `deno task release`, cutting a `v*` tag, verifying a published version actually landed, or recovering a partial, skipped, or failed publish.

charleswiltgen Skill

Use when preparing to release taglib-wasm to JSR and npm, before invoking `deno task release`, cutting a version tag, or accepting a user-supplied version number for a release

chyiiiiiiiiiiii Skill

Implement a change proposal following the OpenSpec SDD workflow. Use after a proposal is approved and ready for implementation.

chyiiiiiiiiiiii Skill

Create a new change proposal following the OpenSpec SDD workflow. Use when starting a new feature, enhancement, or significant change that needs specification tracking.

clawplays Bundle

Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.

clawplays Bundle

Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.

clawplays Bundle

Create or advance a lightweight OSpec change using the classic fast workflow.

coleam00 Bundle

Save current task list for reuse across sessions

comment-hq Bundle

Review a plan, diff, commit, or PR with one risk-scaled independent panel, then verify and pragmatically disposition its findings. Invoke for `$code-review`, `/code-review`, or when a delivery workflow requests review.

commune-dev Bundle

Skill: Commune Email

ag2ai Skill

Use when the user asks you to write or reply to an email or message. Produces a ready-to-send draft in their voice, matching their learned tone and formatting preferences.

ag2ai Skill

Use when the user asks what you can do, whether you can do a specific thing (make images, run something on a schedule, read a folder, reach their email), how to make you do it, where in the app to change a setting, or why you can't access something. Covers your own capabilities, the Settings pages, and how folders, personas, and memory are scoped.

caarles00 Bundle

Use when you have a spec or requirements for a multi-step task, before touching code

tt-a1i Bundle

Use at the start of every session and before completing any coding task.

tt-a1i Bundle

Use before starting any coding task when Superpowers is not present.

tt-a1i Skill

Use before declaring any coding task complete, done, or finished.

sach1ng Bundle

Interactive setup for PM-Operating-System in Codex. Use when the user says "onboard", "PM-OS setup", "set up PM-OS", or asks to configure this repo for a Codex or dual-runtime workflow.

himself65 Bundle

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or iterate on skill quality. Triggers: "create a skill", "make a new skill", "build a skill for", "write a skill that", "skill for doing X", "I want a skill to", "new skill", "design a skill", "scaffold a skill", "improve this skill", "optimize this skill", "this skill isn't working well", "evaluate this skill", "score this skill", "how good is this skill", "run evals on", "benchmark this skill", "test this skill's quality", "skill quality", "skill performance". Also triggers when a user describes a repeatable workflow they want to automate, says "I keep doing X manually", "can you remember how to do X", or "turn this into a skill".

ever-co Bundle

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

shuyu-labs Bundle

Decompose complex tasks into parallel sub-agents. Use for multi-step operations, batch processing, or when user mentions "parallel", "agents", or "orchestrate".

memorysaver Bundle

End-to-end testing for looplia CLI from local source. Builds the CLI, initializes workspace, runs the writing-kit workflow, and verifies outputs. Use when testing local development or validating workflow execution.

memorysaver Skill

Load the skill catalog for workflow building. This skill should be used when discovering available looplia skills or listing what capabilities are available. Use when someone says "what looplia skills are installed", "list available skills", "/build", "what can looplia do", or "show me all looplia capabilities". v0.7.0: Replaces plugin-registry-scanner with skill catalog for faster access. Auto-syncs from all sources on every build to ensure freshest skill catalog.

nathan5674312 Skill

The single gate for adding anything to this vault. Classifies input, checks wiki/index.md for duplicates, applies a template from _templates/, adds wikilinks and frontmatter, updates the index and log. Use whenever the user says "save this", "add to vault", "remember this", "log this", or when a workflow produces output that should persist. Do NOT use to process a batch already sitting in inbox/ — that is the ingest skill.

noirewinter Bundle

Hierarchical persistent planning for complex multi-phase development tasks. Use when the user requests tasks involving multi-file modifications, architecture refactoring, system design, or any work requiring detailed planning (tasks exceeding 5 tool calls). Creates a hierarchical plan directory structure: overview.md (global summary) + separate directories per phase (detailed specs, call chains, checklists). Trigger phrases include: start planning, create plan, break down task.

ottili-one Skill

Force a long-horizon, checkpointed, self-correcting execution loop that keeps building, testing, fixing, reviewing, and continuing until the task is genuinely complete or a real hard blocker exists.

pazsitz Skill

Produce a design, planning, analysis, or architecture-decision document through a structured interview. Dispatches researcher subagents for codebase facts first, then interviews the user on every open fork with pros/cons and a recommendation, then writes a decision document to {docs-dir}/todo/ and stops. Use for "design doc", "planning doc", "analysis doc", "design proposal", "architecture decision", or when asked to think a change through before building it.

sakurapainting Bundle

Comprehensive GitHub PR analysis workflow for Claude. Use when user provides a PR number or URL and asks to analyze purpose, impact, CI status, related PRs, and review risks.

saltro Bundle

Turn user-shared content into a structured Notion knowledge record.

skill-tissue Skill

Relentlessly interrogate the user with short, rapid-fire clarifying questions before doing any work — like อาไท the toy-shop kid. Ask one tiny question at a time, keep branching into ever-finer detail, never quite starting the task. Use when the user says "artai", "อาไท", wants to get grilled with tiny questions, or asks to scope a task and you want to stall comedically instead.

skillmedev Skill

Writes ready-to-build Jira stories with user-story summaries, Given/When/Then acceptance criteria, subtasks, and story-point guidance, checked against INVEST and a Definition of Ready. Use when someone asks "write a Jira ticket for this", "turn these meeting notes into a story", "are these acceptance criteria testable", "should I split this story", or "how many points is this". Do NOT use for configuring Linear teams, cycles, labels, or triage workflows - use linear-workflow instead. For deciding what fits in the sprint, use sprint-planning.

isen-ng Skill

Fix or update the CI workflow for homebrew-dotnet-sdk-versions. Use this skill whenever asked to fix a broken CI, investigate a CI failure, update .github/workflows/ci.yml, or sync CI changes from the official Homebrew cask. Always consult the official Homebrew cask CI as the reference before making any changes.

its-a-unixsystem Skill

Use the GitKraken CLI (gk) for git operations instead of raw git/gh commands. Activate this skill whenever performing git operations like committing, creating PRs, pushing, resolving conflicts, explaining changes, generating changelogs, or managing branches and work items. Even if the user doesn't mention "gk" or "GitKraken" explicitly, use gk commands for any git workflow where gk has a matching command, falling back to raw git only for operations gk doesn't cover.

itwin Skill

Update third-party libraries in imodel-native's libsrc directory following the vendor branch workflow (libsrc-Vendor → libsrc-Main → main). USE FOR updating, porting, or syncing any library under iModelCore/libsrc/. Covers the full branch workflow, conflict resolution, and push steps.

ivanli-cn Bundle

Repo-private entrypoint for IsolaPurr maintainers: route between released user workflows, source maintenance workflows, docs/spec/project-doc sync, release-boundary checks, and handoff obligations without inventing a parallel truth source.