Productivity

az9713 Skill

Project development workflow patterns including Plan-Build-Review-Fix cycle and feature development processes.

belsrc Bundle

Create structured project tickets from user intent. Use when the user wants to create a ticket, formalize a feature request, document a bug or task, or turn a conversation into a structured ticket. Handles project prefix detection, ticket numbering, and context gathering automatically.

bguivarch Skill

Write professional emails to clients

silver2dream Bundle

Principal Workflow

akoliteza Skill

Use when turning a product/design doc into a focused UI design brief, optional AI image-generation concept prompts, and implementation-ready UI direction without replacing the main idea workflow.

alexclymo Bundle

Use when the user wants to set up the task system, set up a tracker, or initialise task tracking in a project — triggers like "set up the task system here", "set up a tracker for this project", "initialise task tracking". Scaffolds a git-tracked tracker/ directory of task and decision documents plus a CLAUDE.md standing-rules block. Manages project task *documents* on disk, not Claude Code's in-session task tools (TaskCreate/TaskList) — those are scoped to one conversation and never persist; this skill is for the durable, git-tracked record instead.

anshmajumdar121 Bundle

Apply the combined rigor + delegation framework for complex tasks. Two operating modes: (1) **Rigor mode** — use the GPT-5.6 Sol 7-step loop, 10 principles, 9-stage architecture, task classification, risk register, validation layers, acceptance/rejection criteria, adversarial review, and pre-delivery checklist (default for any non-trivial task); (2) **Delegation mode** — for codebase-heavy or token-heavy work that can be split into independent parallel slices, use the Efficient Fable delegation pattern: cheap subagents do the heavy lifting, the orchestrator keeps judgment, architecture, synthesis, and final review; always apply the vetting protocol (treat subagent reports as leads, not facts). Trigger when the user says "super skill", "use the super framework", "delegate this efficiently", or any complex task where you want both auditable artifacts AND cost/speed efficiency. Do NOT trigger for trivial single-step questions, or for tasks that don't tolerate any subagent delegation (legal, medical, single-sourc

anthropics Bundle

Helps a teacher prepare to teach an existing K-12 lesson (math / ELA / science / social studies) — a prep partner that thinks through the lesson's key student task with the teacher and leaves a short teacher-only prep note. Triggers on asks to internalize, prepare for, get ready to teach, or understand a lesson, including implicit ones ("help me get ready for tomorrow's lesson"), and right after another skill built a lesson, which it can follow. Not for building or adapting a lesson, grading, rubrics, assessment feedback, or generating quizzes or student-facing material, and not for single-fact lookups a sentence would answer ("what standard is this?", "how long is this lesson?").

hu-wentao Bundle

Translate a formally published Hugo post into English, publish the English counterpart under /en/posts/, and submit its verified URL to Hacker News through the user's main Chrome session. Use when the user explicitly asks to prepare an English Hacker News translation or to translate and publish/submit a blog post to Hacker News. Never run this workflow from scheduled publishing, and never submit to Hacker News without explicit authorization.

hu-wentao Bundle

Discover newly published Hugo articles, enroll them in this repository's external-platform queue, and execute due syndication. Only discover articles published after the configured activation cutoff, resolve eligible targets from the currently authenticated Wechatsync platforms at run time, and handle X as a summary-and-canonical-link post rather than a full article. Use when Codex needs to run the recurring workflow, inspect or reorder the queue, configure exclusions, or recover blocked releases. Never use it to publish drafts or publish to the self-hosted site.

huahill Bundle

Use when a business software project needs an end-to-end domain and architecture workflow: understanding requirements, modeling domains, deciding DDD/Hexagonal/Onion/CQRS boundaries, planning implementation, or handing off to framework-specific guidance such as jfoundry. Does not require any external workflow skill.

huangyun111 Skill

Use when you want to execute the next unfinished task from ./PLAN.md in a fresh, focused session — reads only that task's files, implements, verifies with evidence, ticks the box, reports a closure summary, then stops.

huangyun111 Skill

Use when you have a goal or spec for a multi-step task and want to break it into an ordered PLAN.md task list before any coding. Sets up PLAN.md; does not implement.

huangyun111 Skill

Use when a working session is getting long or you need to pause mid-task — captures the full working state to ./HANDOFF.md so a brand-new session can resume with zero context loss.

huangyun111 Skill

Use when starting any substantial, multi-step task, or when the user mentions planning, a PLAN.md, breaking work into tasks, or short focused sessions, or when a PLAN.md/HANDOFF.md already exists in the project — establishes the plan-driven, short-session workflow and points to the plan, next, and handover skills.

ibm Bundle

Mandatory first workflow for ANY task in an unfinalized CEN Starter checkout (.template/ exists; cen.finalized is false in package.json) — including direct feature requests such as "build a todo app" or "add a page". Pause feature work, guide the user through outcome-focused configuration choices, apply the matching flavors, bootstrap, verify the running app, and finalize with explicit approval before building anything.

ihybrd Bundle

When the user provides a GDC Vault video page URL (not a VTT URL), automatically extract a VTT caption URL and then process it using the gdc-vtt-to-note workflow.

deevus Bundle

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

depot Bundle

Configures and manages Depot CI, a drop-in replacement for GitHub Actions that runs workflows entirely within Depot. Use when migrating GitHub Actions workflows to Depot CI, running `depot ci migrate`, managing Depot CI secrets and variables, running workflows with `depot ci run`, debugging Depot CI runs with `depot ci run list`, `depot ci status`, `depot ci logs`, `depot ci diagnose`, or `depot ci ssh`, inspecting test results with `depot tests` or run artifacts with `depot ci artifacts`, checking workflow compatibility, or understanding Depot CI capabilities. Also use when the user mentions .depot/ directory, depot ci commands, or asks about running GitHub Actions workflows on Depot's infrastructure without GitHub-hosted runners.

dianaprior Bundle

Shared identity, behavior rules, workflow principles, and project conventions for TabPFN tabular competition skills. Referenced by tabpfn-classify, tabpfn-regress, and tabpfn-explore — not invoked directly.

didierrlopes Skill

Judge a completed story ladder as a set - the five task.json files of one story compared side by side, verifying each level genuinely differentiates according to the ladder rules. Triggered once all five levels of a story exist and pass per-task validation.

didierrlopes Skill

Coordinate the authoring of workspace_tasks stories - spawn one task-author subagent per story (each pipelines its own per-level validators), trigger the ladder fairness check, relay flags, and stop for the user's review after each completed persona. Use when asked to author or extend the workspace_tasks suite.

dominikwozniak Skill

Use for any git operation in this project — commit, push, PR, sync, branch, stash. Reads conventions from CLAUDE.local.md; falls back to defaults. Trigger phrases: "commit", "push", "open PR", "create pull request", "sync with main", "stash my work", "new branch".

dominikwozniak Skill

Use when applying the claude-kit setup to a new project — drops CLAUDE.local.md, .claude/settings.local.json, hook scripts, and updates .gitignore. À la carte picker via AskUserQuestion: choose artifacts, pick hooks, optionally brew-install missing deps. All artifacts are local/gitignored. Trigger phrases: "bootstrap this project", "set up workflow", "apply claude-kit".

dropbox Skill

Speak a short summary aloud using Kokoro TTS. Use proactively at the end of any completed task to announce what was done in one sentence. Also use when the user explicitly asks to hear something spoken.

dzhibas Skill

This skill should be used when the user asks to "draft a team update", "write feedback", "prepare for a skip-level", "run a retro", mentions "team announcement", "async update", "SBI feedback", "retrospective", "skip-level meeting", or discusses communication with their engineering team.

eclipse-openvsx Skill

The workflow for changing webui source code — understand, implement, test, changelog, lint. Use whenever writing or modifying source (not for docs-only edits). Enforces that every behavioral change ships with tests and a changelog entry.

economicmind Skill

Orient a user to the Economic Mind plugin and connector - what it is, what data it draws on, which skills and connector tools are available, how to trigger them, and what to expect as the product grows. Use whenever the user is new to Economic Mind or asks what it is / what it can do / how to use it / how to get started - "what is Economic Mind", "getting started", "help", "what can the connector do", "what tools or skills are available", "how do I trigger X", "introduce the plugin", or names Economic Mind without a concrete analysis task yet. As part of the orientation, confirm the user is connected to the Economic Mind connector and offer one quick live example. Do NOT use this when the user already has a concrete request (a company, a peer set, a market to size) - hand off to the matching data skill instead.

edmundmiller Skill

Calendar canvas for displaying events and picking meeting times. Use when showing calendar views or when users need to select available time slots.

millionco Skill

Use when interactive elements that have visual spacing between them (chart bars/columns, list rows, nav items, segmented controls, tabs, calendar cells, icon buttons, legend chips) need hover or click to respond across the whole region with no dead zones. Triggers on "dead space", "deadspace", "gap between bars/items isn't clickable", "hover flickers between items", "have to aim precisely", "hit area too small", "highlight drops out between". Covers separating the hit area from the visual area, why gap/margin/space-between creates dead zones, and the flush-target + inner-spacing fix.

multimodal-art-projection Skill

Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.

openinfer-project Skill

Track any non-trivial task through a doc placed in the right domain directory under docs/ (models/<line>/, subsystems/<area>/, playbooks/, lessons/, etc.). Covers the full lifecycle: read docs first, write a plan, wait for approval, log execution, and capture lessons learned. Use this skill whenever the user gives a concrete task — not just Q&A or casual discussion. Even if the task seems straightforward, if it involves doing something (not just answering something), open or reuse a domain doc. Bias toward using this skill. When in doubt, use it.

phamduchuong517-hub Bundle

🎯 Task Orchestrator v4.5.0 - 任务编排器 (Durable Kanban + Swarm + 成本追踪增强版)

pinguapps Skill

Implement the work supplied alongside this skill on a new branch, commit incrementally, verify the result, push and open a GitHub PR, then use finish-pr to complete review and CI. Use for requests to take new work through the full branch-to-PR workflow.

pinguapps Bundle

Implement one Linear issue end to end in the current repository, using its optional originating spec, plan, domain context, and ADRs when available.

possibilities Bundle

Work with the human to answer, investigate, or deliver an authorized task; clarify material unresolved choices, keep progress visible, and carry implementation through verification and delivery. Use when explicitly asked for the collab workflow.