Productivity

octivi Bundle

Plan and execute Git Trunk-Based Development workflows on a repository with main as trunk. Use whenever the user asks about branch strategy, branch naming, rebasing on main, merge conflicts during rebase, PR flow, merge strategy, safe history rewrite, or branch cleanup, even if they do not mention "trunk-based" explicitly. For commit message formatting and Conventional Commits wording, delegate to git-commits.

zli12321 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.

am-will Bundle

Only to be triggered by explicit /parallel-task-tmux commands. Dependency-aware parallel plan execution that launches each unblocked Codex worker in a live tmux pane, keeps pane output visible in real time, and shrinks the layout by closing panes as tasks complete.

jaredlander Skill

GitHub Actions Workflow Expert

myriad-dreamin Skill

For command `/tinymist-dev:release version`, prepare a tinymist release with an inspect-first workflow that reuses the repository's existing release scripts and stops before external side effects until the maintainer explicitly approves them.

numen-tech Bundle

Humanizes AI-generated text with a 5-pass rewrite workflow in English and six other languages, optional saved preferences, and optional stylometric voice matching from a writing sample. Works without Slop or Not. When Slop or Not Pro is reachable, adds on-device AI detector scoring (English only), native-language readability checks, Text Cleanup, and cleanup stats. Use when the user invokes /agentic-humanizer or asks to humanize text.

cybersys Skill

Use Orca's computer-use CLI for OS/window-level inspection and input in visible local app windows. Use when a task must read or operate a native app or an external browser window (for example, Chrome, Edge, or Safari) or an app webview. Do not use for Orca's embedded browser or page-only browser automation. Use `orca-cli` for Orca's embedded pages and a page-automation tool such as Playwright or CDP for external pages.

kinemotioninc Skill

Guides video analysis for CMJ and drop jump. Use when processing athlete videos, debugging pose detection, troubleshooting analysis failures, or running kinemotion CLI commands.

nousresearch 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.

doobidoo Skill

Email Skill

giacomogaglione Bundle

Extract Jupyter notebook cells into tested Python modules while preserving the exploration workflow. Use when converting prototyping notebooks into production code.

gitsukrit Bundle

Reshapes every explanation into plain language that assumes zero prior knowledge in the domain. Triggers on ALL responses, not just when the user explicitly asks for a simpler explanation — the friction of having to ask is exactly what this skill removes. Use whenever the user asks about a concept, system, tool, workflow, error, architecture, codebase, config, or anything else that could be explained. Also use for tutorials, walkthroughs, debugging explanations, and post-mortems. Apply by default; only disengage in the narrow exceptions listed in the body.

gmh5225 Skill

Decompile Android APK/XAPK/JAR/AAR files and extract/document HTTP APIs (Retrofit/OkHttp/URLs) with a repeatable workflow.

goldziher Skill

Release/publish the spikard Rust core crate and CLI end-to-end. Load when releasing or publishing spikard — cutting a new version, tagging, running `gh release create`, and installing the released build locally. Covers version set via Taskfile, CHANGELOG roll, the clean-tree precondition, GitHub release, local install, and artifact cleanup.

goldziher Skill

Common Task Commands

graphistry Skill

Methodical bug-driven test amplification for pygraphistry features. Use when hardening a feature area via user-workflow exploration, 5-Whys retrospectives, bug-taxonomy derivation, concrete test planning, implementation, and safety-gated validation.

harehare Skill

Tracks multi-step task progress in TODO.md instead of an in-session todo list

hestudy Bundle

This skill should be used when the user asks to "create AI short drama", "write short drama", "generate video prompts", "即梦短剧", "AI短剧", "写短剧", "生成提示词", "短剧剧本", or discusses short video drama production workflow. Provides complete workflow from planning to export for AI-generated short dramas.

hiero-ledger Skill

The CITR control loop as it lives in THIS repo — the NNN-<class>-<slug> numbering scheme, the fully-migrated Chewie call path (858/859/860/861/862, no more legacy fallback), the wire contract fields HCN parses out of a Chewie allocation response, the three disjoint namespace-cleanup crons, and the MATS/XTS/promotion surface around it. Load this before touching any numbered workflow, the Chewie call chain, `.github/chewie.yaml`, or anything that assumes what a CITR workflow does.

hiromaily Skill

Evaluate a request and recommend the appropriate workflow — GitHub issue only, GitHub issue + SDD spec, or full SDD spec — based on scope, complexity, and architectural impact.

huynhsontung Skill

Procedures and guidelines for Git operations and GitHub CLI (`gh`) commands, including branch management, commit messages, and creating pull requests or issues.

hyk260 Bundle

Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.

bear2u Bundle

Use when user wants to create a new Flutter project (Todo/Habit/Note/Expense/Custom domain) with Feature-First Architecture, Riverpod 3 Code Gen, Drift, and modern Flutter stack

lukagiorgadze Bundle

Use this skill when a user asks for non-trivial code changes — such as implementing a new feature, fixing a bug, refactoring, or any task that requires meaningful edits across one or more files. Skip it for minor changes that can be done in a few lines directly.

aliceisjustplaying Bundle

Explicit-only workflow mining across Codex, Pi, and Claude Code chats. Use only when the user invokes $workflow-from-chats or explicitly asks to learn durable preferences from those harnesses and turn them into skills, rules, or workflow docs.

openrouterteam-typescript-agent Skill

Changeset Versioning & Release Workflow

4383 Bundle

Review OpenStack patches from Gerrit with standardized analysis and inline comments. Use this skill whenever the user mentions OpenStack-specific review requests like "review this openstack ticket <number>", "review openstack patch <number>", "check openstack change <number>", or working with OpenStack projects (oslo.*, nova, neutron, etc.) and Gerrit. Also trigger for phrases like "review this gerrit change", "analyze this openstack patch", "check change <number> on gerrit", or any OpenStack code review workflow. Make sure to use this skill for OpenStack Gerrit reviews, not generic GitHub pull requests.

manbothq Skill

> Description: Fossil SCM skill for distributed version control, integrated task tracking, and streamlined project management in a single unified repository system.

mineru98 Skill

Logic optimization and image-based code tasks with Codex CLI in --yolo mode. Use when (1) optimizing code logic or algorithms, (2) processing image inputs (screenshots, diagrams, mockups) to generate or modify code, (3) refactoring business logic, (4) debugging complex logic issues, (5) code generation from visual references, or (6) any task requiring image attachment for context.

nirvanaguha Bundle

Build and maintain a unique, consistent LinkedIn voice for one or more users. Runs a framework-driven persona interview (brand archetypes + tone spectrum + hot-take exercises), then generates ready-to-publish LinkedIn posts across a 30/25/20/15/10 content mix (Personal / Work / Thought-leadership / Educational / Promotional). Handles multi-user installs — teams, agencies, or families can share one install with a persona per person. Trigger on any `/thoth` command, on phrases like "write a LinkedIn post", "draft a post for [name]", "help me sound more like myself on LinkedIn", "onboard me on Thoth", "set up my LinkedIn voice", or when the user asks for help building a personal brand / thought leadership on LinkedIn. Also trigger when the user references their own posting cadence, content calendar, or wants to regenerate a post. Use this skill instead of writing a generic LinkedIn post whenever the user has a Thoth persona on file.

parthganatra Bundle

Use for any non-trivial task with 2+ open decisions/tradeoffs OR multiple implementation steps — instead of deliberating one question at a time in chat, write a structured plan to a file and let the user review it inline in vim with `> Q:` / `> A:` blockquote markers, then revise until agreed before touching any code. Triggers on feature planning, design/architecture decisions, refactors, or multi-step work. Auto-propose it when a task hits the 2+-decisions bar; the user can opt out by saying "just answer". Do NOT use for a single simple question.

pierojf Skill

Use cuando el usuario invoque /workflow-rescue, pida recuperar o rescatar un workflow caído (session limit, TaskStop, crash), el aviso de SessionStart señale workflows posiblemente caídos, o aparezca un run muerto con artefactos huérfanos en disco. Aplica desde cualquier sesión, no solo la del run.

pierojf Bundle

Use ANTES de escribir o editar cualquier script para la tool Workflow — nuevo, resume o edición — y al planear pausar o relanzar un workflow en vuelo. También si un workflow multi-agente va a producir artefactos caros que una caída por session limit podría perder.

rainsunme Skill

Use when: developing, validating, publishing, deploying, or maintaining ToolCapsule; GitHub repo setup, Vercel deployment, npm Trusted Publishing, release tags, domain checks, Dependabot cleanup, CI failures, and launch workflow.

ranveersingh1113 Skill

Search the user's saved tool library before recommending or choosing any tool, library, service, vendor, or technique. USE THIS AGGRESSIVELY — the user rarely asks for it by name. Trigger on "what should I use for", "do I have anything saved about", "I need a tool that", "how do I approach", "any recommendations for", "is there something that does", "what's good for", "which library", "how should I build" — AND on any moment where the user is evaluating, comparing, or picking a tool/service/approach for a task, even with zero mention of saved links, notes, or a library. If the user is about to pick something, check here first. Under-triggering is the main failure mode; when in doubt, run it.

spyfighting Bundle

Rebuild scientific schematic images as editable SVG and Adobe Illustrator paths with live text, or draw new scientific diagrams from explicit content. Use for raster-to-vector reconstruction, editable paper figures, and local Illustrator drawing. Separates labels from tracing and preserves existing artwork through a shared Windows/macOS CLI. Do not use tracing to recover experimental data or apply this workflow to every uploaded image.