Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 870 files from 1 769 authors, of which 62 217 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files. USE WHEN needed for generating, refactoring, templating, or scripting Gaussian job files.
Use dpdata Python Driver plugins to label systems (energies/forces/virials) via System.predict(), list available drivers, and build Driver objects (ase/deepmd/gaussian/sqm/hybrid). Use when working with dpdata Python API (not CLI) and you need driver-based energy/force prediction, plugin registration keys, or examples of using dpdata with ASE calculators or DeePMD models.
> Acts as a knowledge base providing environment checklists, directory/scratch management, and bash command templates. USE WHEN you need to guide the execution of Gaussian computational chemistry jobs (.gjf) on local or remote/HPC environments.
Minimize geometries with dpdata minimizer plugins via System.minimize(), including how minimizers relate to drivers (ASEMinimizer needs a dpdata Driver) and how to list supported minimizers (ase/sqm). Use when doing geometry optimization/minimization through dpdata Python API.
> Run Shell commands as computational jobs, on local machines or HPC clusters, through Shell, Slurm, PBS, LSF, Bohrium, etc. USE WHEN the user needs to submit batch jobs to a cluster, run commands on a remote server, execute tasks via job schedulers (Slurm, PBS, LSF), or safely run long-term/background shell commands that require state tracking and auto-recovery.
> USE WHEN requesting core chemical structural data (SMILES, formula, mass, 2D images) via IUPAC, common, or multilingual names. You MUST actively retrieve the data using this skill; DO NOT hallucinate or generate structures yourself. DO NOT USE WHEN asking for physical properties (melting point, solubility), safety/toxicity data (MSDS), or synthesis pathways.
Manage Obsidian vault operations. Handles markdown formatting, YAML frontmatter, folder organization, internal linking, and vault-specific conventions. Use when creating, updating, or organizing Obsidian notes.
Draft, organize, or update development journal entries. Use when user requests daily journal generation, work review, standup preparation, or asks "what did I work on today/this week?
Nudge the user with time-based reminders (stopping times, meetings, break suggestions). Surfaces via hook on prompt submission -- requires human interaction to fire. NOT for process monitoring or job polling -- use `sleep` in Bash instead.
(TDD) Use when implementing any feature or bugfix. Apply the Logic Gate to identify what needs tests, then use the Iron Rule for strict test-first development on logic.
Complete reference for DTG Base module utilities and helpers. DTGBase is an abstract model providing common utility methods for date/time handling, barcode generation, timezone conversion, file operations, and more.
Draws an activity flow / system architecture diagram as ONE self-contained, INTERACTIVE HTML+SVG page (2-pane app layout — left: diagram, default fit-to-view with zoom/pan; right: sidebar with explainer cards), styled like a real hand-drawn enterprise doc (Stripe/AWS-docs style — real brand logos for MongoDB/Odoo/n8n/etc. from a bundled Simple Icons library, neutral white boxes, sans-serif, no "AI neon" look), scroll-to-zoom, auto light/dark with a toggle button — clicking a flow (a legend chip, a line, or a step badge) highlights that flow with traveling dots along the arrows in their direction, a ping at the destination box, and a sidebar panel that slides out, while everything else dims; two-way arrows (OUT = solid blue / RETURN = dashed green) carry numbered step badges, colored by semantic meaning (red = auth checkpoint, purple = scheduled flow, amber = data pipeline), a small "hop" arc where two lines are forced to cross, dashed group regions, one explainer card per flow in the right sidebar. Use this skill ANY TIME the user wants to "draw a diagram", "draw a flow", "draw a system diagram", "redraw this so it's easier to follow", "interactive diagram", "two-way diagram", "request/response flow", "make a free-form HTML diagram" — even if they never say the word HTML. Especially good when both the request direction AND the response direction need to be shown, or when a templated tool (archify, mermaid) is too rigid. Do NOT use for data charts (bar/line/pie), and do not use when the user asks specifically for archify or mermaid.
> Odoo 17 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 17 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/tree/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code.
Review Odoo code for correctness, security, performance, and version-specific standards (Odoo 16, 17, 18, or 19). Use when reviewing Odoo modules, diffs, or pull requests; produce a scored report with weighted criteria.
> Odoo 16 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 16 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/tree/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code.
> Odoo 18 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 18 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/list/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code.
Trace Odoo code execution flow from entry point to end. Use proactively when planning tasks, reviewing code, or understanding how features work end-to-end. Follows all function calls, method overrides, inheritance chains, and callbacks without missing any execution path.
>- Odoo 19 development knowledge base with 18 specialized guides covering Actions (ir.actions.*, cron jobs, server actions), Controllers (HTTP routing, endpoints, auth types), Data files (XML/CSV records, shortcuts, noupdate), API Decorators (@api.depends, @api.constrains, @api.ondelete, @api.onchange, @api.model, @api.private), SQL Constraints (models.Constraint replacing _sql_constraints), Database Indexes (models.Index), Module development (manifest, wizards, reports), Field types (Char, Text, Monetary, relational fields), Manifest configuration (__manifest__.py, dependencies, asset bundles), Mixins (mail.thread, mail.activity.mixin, mail.alias.mixin, utm.mixin), ORM Model methods (search, CRUD, domain filters, recordsets, CamelCase model naming), Migration scripts (pre/post/end hooks, data migration), OWL frontend components (hooks, services, lifecycle), Performance optimization (N+1 prevention, batch ops, _read_group), QWeb Reports (PDF/HTML, paper formats, barcodes, t-out), Security/ACL (record rules, field permissions, privilege-based groups, @api.private), Testing (TransactionCase, HttpCase, mocking, query count assertions), Transactions (savepoints, UniqueViolation, serialization failures), Translations (i18n, PO files, translatable fields), XML Views (list/form/search, kanban card templates, xpath inheritance, QWeb templates). Use when writing, reviewing, or debugging any Odoo 19 Python or XML code, creating or modifying modules, fixing performance issues, or looking up Odoo 19 API patterns and best practices.
Create beautiful, professional HTML or React slide decks ready for fullscreen presentation. Use this skill when the user wants to: create a PPT/slide/presentation from an idea or outline; build a visually stunning slide deck from existing content; generate an HTML presentation that can be projected fullscreen; convert a document into a presentation. Trigger when you hear: 'create slides', 'make a PPT', 'presentation', 'slide deck', 'pitch deck', 'vibe ppt', 'make a talk', or any request to create a presentation. This skill produces a single self-contained HTML/React artifact — no backend, no installation, no dependencies.
> Guides Odoo-style commit creation following official Odoo git guidelines. create a new commit, stages files explicitly, commits via `git commit -F`, and keeps local history clean before PRs. Auto-invokes for commit-related requests in Odoo repositories and takes priority over generic commit skills.
Use for graph-first codebase navigation and repository analysis: architecture maps, dependency or call-graph tracing, symbol and repository search, change-impact review, historical diffs, CompassQL, graph refreshes, exports, MCP serving, or project artifacts. Also use when the user invokes /compass or asks about Compass.
Release Compass from the latest origin/main. Use this skill whenever a user asks to sync Compass, bump a Compass version, create or merge a release PR, build or publish macOS/Linux/Windows artifacts, write release notes, verify release downloads, or build the matching VS Code VSIX. Follow the complete gated workflow rather than treating a release as a local version edit.
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover, music, sound effects, and other hard constraints. Use when a user wants to turn an idea, story, feeling, or rough/over-specified prompt into a strong text-to-video prompt (Seedance, Sora, Kling, Veo, Runway, etc.), or asks to "rewrite", "improve", "clean up", or "vibe-ify" a video prompt. Do NOT use for long narrative films that need precise word-for-word dialogue sync, industrial shot lists meant to be executed verbatim, or functional/UI demos and step-by-step tutorials.
A work-discipline protocol that makes Opus 4.8 (or any non-frontier model) operate at Fable-5-grade quality. Core idea — output quality = model capability x work discipline: spend extra orchestration to buy single-pass quality via six levers (plan gate, small-card execution, adversarial self-check, real-product verification, context hygiene, checkpoint autonomy). Activate ONLY on an explicit request — the user names the mode ("use fable mode", "enable fable-mode", "work like Fable 5", "rigorous mode", or the Chinese "用 fable 模式"、"开 fable-mode"、"像 Fable 5 一样做"、"严谨模式") — or when the project is already armed with a `.fable/` directory (the hooks handle that). Do not auto-trigger on a task merely being large, important, or quality-sensitive, and not on generic phrases like "do it well / 最高质量 / 别偷懒"; if a task looks like it would benefit, ask the user whether to enable fable-mode instead of assuming.
Create, edit, and evaluate agent skills iteratively.
Plan mode: write markdown plan, no execution.
Review PRs: diffs, inline comments via gh or REST.
Author SKILL.md: frontmatter, structure, writing principles.
Discover available skills in the builtin library by keyword.
Onboarding conversation to generate a user profile.
Sequential 3-lens cleanup of recent code changes.
Pre-commit review: security scan, quality gates, auto-fix.
Throwaway experiments to validate an idea before build.
验证信源可信度的研究过程知识，指导 agent 在涉及事实声明时交叉核验信源
Minimal SVG diagrams as standalone HTML files.
Create distinctive, production-grade frontend interfaces.
Generate charts: select type, extract data, render image.
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
4-phase root cause debugging: understand bugs before fixing.
TDD: enforce RED-GREEN-REFACTOR, tests before code.
Search arXiv papers by keyword, author, category, or ID.
Generate docs: README, API reference, architecture, guides.
Monitor blogs and RSS/Atom feeds via blogwatcher-cli.
Analyze Excel/CSV files with DuckDB SQL via bash.
Generate PPTX presentations from slide plan + content.
Consulting-grade research reports: framework + final report.
Structured peer-review of academic papers.
Systematic multi-angle web research methodology.
Multi-round deep research on any GitHub repo via API.
Research and write professional newsletters.
Inspect codebases: LOC, languages, ratios via pygount.
Public-records OSINT: SEC, sanctions, courts, property.
Systematic literature review across multiple arXiv papers.
ML paper pipeline: experiment design to submission.
Create, triage, label, assign GitHub issues via gh or REST.
GitHub auth setup: HTTPS tokens, SSH keys, gh CLI.
GitHub PR lifecycle: branch, commit, open, CI, merge.
Execute plans task-by-task with two-stage review.
Clone, create, fork repos; manage remotes, releases.
Debug Node.js via --inspect + Chrome DevTools Protocol.
Claude Skills — questions
Answers built from the skills we actually parsed.