Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Deep-investigation methodology for OmniSeek. Sweep in parallel with omniseekgather, judge the signals, zoom through walled sources, structure the evidence, and close with an explicit gap ledger.
freestylefly/xiaohongshu-skills
Skill Claude CodeCodex
A tool for generating Xiaohongshu (小红书) style cover images from a topic. Xiaohongshu is a Chinese social media platform.
Skill Claude CodeCodex
Apply Spatie's Laravel and PHP coding standards for any task that creates, edits, reviews, refactors, or formats Laravel/PHP code or Blade templates; use for controllers, Eloquent models, routes, config, validation, migrations, tests, and related files to align with Laravel conventions and PSR-12.
Skill Claude CodeCodex
Use when interacting with Backlog project management service - creating issues, listing pull requests, managing projects, checking notifications, or any Backlog operation via CLI.
Skill Claude CodeCodex
AI agent harness for coordinating Claude and GPT to make and execute extremely robust plans.
Skill Claude CodeCodex
A Chinese-language traditional divination and naming toolkit covering systems such as Bazi, Ziwei Doushu, Liuyao, Qimen, Feng Shui, and Chinese name selection. It presents these as traditional-culture interpretations, not professional advice.
Skill Claude Code
Perform a security-focused code review of smart contracts, frontends, backends, and mobile apps. Use this skill for a security review, audit, vulnerability scan, or check of code for security issues, including reviewing a pull request, diff, or changed files, or asking "is this safe to merge or ship." Covers Solidity…
shixinnt/codex-image-context-runtime
Skill Claude CodeCodex
Use for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes, relative references, and compact text handoffs.
Skill Claude CodeCodex
Query Lerim's persistent project context before agent work. Use it to check prior decisions, constraints, preferences, and historical context through exact queries or synthesized answers.
filipebraida/adonisjs-starter-kit
Skill Claude Code
Build an end-to-end CRUD stack in AdonisJS + Inertia: resource route → thin controller → VineJS validator → Bouncer policy → single-purpose action → transformer variant → Inertia page. Trigger on: "add CRUD for X", "create resource", "list/create/edit/delete X", "resource endpoint".
eleven-net-cn/llm-wiki-starter
Skill Claude CodeCodex
A guide for creating a local LLM Wiki knowledge base, such as an Obsidian vault, from an official template. An LLM Wiki is a collection of notes organized to help language-model work, while Obsidian is an app for managing linked notes.
Skill Claude CodeCodex
Report or change Tera's Codex model or provider with live validation and restart verification.
Skill Codex
Create Chalk Logic concept-led chalkboard illustrations from briefs. Use for sparse wordless chalkboard explanations, non-diagram editorial chalk compositions, or prompt-only Chalk Logic recipes.
Skill Claude CodeCodex
Use when operating in a portfoliors finance workspace, reviewing portfolios, generating reports, drafting decisions, or working with INVESTMENTPOLICY.md, positions.json, portfolio/policy.toml, diary, decisions, theses, reports, or watchlist files.
liatrio-labs/spec-driven-workflow
Skill Claude Code
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
krishnakanthb13/everything-antigravity
Skill Claude CodeCodex
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
Skill Claude CodeCodex
Use when an AI agent needs to automate a real browser through Agent Browser Bridge CLI, including remote Chrome control, page extraction, clicking, typing, navigation, or screenshots.
prof-little-bear/cc-equity-research
Skill Claude CodeCodex
Create institutional-quality equity research initiation reports through a 5-task workflow. Tasks must be executed individually with verified prerequisites - (1) company research, (2) financial modeling, (3) valuation analysis, (4) chart generation, (5) final report assembly. Each task produces specific deliverables…
Skill Claude Code needs its repo
A rig is a collection of riglets that provide knowledge and tools for AI agents. Rigs and riglets are packaged as Nix flake outputs, so they can both be used inside the project defining them and by other projects depending on it.
Skill Claude CodeCodex
Universal document evaluation engine — evaluate any document against any criteria using cognitively-modelled AI agents with ontology-grounded scoring.
Skill Claude Code
Active Directory attack reference — BloodHound Cypher queries, Kerberos attack decision tree, ACE/ACL abuse, ADCS ESC1-8, and AD misconfig checklist.
Hasasasa/html-to-editable-pptx
Skill Claude CodeCodex
A converter that turns HTML slide decks into editable PowerPoint files. It keeps text as editable content when possible and uses page images for complex decoration when needed.
ForceInjection/forceinjection.github.io
Skill Claude Code
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Also use when the user says "openspec update change" or "opsx update". If the user…
Skill Claude CodeCodex
12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: