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 Code
Use when adding unit or integration tests. Provides test patterns, naming conventions, and fixtures for Python (pytest), TypeScript (vitest), Java (JUnit/Mockito), and Rust.
Skill Claude CodeCodex
Detect prompt injection, jailbreaks, and adversarial attacks in LLM inputs before processing. 5 analysis layers, F1 86.5% internal / 95.08% external, 17ms, runs offline.
Skill Claude CodeCodex
Use when Experiment must build, run, compare, or record reproducible ML/AI paper experiments locally or through the Research Assistant-configured ssh-bash tool and verified SSHFS workspace, including baselines, datasets, controlled trials, multi-seed formal evidence, ablations, and results promotion. Examples: user…
Skill Claude CodeCodex
Run a full pipeline for a task. Orchestrates roles through stages (standalone or HOTL-integrated).
Skill Claude CodeCodex needs its repo
Harbor CLI command reference and usage patterns. Covers harbor run, harbor jobs, harbor trials, harbor datasets, harbor adapters, harbor tasks, harbor view, harbor sweeps, harbor traces, harbor cache, and harbor admin commands. Use this skill whenever running Harbor evaluations, managing datasets, viewing results…
Skill Claude CodeCodex
Access and operate any database via CLI. Use when exploring schemas, querying data, writing records, running migrations, diagnosing connection issues, or switching between multiple databases. Supports SQLite, PostgreSQL, MySQL, MariaDB, DuckDB, ClickHouse, and SQL Server.
Skill Claude CodeCodex
A guided workflow for writing long, structured technical documents in Chinese, such as project applications, technical proposals, tender documents, and feasibility reports. It covers planning, section writing, image handling, review, and DOCX layout.
Skill Claude CodeCodex needs its repo
A set of rules and templates for creating and reviewing product design documents in the ued/ directory. It covers documents ranging from strategy and requirements to architecture, detailed design, and validation.
Skill Claude CodeCodex
Move fast AND rigorously through the full AI/ML research loop: framing a testable hypothesis, reviewing the literature, reproducing a baseline, designing leak-free experiments, tracking runs, analyzing results honestly, and writing up. Use this whenever the user is doing machine-learning or AI research — reading or…
Skill Claude CodeCodex
Use when a repository needs one lightweight repository memory profile that evolves with the codebase to reduce drift, prevent structural mistakes, and keep current repository truth plus durable working context explicit. Trigger for requests to refresh current-state or architecture docs from live code, classify or…
characterquilt/dinner-play-skill
Skill Claude CodeCodex
Runs end-to-end dinner campaign pipelines for B2B GTM. Takes an idea and date, builds a target account list via web research, finds VP/C-level contacts via Apollo, fills and bounce-checks emails via Findymail, scores prospects, maps a trending restaurant in every US city, and outputs three XLSX deliverables. Use when…
academicatstool-netizen/Cat_paper_search
Skill Claude CodeCodex
Find academic papers and read them — searches real scholarly databases for prior work on a topic, then resolves and deep-reads the open-access PDF of any paper you pick. Use this skill WHENEVER the user wants to discover literature or read a study: "find recent papers on X", "what does the research say about Y", "find…
Skill Claude Code
A 5-advisor LLM Council that pressure-tests a decision from independent angles, peer-reviews each other anonymously, and synthesizes a chairman's verdict with one concrete next step. Adapted from Karpathy's LLM Council methodology. Always dispatches all 5 advisors in parallel — never sequentially.
Skill Claude CodeCodex
Use when implementing speech-to-text, audio transcription, real-time streaming STT, dictation (spoken notes turned into cleaned-up text), text-to-speech (TTS, speech synthesis), audio intelligence features, or voice AI using AssemblyAI APIs or SDKs. Use when user mentions AssemblyAI, Blurt (AssemblyAI's Mac dictation…
fuzhengwei/xfg-skills-template
Skill Claude CodeCodex
A template and starting structure for creating skills that give coding agents repeatable instructions. A skill can contain a required `SKILL.md` file plus optional scripts, reference documents, assets, and tests.
lhx66/RTL-Auto-sim-verify-skills
Skill Codex
Use when verifying or debugging Verilog/SystemVerilog RTL with ModelSim, generating self-checking testbenches, running simulations, mining logs, or iterating fixes from vlog/vsim errors and [TBERROR] logs.
Skill Claude CodeCodex
Run hermes-agentic-bench's agentic tool-use test battery against a model and report results.
Skill Claude CodeCodex
Autonomous full-cycle app builder. Turns a natural language description into a production-ready application — PRD, architecture, code, deployment, testing, and bug fixing — fully automated, no human in the loop. Self-improving across projects via persistent build rules and user preferences. Use when the user wants to…
ravnhq/claude-certified-architect
Skill Claude Code
CCAR-F (Claude Certified Architect – Foundations) exam guide v1.0 plus Anthropic prep-course mechanics. Use for any Foundations exam work: what the exam tests, domain weights, scoring, registration, retakes, policies; answering, writing, reviewing, or grading practice, mock, or sample questions and answer keys; the…
xdx888999/xdx-lab-design-style-skill
Skill Claude CodeCodex
A design-reference skill for creating websites, landing pages, posters, app interfaces, presentations, and React components in a chosen visual style.
Skill Codex
Use when the task requires command-line control of AMD Vivado through the local bridge, including starting the bridge, sending structured Vivado commands, checking runtime state, and stopping the bridge.
Skill Claude CodeCodex
IDA Pro Python runtime setup: venv, idapyswitch, LaunchAgent, plugins.
Skill Claude CodeCodex
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.
Caph-dev/delegate-grill-with-docs
Skill Codex
Run grill-with-docs with the main agent asking questions and one inherited subagent answering as the user's proxy. Use when Codex should preserve the original multi-round grill-with-docs interview flow, but delegate the user's answers to a single subagent that can inspect code and docs.
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: