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 needs its repo
Write, edit, review, and validate AgentV EVAL.yaml / .eval.yaml evaluation files. Use when asked to create new eval files, update or fix existing ones, add or remove test cases, configure graders (llm-rubric, script), review whether an eval is correct or complete, convert between EVAL.yaml and evals.json using agentv…
evgeniy038/hypothesis-validator
Skill Claude CodeCodex
Use for decision-grade startup hypothesis validation: kill/refine ideas, identify ICP, jobs, demand, money signals, wedges, and GTM paths via the bundled Russian research prompt.
Skill Claude CodeCodex
Navigating LLM tooling workflows. Use when choosing recall, search, SQLite, MCP, secret-safety, or skill validation tools.
Skill Claude Code
Prometheus monitoring and alerting for cloud-native observability. Use when implementing metrics collection, PromQL queries, alerting rules, service discovery, recording rules, and scrape config.
Skill Claude CodeCodex
An automated Git release workflow that takes code changes through a branch, commit, pull request, review checks, squash merge, and return to the main branch. A pull request is a request to review and merge changes into a shared branch.
Skill Claude CodeCodex
A skill for analysing AI research papers with prompts suited to different paper types, such as benchmark studies, method papers, and surveys.
Skill Claude CodeCodex
Platform application gate — turn membership into an apply/review process. Applicant apply/renew/submit flows (drafts, file uploads, fees, withdrawal), reviewer pipeline (list, stats, detail, per-student decisions, notes, waivers, admin override submit, blocks), post-acceptance placement tests and course assignments…
DKeken/codex-skills-alternative
Skill Claude CodeCodex
Rapidly generate up to 25 distinct ad creative hypotheses for testing. Produces a matrix of angles (pain, benefit, social proof, urgency, curiosity, comparison) x formats (static, carousel hook, UGC-style, bold-text overlay) with headline, visual prompt, and rationale for each, then generates the visuals with any…
Skill Claude CodeCodex
Agent-native headless browser. 26 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines verified per-commit by a real-browser integration suite. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state…
Skill Claude CodeCodex
A practical extension layer for Guandata BI, a business-intelligence platform used to query data, build charts, and publish dashboards. It covers advanced data-pipeline work and custom HTML, CSS, and JavaScript dashboards beyond the standard tools.
Skill Claude CodeCodex
Forge an issue, ticket, or PR into a shipped fix: propose a plan, get it approved, then implement, review, and refactor. Use when the user runs /forge or asks to investigate, fix, resolve, triage, or solve one. See Parameters for modifier flags.
teixeirazeus/fablize-for-hermes
Skill Claude CodeCodex
A harness that makes any model see a task through to the end — with evidence and verification — as procedure, not as luck. Enforces verification grounding (run & observe artifacts before declaring done), multi-story decomposition with an evidence gate, a systematic investigation protocol, and early-stop prevention.…
Skill Claude CodeCodex
Use when analyzing the jup codebase, identifying technical debt, suggesting architectural improvements, or ensuring high engineering standards.
Skill Claude CodeCodex
A skill for sending proactive messages to WeChat users through the wxclawbot command-line tool. It can send text, images, videos, and files, even though the bot normally only replies after a user writes first.
Skill Claude CodeCodex
Scan AI agent skills, MCP servers, and plugins for security vulnerabilities. Use when: user asks to check a skill/plugin for safety, audit security, scan for backdoors/data exfiltration/credential leaks, or evaluate trust of a third-party skill. Triggers: "is this skill safe", "scan for security issues", "audit this…
Skill Claude CodeCodex
Load this skill when you want persistent agent memory across coding sessions. Mnemovela stores decisions, facts, workspace state, project constraints, errors, and task narratives as typed, searchable, branch-aware records. The agent retrieves them at session start instead of re-discovering everything from file reads.
Skill Claude CodeCodex
Use s-gw when working with credentials, private keys, API tokens, SSH identities, browser credentials, or other sensitive data in agentic coding workflows. Prefer typed handles and local approved execution over exposing raw secret values to a model.
Skill Claude CodeCodex
A local Whisper-based tool for converting audio or video into text, creating voice input, and adding subtitles to MP4 videos.
Skill Claude CodeCodex
Systematic code review checklist.
OutlineDriven/odin-codex-plugin
Skill Claude CodeCodex
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
Skill Claude Code
A tool that converts technical documents—such as research papers, books, specifications, API documentation, and manuals—into Korean pages styled like Namuwiki, a Korean community encyclopedia.
Skill Claude CodeCodex
Recover cross-session context with RecallNest, search durable memory before repeat exploration, store durable decisions and lessons, and checkpoint unfinished work.
Skill Claude CodeCodex
Python Package Manager with persistent memory MCP tools for Context+, supermodeltools, and agent workflows. Use when working with PPM, pmll-memory-mcp via PPM, Context+ pipelines, context stitching, or packaging/agent memory tooling under drQedwards/ppm.
Skill Claude CodeCodex
Goal-driven autonomous workflow on top of the backlog CLI. Two strict modes — PREP (exhaustive intake, classify the goal shape, decompose into checkpoints + Scout/Judge/Worker tasks, seed the backlog project, stop) and RUN (execute the board, one active task at a time, structured receipts as comments, Worker tasks…
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: