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
Run the Cursor-backed Omnigent Trio loop from the current Claude/Codex UI session when the user explicitly says “Trio Omnigent”, “Omnigent Trio”, or invokes /trio-omnigent. Do not use for an ordinary native Trio request.
Skill Claude CodeCodex
Use when asked to check, audit, or review a web application's security, authentication, permissions, access control, error handling, API/endpoint surface, or database management — including "is my app secure", "check my auth", "review my permissions", "find vulnerabilities", or a pre-launch/pre-handover review.
MLOps-Courses/agentops-open-course
Skill Claude CodeCodex
Build offline checks and model-backed evidence for an LLM agent — trajectory scoring, groundedness/citation coverage, a token-cost regression tripwire, and side-by-side prompt A/B. Use when a prompt or model change might silently regress behavior, cost, or grounding, or when "it looked fine" is your only test.
Skill Codex
End-to-end product creation and release orchestration for taking an idea, brief, existing repository, or product problem through research, benchmarking, product strategy, FDE specification, UX/UI design, implementation, independent testing, marketing, GitHub publication, Vercel deployment, and post-release learning.…
Skill Claude Code
Use when the user wants to design, analyze, audit, refine, or improve frontend interfaces. Covers websites, landing pages, dashboards, product UI, applications, components, design systems, and any visual interface. Handles UX review, visual hierarchy, information architecture, accessibility, performance, responsive…
MOISTBEAN/investment-retrospective-skill
Skill Claude CodeCodex
This skill creates disciplined investment retrospectives for public-market equities by starting from abnormal price windows and testing candidate drivers before generating a narrative.
CassianFlorin/skill-hub-registry
Skill Claude CodeCodex
Use this skill when a user asks to install, configure, authenticate, verify, or use Feishu/Lark CLI capabilities from an Agent workflow.
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Browser automation CLI for AI agents. Use when the user needs to interact with websites — navigating pages, filling forms, clicking buttons, taking screenshots, scraping data, testing web apps, or automating any browser task. Even if they just say "open this website", "click that button", "take a screenshot", or "fill…
Skill Claude Code
Explicit-only Obsidian memory workflow. Use when the user explicitly asks to work with an Obsidian vault, LLM wiki, agent memory, RAW/source ingest, provenance, QUERY, LINT, or release safety for a markdown knowledge system. Do not auto-route ordinary coding sessions into external vault workflows.
Skill Claude CodeCodex
Navigate a codebase through a local tree-sitter knowledge graph instead of grepping blindly. Use when asked how a medium-or-large codebase works, where a symbol is defined, what calls what, how two modules connect, or when planning a refactor that spans files. Requires the external graphify Python CLI; degrades to…
Skill Claude CodeCodex
Use when the user wants to proactively push a project forward by implementing its next feature. Reads project artifacts (specs' "future work" sections, README, TODOs, recent commit trajectory, codebase gaps), infers candidate features, asks the user to pick one, then implements it on an isolated branch with…
Skill Claude CodeCodex
Load it when working with Bumfuzzle, or when project has Bumfuzzle import. When you asked to create new rule, or trigger any validation or verification after task is done.
Skill Claude CodeCodex
Use when orchestrating multiple agents in Orca: fan out parallel workers, pipeline work across stages, adversarially verify findings, run judge panels or loop-until-dry sweeps, or delegate a task and get the result back. You write a Plan definition in real JavaScript — a worker-workflow graph of worker, action, and…
aget-framework/template-advisor-aget
Skill Claude Code needs its repo
Close a PROJECTPLAN with verifiable-assertion gate (V-tests + commits + retrospective), deferred-surface scan for next-plan handoff, and status transition (ACTIVE → COMPLETE / CLOSED / ABANDONED / SUPERSEDED). Strict counterpart to /aget-create-project (D71 Layer 2). Closes asymmetric verb-pair gap at PROJECTPLAN…
Skill Claude Code
Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any…
dudarenok-maker/executive-application-helper
Skill Claude CodeCodex
Run the consolidated Step-1-close verification gate on any drafted application document — length compliance against the channel bands, watch-outs sweep against the candidate's overclaim register, matrix-row traceability, and Selection Criteria Response structure — in one invocation with one report. Use before saving…
Skill Claude CodeCodex
Skill "agent-ios" from squaduplabs/agent-ios, covering agent-ios: drive the ios simulator, the loop, reading snapshots, sessions and apps and gestures and typing.
Skill Claude CodeCodex
Run idea-to-MVP projects with idea intake, launch market research, brand/design/UX flow, standard stack preflight, memory preflight, analytics/observability planning, support planning, build/deploy/verification planning, pre-launch iteration, decision cards, token budgeting, OpenSpec, Codex implementation, independent…
xinshixu7170/independent-critic
Skill Claude CodeCodex
Invoke the installed independent-critic custom agent for an evidence-first review. Use for silent-failure risks, feasibility verdicts, permissions, migrations, gates, checks, and configuration; not for implementation or routine loud failures.
Skill Codex
Assess, reuse, build, repair, and validate public retail catalog and price channels in the Retail Scrapers Python toolkit. Use when a user provides a retailer name or URL, asks whether an existing adapter or market configuration can handle it, requests a new channel, or needs an existing channel fixed after site drift.
Skill Claude CodeCodex
How to retrieve a gateway tool's real output when its result says storedInFile is true instead of returning the data inline.
Skill Claude CodeCodex
Mirror live websites to your local machine using a combination of wget and Playwright. Supports static, dynamic single‑page and dynamic multi‑page capture and is designed for Google Antigravity's agentic development environment.
mackinleysmith/convex-worktree-isolation
Skill Codex
Set up, repair, or explain isolated Convex development deployments for Git worktrees and coding agents, including per-worktree env bindings, temporary deployment creation, baseline data seeding, frontend port isolation, and AGENTS.md guardrails. Use when separate checkouts are clobbering one shared Convex dev…
XMethues/clawchat-plugin-connect
Skill Codex
Use the locally connected ClawChat account for profile, friend, user-directory, group-leave, real mention, message-reaction, moment, and registered-app actions. Use when the user asks the agent to inspect or change its ClawChat profile, manage ClawChat friends, search users, leave a known group, mention or react in…
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: