3,823 tagged agent-framework, measured the same way as everything else here.
Browse within: ai-skills 296agent-orchestration 216Autonomous Agents 174agentic-workflow 171agentic 130ai-framework 127cfo-tools 125financial-analysis 125ai-prompts 120ai-coding 84chatbot 82openclaw 77context-engineering 71ai-operating-system 67
Skill Claude CodeCodex
Update and restart everything after a change — installed binaries, the long-running services, the mecha-graph MCP server, the benchmark binary, the factory client, and the droplet. Use when asked to "update everything", "deploy", "restart the services", after cutting a release, or whenever something running looks…
Skill Claude CodeCodex
Run a structured codebase audit — map architecture, assess health (compliance / tests / docs), perform deep analysis (security / performance / code quality), and synthesize a prioritized roadmap. Use this skill when the user says things like 'audit the codebase', 'understand this project', 'find problems', '/audit'…
Skill Claude CodeCodex
A quick intent check performed before implementation to verify that the requested work has been understood correctly.
Skill Claude CodeCodex
Create a nui ADL agent definition from the current conversation and save it to /.nui/agents/.
Skill Claude CodeCodex
Interactive project setup: copy templates, configure fleet, define compliance floor, add first specialist agent.
bestdeejay-design/agent-skills
Skill Claude CodeCodex
A method for designing presentations as audience stories, combining the message, visual style, and way the presentation is delivered. It is described in Russian and focuses on moving an audience from a problem to a clear action.
Skill Claude CodeCodex
You have access to Siftable, a shared evidence-backed work graph connecting human planning, executable agent work, projects, knowledge, relationships, calendar, code, governed actions, and verification.
Skill Claude CodeCodex
Reference for the Codex API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Codex/Anthropic in any form (Codex, Anthropic…
Skill Claude CodeCodex
A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.
Skill Claude CodeCodex
TheoKit agent/LLM integration — agents/.ts convention (AgentBuilder), the tool() builder, capabilities (advanced/DI), useAgent client hook.
Skill Claude CodeCodex
Expert guidance for building, debugging, and extending applications with AgentFlow (10xscale-agentflow). TRIGGER when: code imports from agentflow (e.g. from agentflow import, StateGraph, Agent, ToolNode, AgentState); user references agentflow.json or CLI commands (agentflow init, agentflow api, agentflow play…
Skill Claude CodeCodex
Skill "intern-os" from poktalabs/intern-os, covering internos — workstreams (claude code), what "thread" means in claude code, resolution: pwd → workstream, returns workstream absolute path on stdout (exit 0), or and operating protocol.
Skill Claude CodeCodex
Runs session-end consolidation — the hippocampal sleep-replay pass that compresses session observations into long-term memory. Handles micro-hypothesis sweep, encoding queue processing, knowledge debt sweep, tree rebalancing, experience-to-skill mining, skill health check, aspiration archive, user recap, handoff…
parijatmukherjee/openclaw-hawkins
Skill Claude CodeCodex
Communication specialist for the OpenClaw multi-agent system. Use this skill when the task involves: drafting or sending emails, posting to Discord or other chat platforms, scheduling calendar events, sending notifications, or any outbound communication on behalf of the user. Always drafts before sending and requires…
Skill Claude CodeCodex
A periodic cleanup framework for an AI memory store: a collection of saved facts used to retain knowledge between sessions. It sorts, combines, reviews, updates, and reorganizes facts in a chosen area.
Skill Claude CodeCodex
Regelmäßiger Pflegedurchlauf für ein bereits veröffentlichtes GitHub-Repository (Stufe 1, günstig und oft wiederholbar): zuerst alle Distributionsflächen des Projekts ermitteln (npm, PyPI, Registries, Marketplaces, Stores, Website) und Änderungen später dorthin spiegeln, dann Topics setzen, Privacy-Gate, Dokumente auf…
Skill Claude CodeCodex
Use when named delegation is a genuine option for current work, when preparing or reviewing a handoff, or when continuing delegated work to a verified outcome. It supplies context recovery, deliberate skill selection, necessary-only delegation, evidence requirements, and continuation discipline. Do not use for…
Skill Claude CodeCodex
Operates Harneloop harness units through adaptive intake, environment mapping, artifact-aware attempts, explicit evaluation decisions, candidates, and evidence-gated promotion. Use when creating, continuing, evaluating, or recovering context for a Harneloop harness unit.
Skill Claude CodeCodex
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
r-design-j/tri-party-framework
Skill Claude CodeCodex
A framework for collaboration between Codex, Claude, and Gemini, three different AI models.
polymind-inc/agent-framework-js
Skill Claude CodeCodex
Converts values between metric and imperial units, using the project's agreed factors.
Skill Claude CodeCodex
Orchestrate a full-project consistency audit using a parallel agent team. Spawns lane-specific auditors to cross-reference docs vs code vs tests vs infra, deduplicates findings, and writes a severity-scored audit report.
Skill Claude CodeCodex
Detect when a task is being repeated often enough to be worth automating, then propose the right automation — a PROGRAM (deterministic script) or a SKILL (reusable judgment procedure). Analyzes the current session, the memory/ record, or an observation log; classifies program-vs-skill; estimates payoff; drafts the…
Skill Claude CodeCodex
Walk captured open items one at a time, resolving each into the relevant source doc.
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: