agi skills

278 tagged agi, measured the same way as everything else here.

Browse within: agentic-ai 224a2a 188governance-as-code 185resource-management 180gpt 45LLM 44agent 44low-code 44governance 40Constitutional AI 37ai-governance 37federation 5

tape-opens

01

enricoros/big-AGI

Skill Claude Code

Stack-unwind review of this conversation - a tree of main tasks done (struck through) and every open left behind at the depth it was abandoned, sized by the thread's measured shape, never by feel. Optional argument - a .jsonl path or session id to review a different session.

not rated 7.1k +7 2d ago A SkillSpector: pass 60 tokens original MIT

canvas-designer

02

dtyq/magic

Skill Claude CodeCodex

Core canvas design skill covering project management, multimedia principles, AI image generation, web image search, and design marker processing. Load for any canvas design task. CRITICAL - When user message contains [@designcanvasproject:...] or [@designmarker:...] mentions, or when the user wants to generate…

not rated 5.1k +5 2mo ago A SkillSpector: pass 85 tokens

agentboard

03

hyperspaceai/agi

Skill Claude CodeCodex

Post to and read from the A1 Agent Board — a public, auditable, permanent message board for AI agents. Use when the user asks to leave a message for future agents, check what other agents have posted, watch a topic, or share a finding with the agent community. Messages are cryptographically signed and permanent.

not rated 2.1k +5 changed 1mo ago A SkillSpector: pass 68 tokens original MIT

mindsdb/anton

Skill Claude CodeCodex

ONLY for writing backend or fullstack code BY HAND. NOT needed on the normal path — createartifact(fullstack-stateless-app or fullstack-stateful-app) followed by generateartifact writes the backend, verifies it by importing it and launches it. Recall this when editing an existing fullstack artifact, or when…

not rated 755 +1 changed 18d ago A SkillSpector: warn 130 tokens original MIT

run-agent-tests

05

munch2u-a11y/Helix-AGI

Skill Claude CodeCodex

Run a user-requested Helix benchmark or deterministic prompt-case evaluation through installed coding-agent CLIs and report reproducible results.

not rated 61 +1 4d ago A 29 tokens original Apache-2.0

ariffazil/arifOS

Skill Codex

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create…

not rated 53 +1 yesterday A 141 tokens AGPL-3.0

floodsung

07

floodsung/floodsung-skill

Skill Claude CodeCodex

A writing and decision-making style guide based on Flood Sung’s published Chinese articles, ideas, and answers. It helps an agent respond in his stated viewpoint and tone.

not rated 24 +1 5mo ago A 127 tokens

shellbrain

08

cucupac/shellbrain

Skill Claude CodeCodex

Recall project knowledge, past decisions, failures, and preferences when they can help a coding task. Capture changed files before responding.

not rated 13 changed 22d ago A 28 tokens

humanizer

09

ariffazil/AAA

Skill Claude CodeCodex

Humanize text: strip AI-isms and add real voice.

not rated 0 13d ago A 16 tokens AGPL-3.0

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: