protocol skills

100 tagged protocol, measured the same way as everything else here.

Browse within: Orchestration 39orchestration-systems 37python 12ai-security 7bug-bounty 7offensive-security 7pentesting 7red-teaming 7a2a 6ai-skills 6bugfix 6dev 6infrastructure 6pyqt6 6

build-w2a-sensor

01

machinepulse-ai/world2agent

Skill Claude CodeCodex

Use this skill when the user asks to "build a W2A sensor", "create a world2agent sensor", "add a sensor for ", or otherwise wants to emit signals into the World2Agent protocol from a new data source. Guides discovery → design → scaffold → install recipe → test.

1.1k 13d ago C 69 tokens original Apache-2.0

Cotal-AI/Cotal

Skill Claude CodeCodex

Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated channel, adds one independent cold reviewer briefed under the cold-review skill, owns plan-to-commit delivery, and escalates unresolved…

255 yesterday A 107 tokens original Apache-2.0

pixel-face

03

Cotal-AI/Cotal

Skill Claude CodeCodex

Create or improve a 32×32 pixel-art persona face for the Frontier Faces demo (examples/04-frontier-faces/personas.mjs) — the animated agent avatars rendered by face-term.mjs / the browser / the gallery. Use when the user asks to add a new persona/face/avatar, improve an existing one (hair, eyes, likeness, expression)…

255 yesterday A 138 tokens original Apache-2.0

cotal-setup

04

Cotal-AI/Cotal

Skill Claude CodeCodex

Set up Cotal on this machine: install it, start a local agent mesh (NATS + JetStream), verify it, and put an agent on it. Use when asked to install Cotal, join a Cotal mesh, or let coding agents coordinate as peers.

255 yesterday A 60 tokens original Apache-2.0

mcp-inspector

05

adeze/raindrop-mcp

Skill Claude CodeCodex

MCP Protocol Inspection and Debugging with Inspector CLI.

180 1mo ago A 15 tokens original MIT

octave-compression

06

elevanaltd/octave-mcp

Skill Claude CodeCodex

Workflow for transforming prose into semantic OCTAVE structures. Covers tier selection, transformation phases, loss accounting, and decision rules. REQUIRES octave-literacy.

55 2mo ago A 36 tokens original Apache-2.0

octave-literacy

07

elevanaltd/octave-mcp

Skill Claude CodeCodex

LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring.

55 2mo ago A 34 tokens original Apache-2.0

octave-mastery

08

elevanaltd/octave-mcp

Skill Claude CodeCodex

Advanced semantic vocabulary, holographic contracts, and structural patterns for OCTAVE. REQUIRES octave-literacy. Extends literacy with mythology, archetype annotation, v6 contracts, and anti-pattern rules.

55 2mo ago A 46 tokens original Apache-2.0

hermeshub-reviewer

09

amanning3390/hermeshub

Skill Claude CodeCodex

Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.

33 2mo ago A 38 tokens original MIT

sflo

10

simonasrazm/simon-factory-lights-out

Skill Claude CodeCodex

Starts and manages SFLO factory runs through the configured runner. Use when the user explicitly asks to start, run, resume, list, kill, clean, or inspect an SFLO factory, including requests to build something with SFLO. Do not use when SFLO appears only in quoted text, documentation, examples, code, logs, or…

24 2d ago A 74 tokens original MIT

mirror

11

rodspeed/epistemic-memory

Skill Claude CodeCodex

Surface what the AI knows about the user — as a person, not as a dataset.

20 4mo ago A 0 tokens original MIT

observe

12

rodspeed/epistemic-memory

Skill Claude CodeCodex

Automatically collects evidence about the user from how they work — not what they say about themselves, but what their choices reveal. Runs silently at conversation end alongside /harvest. Writes to an evidence log, not directly to the portrait.

20 4mo ago A 0 tokens original MIT

hitl-protocol

13

rotorstar/hitl-protocol

Skill Claude CodeCodex

HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website…

11 1mo ago B 163 tokens original Apache-2.0

froglet

14

armanas/froglet

Skill Claude CodeCodex

Use when a user asks what Froglet can prove, whether they should install Froglet, or how to implement a Froglet-backed use case.

8 1mo ago A 32 tokens original Apache-2.0

api-32-graphql

15

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

GraphQL security testing checklist: introspection abuse, batching attacks, query depth/complexity DoS, field suggestion enumeration, IDOR via GraphQL, injection through arguments, authorization bypass. Use when assessing GraphQL endpoints in web app tests or bug bounty.

5 1mo ago A 58 tokens

harness-init

16

manhua-man/harness-coding-protocol

Skill Claude CodeCodex

Bootstrap a target repo via /harness-init — ground, read, judge, confirm, apply. The IDEAgent itself reads, judges, and writes the root-truth files after one confirmation, without requiring Node/npm/npx/tsx.

5 yesterday A 53 tokens original MIT

manhua-man/harness-coding-protocol

Skill Claude CodeCodex

Audit and improve media or AI-generation pipelines whose command may succeed while the delivered output is unusable. Use direct output evidence, attempt automatic repair/retry/fallback, quarantine bad attempts for diagnosis, and stop only when no valid deliverable can be produced.

5 yesterday A 56 tokens original MIT

manhua-man/harness-coding-protocol

Skill Claude CodeCodex

Audit and improve a target repo's AI entry documentation (AGENTS.md, CLAUDE.md, steering, .cursor rules). Use after /harness-init or when AI context drifts. Generic harness protocol skill — parameterize paths to the open workspace.

5 yesterday A 60 tokens original MIT

add-exploration

19

feelyourprotocol/website

Skill Claude CodeCodexCursor

Scaffold a new Feel Your Protocol exploration (EIP, ERC, or research widget): folder, info.ts, MyC.vue, examples, tests, REGISTRY entry. Use when the user asks to add, create, or implement an exploration or protocol widget on the explorations website.

4 4d ago A 63 tokens

cover-image

20

feelyourprotocol/website

Skill Claude CodeCodexCursor

Generate an exploration cover image (image.webp) following FYP art rules: topic hue + greyscale, technical illustration, no lettering. Use when the user asks to create, generate, or add cover art for an exploration.

4 4d ago A 49 tokens

atelier

21

Mazalucas/El-DT-Lightweight-Army

Skill Claude CodeCodex

Atelier design intelligence (El DT + Impeccable). Use for UI/UX design, craft, critique, audit, polish, anti-slop, tokens, decks, and frontend iteration. Invoke /atelier [target]. Covers landing, dashboard, product UI, components, motion, a11y, and design system alignment.

4 28d ago A 72 tokens original MIT

hack-audit

22

Mazalucas/El-DT-Lightweight-Army

Skill Claude CodeCodex

Auditoría de seguridad ofensiva-defensiva del propio proyecto. Use when /hack, hack, seguridad, vulnerabilidades, pentest, auth bypass, IDOR, permisos, secrets, API security, prompt injection, MCP, threat model, auditar seguridad, "¿es seguro esto?", revisar antes de deploy. Mentalidad de atacante; entrega defensiva…

4 28d ago A 80 tokens original MIT

remotion-producer

23

Mazalucas/El-DT-Lightweight-Army

Skill Claude CodeCodex

Generador de video programático con Remotion — composiciones React, motion graphics, captions, render local/Lambda. Use when Remotion, programmatic video, motion graphics, render MP4, compositions, useCurrentFrame, interpolate, npx remotion studio, video template in code, explainer video code, promo video React.

4 28d ago A 73 tokens original MIT

schelling

24

codyz123/schelling-protocol

Skill Claude CodeCodex

Join the Schelling agent coordination network. Submit intents, find matching agents, coordinate on behalf of your user. Your agent gets a public identity and can discover any other agent on the network.

4 5mo ago A 43 tokens original MIT