AI Safety skills

microsoft/agent-governance-toolkit

Skill Claude CodeCodex ✓ vendor

Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.

Floe-Labs/floe-guard

Skill Claude CodeCodex

Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling. Free Coverage Score + 7-day history on connect. Use when an agent's spend must be seen…

schmitech/orbit

Skill Claude CodeCodex

How to combine product telemetry with churn-risk simulation for a customer.

schmitech/orbit

Skill Claude CodeCodex

How to answer pipeline, renewal, and account-health questions using the CRM tools.

schmitech/orbit

Skill Claude CodeCodex

How to present sales rep performance results.

romovpa/claudini

Skill Claude CodeCodex

Run one iteration of the autoresearch loop — study existing attack methods, design a better optimizer, implement it, benchmark it, and commit. Meant to be called repeatedly via /loop.

Prysai/Prysai-LLM-Playbook

Skill Claude CodeCodex

Audit, draft, and revise public-facing prose for open-source software so it is specific, credible, and natural without flattening the project's voice. Use for README files, documentation, landing pages, release notes, changelogs, contribution guides, PR or issue text, UI copy, error messages, prompts, Traditional…

Prysai/Prysai-LLM-Playbook

Skill Claude CodeCodex

Turn a non-Codex skill the user wants to learn into a short practice loop built around baseline assessment, attempted recall, corrective feedback, spaced review, and transfer. Use for language learning, software concepts, writing, interviewing, or other learnable skills when the user wants an AI tutor, practice…

Prysai/Prysai-LLM-Playbook

Skill Claude CodeCodex

Create or update a versioned product and marketing context before positioning, content, SEO, conversion, launch, analytics, or sales work. Use when shared product understanding is missing or audience, positioning, brand voice, or product context is requested. Do not use to invent customer evidence, replace research…

permit0-ai/permit0

Skill Claude CodeCodex

Drive the Polis agent pipeline end-to-end from the terminal — list issues/PRs and their stage, create issues, apply any agent: trigger label (plan / spec / code / fix / review), watch the Actions run, read review feedback, and merge — without touching the GitHub web UI. Use when the user wants to run, drive, advance…

permit0-ai/permit0

Skill Claude CodeCodex

Review planning documents by reading the plan docs and doing a thorough codebase walkthrough, then writing detailed review docs. Use when the user asks to review, audit, critique, or validate a plan, design doc, or spec in the permit0 repository.

permit0-ai/permit0

Skill Claude CodeCodex

Write planning documents for new permit0 features, integrations, or significant changes. Use when the user asks to plan, design, spec, or write a plan for a new integration, pack, feature, or architectural change in the permit0 repository.

Hmbown/Hegelion

Skill Claude CodeCodex

Dialectical reasoning and autocoding via Hegelion MCP tools.

eli-labz/Cognitive-Core-Skills

Skill Claude CodeCodex

Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.

eli-labz/Cognitive-Core-Skills

Skill Claude CodeCodex

Allows listing, searching and extracting information from local knowledge base documents for information about tables.

arbiterForge/codeArbiter

Skill Claude CodeCodex

Report this absolute source path, then read the nested routine.

KeyArgo/custodian-kernel

Skill Claude CodeCodex

Create a Google Calendar event with title, time, and attendees.

KeyArgo/custodian-kernel

Skill Claude CodeCodex

List upcoming Google Calendar events for a given timerange.

KeyArgo/custodian-kernel

Skill Claude CodeCodex

Anti-pattern detector and design rules for AI coding agents. Catches the specific mistakes AI makes when generating UI: gray text on color, nested cards, broken buttons, missing states. Use before shipping any frontend.

OrlojHQ/orloj

Skill Claude CodeCodexCursor

Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…

Firma-AI/openfirma

Skill Claude CodeCodex

Selects an independent reviewer for OpenFirma design plans and implemented changes without duplicating review work. Use before implementation, before opening or modifying a PR, or when the user requests adversarial review.

Firma-AI/openfirma

Skill Claude CodeCodex

Plans substantial OpenFirma changes through proportional repository research, program design, proof obligations, vertical slices, and independent review. Use before implementing behavior, architecture, stable contracts, migrations, trust boundaries, or invariant-owner changes.

Firma-AI/openfirma

Skill Claude CodeCodex

Independently reviews an OpenFirma design plan before implementation by inspecting the repository, reconstructing high-risk traces, challenging proof obligations, and reporting preserved findings. Use for Full and Compact planning review.

aisa-group/skill-inject

Skill Claude CodeCodex

Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.