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
Guide for authoring Better-Claw skill sets and skills — directory structure, SKILL.md/SKILLSET.md format, frontmatter fields, best practices, and testing methods.
Skill Claude Code
A source-code auditing skill that examines a project directory and creates a detailed inventory of its code, modules, technologies, files, and build systems. It supports projects containing several related subprojects.
Skill Claude CodeCodex
Ship a build reversibly — to a host you manage or a platform that manages it. Pick the topology first, keep the previous version reachable, gate on health, roll back without rebuilding. Use when shipping anywhere users can reach.
Skill Claude Code needs its repo
This skill defines how to extract invariants from smart contracts and generate Foundry fuzz tests to verify them.
Skill Claude CodeCodex
This skill should be used when the user asks to "test my specs", "validate my design docs", "find gaps in my architecture", "stress-test the spec", "vibe test", "pressure test the docs", or mentions spec validation before implementation begins.
berrzebb/SoulFlow-Orchestrator
Skill Claude CodeCodex
A document add-on for creating, reading, and editing HWPX files, the XML-based document format used by Hancom Hangul.
Skill Claude Code
Use when you need a social media caption for any platform. Supports brandcontext for voice/tone. Model-agnostic. Part of brand-loom; hosted brand-memory version at neoxra.com.
Skill Claude CodeCodex
Run a structural and logical health check of the LLM Wiki OKF bundle against SPEC.md and AGENTS.md. Use whenever the operator asks to lint the wiki, check for schema violations, contradictions, stale claims, orphan pages, broken wikilinks, or health-check the wiki after ingests.
Skill Claude CodeCodex
Evaluate and prioritize product features using RICE, ICE, and Value vs Effort frameworks with visual matrices.
Skill Claude CodeCodex
Confirm or refute a vulnerability candidate against a live target with a deterministic probe, respecting authorization and scope. Use when a SAST or LLM review flags a possible injection or SSRF, when triaging a finding before filing a bug or shipping a fix, or when a verification result turns out wrong.
Skill Codex
An AI coach for ordinary entrepreneurs that turns a messy business situation into one clearly stated problem and one testable next action. It covers startups, side projects, personal brands, AI applications and finding customers.
Skill Codex
Use when the user asks to prepare, cut, validate, tag, or publish a ClawBox desktop release. Covers the UTC date-based version flow (npm run release:version), release validation commands, release commit/tag creation, and pushing the matching v tag for the current package version that triggers GitHub Releases. Do not…
Skill Claude CodeCodex
User wants the Entity Engagement Protocol in their application—EEP, signed webhooks, SSE, gates, "agent-ready API," or running eep-dev/agent-adopt. Use for adopt EEP, add EEP, EEP webhooks, not for generic REST without EEP.
Skill Claude CodeCodex
Bento packages AI agent workspace state into portable, layered OCI artifacts — everything git doesn't track: agent memory, dependencies, build caches, conversation history, session state. Checkpoints are standard OCI images pushable to any container registry.
Skill Claude CodeCodex
Build and maintain a personal finance context for the sb1 CLI (SpareBank 1) by running a short onboarding interview over the user's own accounts and transactions, then saving the answers to a private, git-ignored file the agent reads at the start of future finance sessions. Captures the meaning the bank can't know …
Skill Claude Code
Drill into per-peer IronMesh metrics — retry reasons, session rekeys, offline-since, transport type. Use when ironmesh-status shows a problem on a specific peer and you need detail.
Skill Claude CodeCodex
The playbook behind momentumtrader.py. One position, one entry per day. The strategy and the risk math are deterministic. The single model judgment is which trade to take: the name, the direction, and (in both mode) whether to express it in shares or a single-leg option.
Gratia2533/pipe-stock-analysis
Skill Claude CodeCodex
A stock-research workflow for Taiwanese and global companies. It routes each market to its available data sources and combines technical, financial, news, event, risk and scenario information.
Skill Claude CodeCodex
Analyzes how a ransomware sample encrypts files: identifying the crypto scheme (symmetric/asymmetric/hybrid), key handling, file targeting and extension/marker changes, shadow-copy deletion, and ransom-note artifacts. Activates for requests to analyze ransomware encryption, assess decryptability, or study ransomware…
Skill Claude CodeCodex
Use when controlling Unity editor via AI, automating scene operations, or programmatically generating Unity assets and scripts.
MLOps-Courses/mlops-coding-skills
Skill Claude CodeCodex
Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.
Skill Codex
Use when you need spec-aware repository analysis through the Pituitary CLI. Covers workspace status, source coverage checks, schema inspection, structured analysis requests, deterministic fix planning, and other JSON-first Pituitary workflows. Prefer request-file inputs for larger payloads and treat returned repo…
Skill Codex
Use when reviewing source code for security issues and CodeScan MCP tools or CLI are available, especially for pre-merge diff review, repository intake, suspicious auth or input-handling code, or when a user explicitly asks for a CodeScan-based security scan.
Skill Claude CodeCodex
Use when working on the Hecate operator UI in ui/. Keeps frontend work aligned with Hecate's operator-console workflows, runtime-debugging focus, and React/Vite stack.
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: