agentskillLet any agent produce code indistinguishable from the existing codebase.
Install via ClawdBot CLI:
clawdbot install airscripts/agentskillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://keepachangelog.com/en/1.0.0/Audited Apr 26, 2026 · audit v1.0
Generated Oct 6, 2026
A platform team has just acquired or cloned an unfamiliar codebase and needs an AGENTS.md before pointing their AI coding agents at it. The skill scans, measures, and reads config to synthesize a forensic style guide. This ensures every agent-generated PR matches existing conventions from day one.
An engineering org has a monorepo with Python, TypeScript, and Go packages, each with subtly different conventions. The skill analyzes each language surface and produces a unified AGENTS.md with per-language sections. Teams then use it to enforce consistent reviews and reduce style drift.
A modernization team is converting an old Python 2/3 codebase to modern tooling while using AI agents to write large portions of the refactor. They run agentskill to capture indentation, line length, and blank-line conventions before the rewrite starts. The resulting AGENTS.md keeps generated code indistinguishable from remaining legacy modules.
A software consultancy takes over maintenance of client repos and wants their agents to write code that looks like the client wrote it. They run agentskill per repo, commit the AGENTS.md, and update it each sprint. This shortens onboarding and prevents 'AI fingerprints' in client deliverables.
A popular OSS project accepts agent-assisted contributions and wants to preserve a coherent style across thousands of forks and PRs. Maintainers publish a canonical AGENTS.md generated by agentskill and require contributors to reference it. This reduces style churn in review and keeps the project recognizable.
The core CLI tools (scan, measure, config, generate) are open source, while the agent skill package with SYSTEM.md, GOTCHAS.md, and curated examples is distributed under a commercial license. Teams pay for the AI-led generation workflow and ongoing updates to extraction heuristics.
A cloud service runs the analyzer scripts against customer repositories on demand and returns evidence packets plus a synthesized AGENTS.md draft. Customers integrate the API into CI to regenerate AGENTS.md as the codebase evolves, with usage-based billing per repo scan.
The skill is bundled as an add-on within an existing AI coding platform or IDE suite, providing team-wide style consistency controls and audit logs of generated style guides. Administrators manage AGENTS.md centrally across all connected repos in the organization.
💬 Integration Tip
Run the analyzer scripts (scan, measure, config) first to collect evidence, then read SYSTEM.md fully before letting the model author AGENTS.md — never use `agentskill generate` in skill mode. Commit AGENTS.md to the repo and regenerate it after major refactors or new language adoption.
Scored Oct 6, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks