agent-skills / accelint-skill-manager
AGENTS.md25 starsChanged 54 days agoApache-2.0View on GitHub
Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring agent skills. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Comprehensive guide for agent skills, designed for AI agents and LLMs. Each rule includes one-line summaries here, with links to detailed examples in the references/ folder. Load reference files only when you need detailed implementation guidance for a specific rule. This structure minimizes context…
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
Use kebab-case for directories/scripts, UPPERCASE for main files, keep references one level deep.
- Distinctive: line 43
Write "Use when..." descriptions with triggering conditions only, never workflow summaries.
- Very specific: line 51
Keep SKILL.md <500 lines, metadata ~100 tokens, load resources on-demand.
- Very specific: line 55
Use ❌/✅ examples, self-contained files, avoid duplication with SKILL.md.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Manager
Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring agent skills. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows.
Abstract
Comprehensive guide for agent skills, designed for AI agents and LLMs. Each rule includes one-line summaries here, with links to detailed examples in the references/ folder. Load reference files only when you need detailed implementation guidance for a specific rule.
How to Use This Guide
- Start here: Scan the rule summaries to identify relevant optimizations
- Load references as needed: Click through to detailed examples only when implementing
- Progressive loading: Each reference file is self-contained with ❌/✅ examples
This structure minimizes context usage while providing complete implementation guidance when needed.
Quick Reference
- 1.1 File System - Directory structure and naming conventions
- 1.2 SKILL.md - Description field and keyword usage
- 1.3 AGENTS.md - Token efficiency and compression
- 1.4 Progressive Disclosure - Context optimization
- 1.5 References - Example format and organization
- 1.6 Scripts - Bash conventions and error handling
- 1.7 Assets - Templates and static resources
1. General
1.1 File System
Use kebab-case for directories/scripts, UPPERCASE for main files, keep references one level deep. View detailed examples
1.2 SKILL.md
Write "Use when..." descriptions with triggering conditions only, never workflow summaries. View detailed examples
1.3 AGENTS.md
Provide rule summaries with reference links, compress examples, eliminate redundancy. View detailed examples
1.4 Progressive Disclosure
Keep SKILL.md <500 lines, metadata ~100 tokens, load resources on-demand. View detailed examples
1.5 References
Use ❌/✅ examples, self-contained files, avoid duplication with SKILL.md. View detailed examples
1.6 Scripts
Bash preferred, use set -e, stderr for messages, stdout for JSON output. View detailed examples
1.7 Assets
Static resources, templates, data files for complex/repetitive tasks. View detailed examples
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/accelint-design-foundation/AGENTS.mdAGENTS.md
- skills/accelint-eval-architect/AGENTS.mdAGENTS.md
- skills/accelint-nextjs-best-practices/AGENTS.mdAGENTS.md
- skills/accelint-prompt-manager/AGENTS.mdAGENTS.md
- skills/accelint-react-best-practices/AGENTS.mdAGENTS.md
- skills/accelint-react-testing/AGENTS.mdAGENTS.md
- skills/accelint-readme-writer/AGENTS.mdAGENTS.md
- skills/accelint-security-best-practices/AGENTS.mdAGENTS.md
- skills/accelint-skill-manager/references/agents.mdAGENTS.md
- skills/accelint-ts-best-practices/AGENTS.mdAGENTS.md
- skills/accelint-ts-documentation/AGENTS.mdAGENTS.md
- skills/accelint-ts-performance/AGENTS.mdAGENTS.md
- skills/accelint-ts-testing/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- accelint-ac-to-playwrightSkill
- accelint-architecture-docSkill
- accelint-archive-synthesisSkill
- accelint-design-foundationSkill
- accelint-english-managerSkill
- accelint-eval-architectSkill
- accelint-nextjs-best-practicesSkill
- accelint-onboard-agentsSkill
- accelint-onboard-openspecSkill
- accelint-persona-reviewSkill
- accelint-prompt-managerSkill
- accelint-qrspi-applySkill
- accelint-qrspi-archiveSkill
- accelint-qrspi-proposeSkill
- accelint-react-best-practicesSkill
- accelint-react-testingSkill
- accelint-readme-writerSkill
- accelint-security-best-practicesSkill
- referencesSkill
- accelint-skill-managerSkill
- accelint-skill-proseSkill
- accelint-tanstack-query-best-practicesSkill
- accelint-ts-audit-allSkill
- accelint-ts-best-practicesSkill
- accelint-ts-documentationSkill
- accelint-ts-performanceSkill
- accelint-ts-testingSkill
- constraints-extractorSkill
- context-driftSkill
- epistemic-mapperSkill
- generate-docsSkill
- jargon-extractorSkill
- pr-descriptionSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

