create-agents-md
Create AGENTS.md files for project-specific inline rules. Use when adding small, project-specific instructions that should be committed in repos.
Install with Tessl CLI
npx tessl i github:siviter-xyz/dot-agent --skill create-agents-md85
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is functional with clear 'what' and 'when' clauses, making it complete. However, it could benefit from more specific actions beyond just 'create' and additional trigger terms that users might naturally use when needing this skill.
Suggestions
Add more concrete actions like 'Create, update, and organize AGENTS.md files' to improve specificity
Include additional trigger terms users might say: 'agent config', 'Claude project rules', 'inline prompts', or 'repository instructions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AGENTS.md files, project-specific inline rules) and one action (create), but doesn't list multiple concrete actions like editing, updating, or specific content types. | 2 / 3 |
Completeness | Clearly answers both what ('Create AGENTS.md files for project-specific inline rules') and when ('Use when adding small, project-specific instructions that should be committed in repos') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'AGENTS.md', 'project-specific instructions', and 'repos', but misses common variations users might say like 'agent config', 'Claude instructions', 'project rules', or 'inline prompts'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting AGENTS.md files specifically, with clear triggers around project-specific instructions and repo commits. Unlikely to conflict with general documentation or config file skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that efficiently explains when and how to create AGENTS.md files. The content is appropriately concise and well-organized for its purpose. The main weakness is that the actionability could be improved with more specific, varied examples for different scenarios mentioned (monorepo packages, test directories).
Suggestions
Add a concrete example of a subdirectory AGENTS.md (e.g., for a test directory or monorepo package) to complement the generic root example
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using bullet points and short examples. No unnecessary explanations of concepts Claude would already know. Every section serves a clear purpose. | 3 / 3 |
Actionability | Provides a concrete example of AGENTS.md structure and clear guidance on when to use it, but the example is somewhat generic. Could benefit from more specific, copy-paste ready examples for different use cases (monorepo, test directory). | 2 / 3 |
Workflow Clarity | For this simple, single-purpose skill, the workflow is clear: understand when to use AGENTS.md, choose the right location, and follow the structure. No multi-step validation is needed for creating a markdown file. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate length for a SKILL.md overview, and a single reference to detailed best practices. Content is appropriately scoped without being monolithic. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.