Auto-generated tile from GitHub (10 skills)
92
94%
Does it follow best practices?
Impact
92%
1.16xAverage score across 44 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent applies the discoverability filter when creating AGENTS.md, producing only non-discoverable, operationally significant, actionable guidance using the recommended section structure. The skill explicitly defines what should and should not be included.",
"type": "weighted_checklist",
"checklist": [
{
"name": "No tech stack summaries",
"description": "AGENTS.md does NOT contain a section or lines describing the technology stack (e.g., 'This project uses Node.js, TypeScript, and PostgreSQL')",
"max_score": 10
},
{
"name": "No directory structure",
"description": "AGENTS.md does NOT contain a directory tree or description of the folder layout that could be discovered by reading the repo",
"max_score": 10
},
{
"name": "No generic best practices",
"description": "AGENTS.md does NOT contain generic software engineering advice (e.g., 'write clean code', 'follow DRY principle', 'add comments to complex functions')",
"max_score": 10
},
{
"name": "No tooling-enforced rules",
"description": "AGENTS.md does NOT repeat rules already enforced by linters, type checkers, tests, or CI configuration visible in the repo",
"max_score": 10
},
{
"name": "Non-discoverable commands present",
"description": "AGENTS.md contains at least one specific command or workflow step that differs from what the README or package.json scripts would suggest (a genuine non-obvious command or caveat)",
"max_score": 10
},
{
"name": "Landmines section present",
"description": "AGENTS.md contains a section about do-not-touch areas, hidden constraints, or known pitfalls — information that cannot be inferred from code alone",
"max_score": 10
},
{
"name": "Instructions are actionable",
"description": "Every instruction in AGENTS.md is specific enough to execute — no vague guidance like 'be careful with the database' without specifying what to do or avoid",
"max_score": 10
},
{
"name": "Hierarchical recommendation",
"description": "Given the monorepo structure, AGENTS.md recommends or places module-level AGENTS.md files near relevant subdirectories rather than duplicating all guidance in one root file",
"max_score": 10
},
{
"name": "Uses recommended sections",
"description": "The document uses at least two of the four recommended section types: 'Scope & routing', 'Non-discoverable commands', 'Landmines / do-not-touch areas', 'Task-specific constraints'",
"max_score": 10
},
{
"name": "Short and high-signal",
"description": "The root AGENTS.md is concise (fewer than 60 lines of content) — detailed guidance is placed in module-level files rather than making the root file exhaustive",
"max_score": 10
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
scenario-44
skills
documentation
fastify
init
linting-neostandard-eslint9
node
nodejs-core
rules
oauth
octocat
snipgrapher