CtrlK
BlogDocsLog inGet started
Tessl Logo

uinaf/docs

Update repo documentation and agent-facing guidance such as AGENTS.md, README.md, docs/, specs, plans, and runbooks. Use when code, skill, or infrastructure changes risk doc drift or when documentation needs cleanup or restructuring. Do not use for code review, runtime verification, or `agent-readiness` setup.

98

1.00x
Quality

100%

Does it follow best practices?

Impact

94%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-1/

{
  "context": "Tests whether the agent produces an AGENTS.md that follows the skill's structural guidance: ~100 lines, terse table-of-contents format, contains required sections (boot, test, key conventions, doc links), and strips content that should NOT be in AGENTS.md (directory listings, auto-generated tables, full architecture tours, full API docs).",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Length constraint",
      "description": "The new AGENTS.md is at most 120 lines (allowing slight tolerance around the ~100 line target)",
      "max_score": 10
    },
    {
      "name": "Boot command present",
      "description": "AGENTS.md contains the exact command to start the development server (e.g. `npm run dev` or equivalent)",
      "max_score": 10
    },
    {
      "name": "Test command present",
      "description": "AGENTS.md contains the command(s) to run tests (e.g. `npm test`)",
      "max_score": 10
    },
    {
      "name": "Links to deep docs",
      "description": "AGENTS.md contains links or pointers to at least two deeper docs files (e.g. docs/architecture.md, docs/api.md, docs/deployment.md)",
      "max_score": 10
    },
    {
      "name": "No directory listing",
      "description": "AGENTS.md does NOT contain a full directory tree or file listing (no ASCII tree with multiple nested levels)",
      "max_score": 10
    },
    {
      "name": "No auto-generated content",
      "description": "AGENTS.md does NOT contain the auto-generated file stats table or any section marked as auto-generated",
      "max_score": 10
    },
    {
      "name": "No full API docs",
      "description": "AGENTS.md does NOT include full API endpoint documentation (request/response bodies, full route listings) — at most a pointer to docs/api.md",
      "max_score": 10
    },
    {
      "name": "Deprecated script removed",
      "description": "AGENTS.md does NOT reference the deprecated `scripts/bootstrap.sh` — only `scripts/setup.sh` if referenced at all",
      "max_score": 10
    },
    {
      "name": "Key deviating conventions",
      "description": "AGENTS.md mentions at least one key convention that deviates from defaults (e.g. use custom logger instead of console.log, use AppError class, TypeScript strict mode no-any)",
      "max_score": 10
    },
    {
      "name": "Doc report produced",
      "description": "A doc-report.md file exists that lists what was removed from the old AGENTS.md and the reasoning",
      "max_score": 10
    }
  ]
}

evals

scenario-1

criteria.json

task.md

SKILL.md

tile.json