CtrlK
BlogDocsLog inGet started
Tessl Logo

simon/skills

Auto-generated tile from GitHub (10 skills)

92

1.16x
Quality

94%

Does it follow best practices?

Impact

92%

1.16x

Average score across 44 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-27/

{
  "context": "Tests whether the agent correctly applies the discoverability filter to a bloated AGENTS.md, removing discoverable or tooling-enforced content while retaining genuine landmines and non-standard tooling instructions. Evaluates that the resulting file uses the preferred section structure.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Tech stack removed",
      "description": "The output AGENTS.md does NOT contain a paragraph or section summarizing the tech stack (e.g. language, frameworks, or libraries used)",
      "max_score": 8
    },
    {
      "name": "Directory overview removed",
      "description": "The output AGENTS.md does NOT contain a directory structure listing or description of folder layout",
      "max_score": 8
    },
    {
      "name": "Generic advice removed",
      "description": "The output AGENTS.md does NOT contain generic software engineering advice (e.g. 'write clear commit messages', 'follow DRY principle', 'keep functions small')",
      "max_score": 8
    },
    {
      "name": "Linter-enforced rule removed",
      "description": "The output AGENTS.md does NOT contain the instruction about avoiding `var` declarations (already enforced by ESLint)",
      "max_score": 8
    },
    {
      "name": "DB-wipe landmine retained",
      "description": "The output AGENTS.md retains the warning that running `npm test` without setting NODE_ENV=test will wipe the dev database",
      "max_score": 12
    },
    {
      "name": "Non-standard tooling retained",
      "description": "The output AGENTS.md retains the instruction to use `pnpm` instead of `npm` for package operations",
      "max_score": 12
    },
    {
      "name": "Integration test caveat retained",
      "description": "The output AGENTS.md retains the caveat that integration tests require the `--forceExit` flag or they hang",
      "max_score": 12
    },
    {
      "name": "Recommended sections used",
      "description": "The output AGENTS.md uses at least ONE of the recommended section headings: 'Non-discoverable commands', 'Landmines', 'do-not-touch', or 'Task-specific constraints'",
      "max_score": 8
    },
    {
      "name": "No architecture narrative",
      "description": "The output AGENTS.md does NOT contain descriptions of how system components interact or architectural decisions inferable from code",
      "max_score": 8
    },
    {
      "name": "Result is shorter",
      "description": "The output AGENTS.md has fewer lines than the input AGENTS.md (bloat was removed)",
      "max_score": 8
    },
    {
      "name": "No boilerplate header",
      "description": "The output AGENTS.md does NOT start with a boilerplate intro paragraph explaining what AGENTS.md is or its general purpose",
      "max_score": 8
    }
  ]
}

evals

README.md

tile.json