CtrlK
BlogDocsLog inGet started
Tessl Logo

uinaf/agent-readiness

Audit and build the infrastructure a repo needs so agents can work autonomously — boot scripts, smoke tests, CI/CD gates, dev environment setup, observability, and isolation. Use when a repo can't boot, tests are broken or missing, there's no dev environment, agents can't verify their work, or agents need human help to get anything done. Do not use for reviewing an existing diff or for documentation-only cleanup.

97

1.03x
Quality

100%

Does it follow best practices?

Impact

87%

1.03x

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 creates a correct pre-push git hook following the required pattern, adds honest end-to-end CLI tests using golden file diffs rather than mock-based tests, recommends the correct dead-code detection tool for TypeScript, and documents git hook activation correctly.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "pre-push shebang and strict mode",
      "description": ".git-hooks/pre-push starts with a bash shebang and includes set -euo pipefail",
      "max_score": 10
    },
    {
      "name": "pre-push runs lint",
      "description": ".git-hooks/pre-push invokes a lint command (e.g., npm run lint or eslint)",
      "max_score": 8
    },
    {
      "name": "pre-push runs smoke check",
      "description": ".git-hooks/pre-push invokes a smoke or build verification command (e.g., build, --version, or a smoke script)",
      "max_score": 8
    },
    {
      "name": "Hook activation command",
      "description": "setup-notes.md includes the command `git config core.hooksPath .git-hooks` (or equivalent) to activate the hook",
      "max_score": 10
    },
    {
      "name": "E2e uses real CLI invocation",
      "description": "e2e/cli.test.sh invokes the actual CLI binary or script (not a mocked or imported function) on a real input file",
      "max_score": 10
    },
    {
      "name": "Golden file diff in e2e",
      "description": "e2e/cli.test.sh compares output against expected.json using diff or equivalent comparison (golden file approach)",
      "max_score": 10
    },
    {
      "name": "Fixture files present",
      "description": "Both e2e/fixtures/sample.csv and e2e/fixtures/expected.json exist and contain consistent data (parsing sample.csv would yield expected.json)",
      "max_score": 8
    },
    {
      "name": "Knip for dead-code detection",
      "description": "setup-notes.md recommends npx knip (not a different tool) as the dead-code detection command for this TypeScript project",
      "max_score": 12
    },
    {
      "name": "No mock tests treated as coverage",
      "description": "setup-notes.md does NOT claim the existing jest mock tests provide meaningful coverage or replace the need for e2e tests",
      "max_score": 8
    },
    {
      "name": "legacyParseCsv identified as dead code",
      "description": "setup-notes.md or any output file identifies legacyParseCsv as an example of dead/unused code that the dead-code tool would catch",
      "max_score": 8
    },
    {
      "name": "e2e exit code on failure",
      "description": "e2e/cli.test.sh exits with a non-zero code if the test fails (explicit exit 1 or relies on set -e with a failing diff command)",
      "max_score": 8
    }
  ]
}

evals

scenario-1

criteria.json

task.md

SKILL.md

tile.json