Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Autonomous Agent Readiness Assessment · majiayu000 | DecimalAI

agent toolingby majiayu000

Autonomous Agent Readiness Assessment

majiayu000/autonomous-agent-readiness

Source majiayu000/claude-skill-registry ↗License MIT

Assess a codebase's readiness for autonomous agent development and provide tailored recommendations.

SkillScore95Maintained

Automatic

AI Engineer pack

Last verified 8/18/2026

What it changes

Passed 21 of 22 test cases with the skill, and 17 of 22 without it.

Without skill77%

With skill95%

Checks it passed that the model alone missed

The maximum total readiness score is 36 points.
The framework evaluates exactly 12 key dimensions.
Individual dimensions are scored on a scale from 0 to 3.

and 9 more in the full report

5 fixed16 passed either way0 still failing1 broke

Pass-rate lift: +18 pp
Tokens: +42%
Agent turns: 0%
Response time: -12%

Model gemini-3.6-flashMeasured 8/18/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-autonomous-agent-readiness/SKILL.md https://app.decimal.ai/s/majiayu000-autonomous-agent-readiness/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-autonomous-agent-readiness, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-autonomous-agent-readiness/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-autonomous-agent-readiness

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-autonomous-agent-readiness/SKILL.md https://app.decimal.ai/s/majiayu000-autonomous-agent-readiness/SKILL.md

Raw file: /s/majiayu000-autonomous-agent-readiness/SKILL.md ↗ · machine-readable summary at /s/majiayu000-autonomous-agent-readiness.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

How many total evaluation dimensions are evaluated in the readiness framework, and what is the maximum achievable raw score?

What was checked, without and with the skill
Checked	Without skill	With skill
The framework evaluates exactly 12 key dimensions.	Missed	Passed
The maximum total readiness score is 36 points.	Missed	Passed

case-22 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md160 linessingle file

Autonomous Agent Readiness Assessment

Evaluate a codebase against proven patterns for autonomous agent execution and provide tailored recommendations.

Core Philosophy

Most agent failures are system design failures, not model failures. An agent that requires human approval at every step or depends on a developer's laptop being open is not autonomous. Autonomy is an infrastructure decision.

Assessment Workflow

Phase 1: Discovery

Gather information about the project's current state:

Examine project structure
- Look for CI/CD configuration (.github/workflows/, Jenkinsfile, .gitlab-ci.yml)
- Check for containerization (Dockerfile, docker-compose.yml, devcontainer.json)
- Identify test infrastructure (tests/, __tests__/, test config files)
- Find environment management (.env.example, requirements.txt, package.json)
Review development workflow
- Read contributing guidelines, README, or developer docs
- Check for sandbox/isolation patterns
- Look for database setup scripts or fixtures
- Identify how dependencies are managed
Assess current automation
- Review existing CI/CD pipelines
- Check for automated testing patterns
- Look for environment provisioning scripts
- Identify cleanup/teardown procedures

Phase 2: Evaluate Against Principles

Score the project (0-3) on each dimension. See references/assessment-criteria.md for detailed rubrics.

Dimension	What to Look For
Sandbox Isolation	Ephemeral environments, container support, clean state per run
Database Independence	Local DB setup, migrations in code, no external DB dependencies

Track record

Benchmark

21 / 22

test cases passed, vs 17 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/autonomous-agent-readiness-petekp-agent-skills/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Autonomous Agent Readiness Assessment

Core Philosophy

Assessment Workflow

Phase 1: Discovery

Phase 2: Evaluate Against Principles

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills