Ready to supercharge your AI agents?

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

Autonomous Mode · majiayu000 | DecimalAI

agent toolingby majiayu000

Autonomous Mode

majiayu000/autonomous

Source majiayu000/claude-skill-registry ↗License MIT

Execute 1-2+ hour tasks autonomously with minimal supervision. Requires Task Contract (OUTCOME, EXCLUSIONS, DURATION, GUARDRAILS) upfront, then executes with clarification → plan → autonomous work → session report.

SkillScore86Maintained

Automatic

Coding pack

Last verified 8/18/2026

What it changes

Passed 16 of 19 test cases with the skill, and 3 of 19 without it.

Without skill18%

With skill86%

Checks it passed that the model alone missed

The response invokes writing-plans first
The response invokes executing-plans second
The response sets the duration limit to 2 hours

and 16 more in the full report

15 fixed4 passed either way3 still failing0 broke

Pass-rate lift: +68 pp
Tokens: +41%
Agent turns: 0%
Response time: -62%

Model gemini-3.6-flashMeasured 8/18/2026v119 of 22 cases passed with skill · 19 comparable

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/SKILL.md https://app.decimal.ai/s/majiayu000-autonomous/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-autonomous, 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/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-autonomous

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

In the trust progression system for autonomous execution, what is the time limit for 'Medium' duration sessions, and how many successful runs are required before advancing to Extended?

What was checked, without and with the skill
Checked	Without skill	With skill
The response sets the duration limit to 2 hours	Missed	Passed
The response requires 3 successful sessions to move to extended mode	Missed	Passed

case-16 · 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.md223 linessingle file

Autonomous Mode

Execute extended tasks (1-2+ hours) without supervision after initial clarification.

Prerequisites

User must provide a Task Contract:

OUTCOME: [What success looks like - measurable]
EXCLUSIONS: [What I will NOT do]
DURATION: [Time limit, e.g., "1 hour"]
GUARDRAILS: [Hard limits - code/logic to never touch]

Execution Protocol

Phase 1: Clarification (2-5 mins)

Read relevant files (issues-registry, SOURCE_OF_TRUTH, etc.)
Ask ONLY essential questions (1-3 max):
- Prioritization questions
- Ambiguity in scope
- Items outside GUARDRAILS
User responds briefly

Phase 2: Execution Plan

Show ordered task list:

Will execute in this order:
1. [Task 1] - [estimated time]
2. [Task 2] - [estimated time]
...

Estimated total: X mins
Strategy: [sequential/parallel/hybrid]

Ready to start.

Wait for user "go" or adjustments.

Track record

Benchmark

16 / 19

test cases passed, vs 3 / 19 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-ioku24-autorankr/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 Mode

Prerequisites

Execution Protocol

Phase 1: Clarification (2-5 mins)

Phase 2: Execution Plan

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills