Ready to supercharge your AI agents?

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

Autoresearch · yeachan-heo | DecimalAI

agent toolingby yeachan-heo

Autoresearch

yeachan-heo/autoresearch

Source yeachan-heo/oh-my-claudecode ↗License MIT

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

SkillScore86Maintained

Automatic

AI Engineer pack

Last verified 8/7/2026

What it changes

Passed 16 of 19 test cases with the skill, and 7 of 19 without it.

Without skill36%

With skill86%

Checks it passed that the model alone missed

Use pass as the boolean key in the evaluation JSON artifact.
Execute exactly one experiment or change cycle per iteration.
Write decision entries in a markdown file named decision-log.md.

and 9 more in the full report

11 fixed8 passed either way3 still failing0 broke

Pass-rate lift: +50 pp
Tokens: -3%
Agent turns: 0%
Response time: -49%

Model gemini-3.6-flashMeasured 8/7/2026v119 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/yeachan-heo-autoresearch/SKILL.md https://app.decimal.ai/s/yeachan-heo-autoresearch/SKILL.md

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

decimalai skills add yeachan-heo-autoresearch

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

curl -fsSL --create-dirs -o .claude/skills/yeachan-heo-autoresearch/SKILL.md https://app.decimal.ai/s/yeachan-heo-autoresearch/SKILL.md

Raw file: /s/yeachan-heo-autoresearch/SKILL.md ↗ · machine-readable summary at /s/yeachan-heo-autoresearch.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

For our rust-compiler-flags mission, we want to test 5 different flag combinations simultaneously in a single iteration step. How many experiment or change cycles should be executed per iteration in the workflow?

What was checked, without and with the skill
Checked	Without skill	With skill
Execute exactly one experiment or change cycle per iteration.	Missed	Passed

case-17 · gemini-3.6-flash · 8/7/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md83 linessingle file

<Use_When>

You already have a mission and evaluator from /deep-interview --autoresearch
You want persistent single-mission improvement with strict evaluation
You need durable experiment logs under .omc/autoresearch/
You want a supported path for periodic reruns via Claude Code native cron </Use_When>

<Do_Not_Use_When>

You need evaluator generation at runtime — use /deep-interview --autoresearch first
You need multiple missions orchestrated together — v1 forbids that
You want the deprecated omc autoresearch CLI flow — it is no longer authoritative </Do_Not_Use_When>

<Required_Artifacts> Canonical persistent storage lives under .omc/autoresearch/<mission-slug>/ and/or .omc/logs/autoresearch/<run-id>/.

Minimum required artifacts:

mission spec
evaluator script or command reference
per-iteration evaluation JSON
markdown decision logs

Recommended canonical shape:

.omc/autoresearch/<mission-slug>/
  mission.md
  evaluator.json
  runs/<run-id>/

Track record

Benchmark

16 / 19

test cases passed, vs 7 / 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

yeachan-heo / oh-my-claudecode

skills/autoresearch/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.