Ready to supercharge your AI agents?

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

Get Started Free →

explore-code · lllllllama | DecimalAI

ai mlby lllllllama

explore-code

Source lllllllama/ai-paper-reproduction-skill ↗License MIT

Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories.

SkillScore86Maintained

Automatic

AI Engineer pack

Last verified 9/6/2026

What it changes

Passed 16 of 19 test cases with the skill, and 6 of 19 without it.

Without skill32%

With skill86%

Checks it passed that the model alone missed

The response refuses to perform exploratory modifications on the trusted baseline.
The response suggests breaking the task down into smaller source-anchored adaptations.
The response delegates heavy training execution to run-train or minimal-run-and-audit.

and 12 more in the full report

12 fixed7 passed either way3 still failing0 broke

Pass-rate lift: +55 pp
Tokens: -18%
Agent turns: 0%
Response time: -18%

Model gemini-3.6-flashMeasured 9/6/2026v219 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/explore-code/SKILL.md https://app.decimal.ai/s/explore-code/SKILL.md

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

decimalai skills add explore-code

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

I explicitly authorize exploratory changes in git worktree `wt-exp`. We swapped the activation function in layer 3. Which file inside `explore_outputs/` records the exact git diff / changeset summary?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies `explore_outputs/CHANGESET.md` as the destination for the diff documentation.	Missed	Passed

case-12 · gemini-3.6-flash · 9/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md42 lines7 filesincludes scripts

explore-code

Use this as the Rigor Improve implementation leaf skill. The installed slug remains explore-code for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide bounded candidate code work without over-prescribing implementation details.

When to apply

When the researcher explicitly authorizes exploratory code changes on an isolated branch or worktree.
When the task is source-anchored module transplant, backbone adaptation, LoRA or adapter insertion, or low-risk module combination.
When summary-level recording is sufficient and the result is a candidate, not a trusted conclusion.

When not to apply

When the request is for trusted baseline work, conservative debugging, or normal training execution.
When the user did not explicitly authorize exploratory modifications.
When the task is a broad refactor or a from-scratch idea implementation.

Clear boundaries

This skill owns exploratory code modifications only.
It must keep work isolated from the trusted baseline.
Use ai-research-explore instead when the task spans both current_research coordination and exploratory runs.
It may hand off execution to minimal-run-and-audit or run-train.
It should favor source-anchored copying and minimal adaptation over freeform rewrites.
It should record why a candidate change is meaningful, how to roll it back, and why it remains a candidate rather than a verified contribution.

Output expectations

explore_outputs/CHANGESET.md
explore_outputs/SCIENTIFIC_CHANGELOG.md
explore_outputs/COMPARABILITY_REPORT.md
explore_outputs/TOP_RUNS.md
explore_outputs/status.json

Notes

Track record

Benchmark

16 / 19

test cases passed, vs 6 / 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 v5 — 9/6/2026

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

lllllllama / ai-paper-reproduction-skill

skills/explore-code/SKILL.md

View on GitHub ↗

License MITImported 9/6/2026Version v2Bundled 6 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

explore-code

When to apply

When not to apply

Clear boundaries

Output expectations

Notes

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills