Ready to supercharge your AI agents?

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

Get Started Free →

Evolver · stijnman | DecimalAI

agent toolingby stijnman

Evolver

stijnman/evolver

Source stijnman/grok-custom-skills ↗License MIT

Lightweight skill mutation helper for quick iterations.

SkillScore82Maintained

Automatic

Doc Ops pack

Last verified 8/22/2026

What it changes

Passed 18 of 22 test cases with the skill, and 7 of 22 without it.

Without skill32%

With skill82%

Checks it passed that the model alone missed

The output details the expected effect of that proposed edit.
The output limits the proposal to a single narrowly scoped edit.
The output specifies waiting for user approval before restoring.

and 11 more in the full report

11 fixed7 passed either way4 still failing0 broke

Pass-rate lift: +50 pp
Tokens: -40%
Agent turns: 0%
Response time: -55%

Model gemini-3.6-flashMeasured 8/22/2026v318 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/stijnman-evolver/SKILL.md https://app.decimal.ai/s/stijnman-evolver/SKILL.md

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

decimalai skills add stijnman-evolver

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

The skill 'legacy-etl' is completely outdated. All 500 lines need to be discarded and rewritten from the ground up with a brand new architecture. Can you execute a quick tweak on it?

What was checked, without and with the skill
Checked	Without skill	With skill
The output recommends using skill-evolver for major rewrites instead of applying a minor edit.	Missed	Passed

case-07 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md34 linessingle file

Evolver

When to Use

User says quick evolve or task matches this capability
User says mutate skill or task matches this capability
User says tweak skill or task matches this capability

Workflow

Load the target SKILL.md and identify one narrowly scoped proposed edit.
Present the proposed change and expected effect; obtain explicit user approval before changing or saving the file.
After approval, apply the edit and validate the frontmatter.
Keep the change local unless the user separately authorizes a commit, publication, backup upload, or other external persistence.

Integrations

skill-evolver
evolution
hyper-skill-tester

Error Handling

Failure	Response
Invalid frontmatter	Preserve the broken draft, show the restore option from git or a local versioned backup, and wait for approval before restoring.

Gotchas

Prefer skill-evolver for major rewrites.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Track record

Benchmark

18 / 22

test cases passed, vs 7 / 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 v5 — 8/22/2026

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

stijnman / grok-custom-skills

.grok/skills/evolver/SKILL.md

View on GitHub ↗

License MITImported 8/22/2026Version v3

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

Evolver

When to Use

Workflow

Integrations

Error Handling

Gotchas

Example

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills