Ready to supercharge your AI agents?

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

Get Started Free →

Skill Evolution Engine · stijnman | DecimalAI

agent toolingby stijnman

Skill Evolution Engine

stijnman/skill-evolution-engine

Source stijnman/grok-custom-skills ↗License MIT

Manages skill version history and automated improvement cycles.

SkillScore83Maintained

Automatic

AI Engineer pack

Last verified 8/28/2026

What it changes

Passed 19 of 23 test cases with the skill, and 4 of 23 without it.

Without skill17%

With skill83%

Checks it passed that the model alone missed

Forbids persisting changes prior to user review.
Specifies that version backups must be maintained locally.
Demands explicit user approval before persisting changes to disk.

and 26 more in the full report

15 fixed4 passed either way4 still failing0 broke

Pass-rate lift: +65 pp
Tokens: -34%
Agent turns: 0%
Response time: -50%

Model gemini-3.6-flashMeasured 8/28/2026v319 of 23 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-skill-evolution-engine/SKILL.md https://app.decimal.ai/s/stijnman-skill-evolution-engine/SKILL.md

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

decimalai skills add stijnman-skill-evolution-engine

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

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

Raw file: /s/stijnman-skill-evolution-engine/SKILL.md ↗ · machine-readable summary at /s/stijnman-skill-evolution-engine.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

The user has explicitly approved our proposed changes to the research-assistant skill diff, and we have committed the updates. What is the mandatory immediate next step in the workflow?

What was checked, without and with the skill
Checked	Without skill	With skill
Mandates running tests post-application to compare scores against the pre-edit baseline.	Missed	Passed

case-15 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md35 linessingle file

Skill Evolution Engine

When to Use

User says evolve skills or task matches this capability
User says version skills or task matches this capability
User says skill maintenance or task matches this capability

Workflow

Snapshot the current SKILL.md to a local versioned backup and run the hyper-skill-tester baseline.
Prepare the proposed evolution as a reviewable diff with expected benefits, risks, and rollback path.
Obtain explicit user approval before applying, committing, publishing, or otherwise persisting the proposed change.
After approval, apply the change and compare scores. Present any regression and its rollback option for approval rather than rolling back automatically.

Integrations

skill-evolver
evolution
evolver
hyper-skill-tester

Error Handling

Failure	Response
Score regression	Preserve the evidence, present the latest backup and rollback diff, and wait for user approval before restoring.

Gotchas

Keep version backups locally; do not publish, delete, or restore them without explicit user approval.

Example

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

Track record

Benchmark

19 / 23

test cases passed, vs 4 / 23 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/skill-evolution-engine/SKILL.md

View on GitHub ↗

License MITImported 8/22/2026Version v3

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

Skill Evolution Engine

When to Use

Workflow

Integrations

Error Handling

Gotchas

Example

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills