Ready to supercharge your AI agents?

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

Evolution — measured AI agent skill | DecimalAI

stijnman/evolution

SkillScore95Maintained

Tracks incremental improvements to skills and workflows over time. Use when iterating on skill quality or user says evolve skill, track evolution. Trigg ers:evolve skill, track evolution, improve over time.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

decimalai skills pull stijnman-evolution

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-evolution/SKILL.md

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

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +45% lift-55% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-15%	0%
case-02	✗→✓	▲ Improved	-29%	0%
case-03	✗→✓	▲ Improved	-52%	0%
case-04	✗→✓	▲ Improved	-53%	0%
case-07	✗→✓	▲ Improved	-50%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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/evolution/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Evolution

When to Use

User says evolve skill or task matches this capability
User says track evolution or task matches this capability
User says improve over time or task matches this capability

Workflow

Capture baseline metrics (triggers, success rate, user feedback).
Propose one improvement per cycle.
Apply via skill-evolver; version backup.
Compare before/after; keep or rollback.

Integrations

skill-evolver
skill-evolution-engine
evolver

Error Handling

| Failure | Response | |---------|----------| | Regression detected | Rollback from versions/ backup. |

Gotchas

One change per evolution cycle for clear attribution.

Example

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

Want to see if stijnman/evolution would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.