Ready to supercharge your AI agents?

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

Self Refine Loop — measured AI agent skill | DecimalAI

stijnman/self-refine-loop

SkillScore82Maintained

Runs a generator-critique-reviser loop to iteratively improve agent outputs. Use when the user asks to refine, critique, or improve a draft, or mentionss elf-refine, reflexion, or iterative revision. Stops at 5 iterations orconfid ence 8/10. Triggers: self refine, reflexion loop, critique and revise.

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-self-refine-loop

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-self-refine-loop/SKILL.md

Raw file: /s/stijnman-self-refine-loop/SKILL.md ↗ · machine-readable summary at /s/stijnman-self-refine-loop.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 — +32% lift+8% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	2%	0%
case-01	✗→✓	▲ Improved	25%	0%
case-03	✗→✓	▲ Improved	-5%	0%
case-06	✗→✓	▲ Improved	-36%	0%
case-16	✗→✓	▲ Improved	15%	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/self-refine-loop/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Self Refine Loop

When to Use

User says self refine or task matches this capability
User says reflexion loop or task matches this capability
User says critique and revise or task matches this capability
User says improve output or task matches this capability

Workflow

Capture the current output and the user's quality criteria.
Generate a critique listing specific weaknesses (max 5 bullets).
Revise the output addressing every critique point.
Score confidence 0-10 on whether criteria are met.
Repeat until confidence >= 8 or 5 iterations; return best version with changelog.

Integrations

goal-verifier
agentic-uncertainty-quantifier
dspy-prompt-optimizer

Error Handling

| Failure | Response | |---------|----------| | No criteria given | Ask user for 1-3 success criteria before looping. | | Confidence stuck below 5 | Stop early; report blocker and ask for guidance. | | Output grows unbounded | Cap revisions to prior length + 20%. |

Gotchas

Do not loop on trivial typos; one-pass fix is enough.

Example

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

Want to see if stijnman/self-refine-loop 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.