self-refine-loop SKILL.md skillA

self-refine-loop from stijnman/grok-custom-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stijnman/grok-custom-skills/self-refine-loop@v1.2.0

Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stijnman/grok-custom-skills
Path
.grok/skills/self-refine-loop/SKILL.md
Versions recorded
4
Latest version
v1.2.0, committed Aug 14, 2026
First version recorded
May 19, 2026
Size
1,707 bytes
Repository stars
14
License
MIT

Runs a generator-critique-reviser loop to iteratively improve agent outputs. Use for: self refine, reflexion loop, critique and revise, improve output.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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

1. Capture the current output and the user's quality criteria.
2. Generate a critique listing specific weaknesses (max 5 bullets).
3. Revise the output addressing every critique point.
4. Score confidence 0-10 on whether criteria are met.
5. 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.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add stijnman/grok-custom-skills/self-refine-loop@sha256:2635d785c161e29a

The line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_oyhfdxhdarojr7vm.svg)](https://markdownregistry.com/a/art_oyhfdxhdarojr7vm)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between May 19, 2026 and Aug 14, 2026, about one every 29 days. Its first recorded version is graded C and its latest A.

versioncommittedcommitsizeaudit
v1.2.0 latest2026-08-14 abe185a 1,707 BA view · diff
v1.1.02026-06-24 5c9866b 1,867 BA view · diff
v1.0.02026-06-11 5771a0a 732 BA view · diff
git:20260519.e01a4dd2026-05-19 e01a4dd 376 BC view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1707 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

stijnman/grok-custom-skills · 14 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_oyhfdxhdarojr7vm
GET https://markdownregistry.com/api/v1/resolve?ref=stijnman/grok-custom-skills/self-refine-loop
GET https://markdownregistry.com/api/v1/blob/2635d785c161e29a64d4c2d69dfa4fa9a48d3c75d2acccf66f2756e0514a0261

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from stijnman/grok-custom-skills

accessible-color-review SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/accessible-color-review/SKILL.md · Review color choices for contrast, semantic consistency, color-vision accessibility, and readable user-interface…
v1.0.0 · audit A · 14 stars
adaptive-workflow-composer SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/adaptive-workflow-composer/SKILL.md · Composes multi-step agent workflows from goals and available skills. Use for: compose workflow, plan steps, adaptive…
v1.2.0 · audit A · 14 stars
agent-reach-wrapper SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/agent-reach-wrapper/SKILL.md · Thin wrapper around Panniantong/Agent-Reach for live web, YouTube transcripts, RSS, GitHub, Bilibili, Exa search, and…
v1.0 · audit A · 14 stars
agent-red-team SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/agent-red-team/SKILL.md · Defensive adversarial testing for AI agents, tools, MCP servers, and skills. Finds prompt-injection, jailbreak leakage…
v1.0.0 · audit B · 14 stars
agentic-uncertainty-quantifier SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/agentic-uncertainty-quantifier/SKILL.md · Scores task uncertainty to calibrate memory depth and iteration count. Use for: quantify uncertainty, fast slow think…
v1.2.0 · audit A · 14 stars
ai-share-extractor-v4 SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/ai-share-extractor-v4/SKILL.md · Extracts shareable insights from long agent sessions for export. Use for: extract shares, shareable summary, export…
v1.2.0 · audit A · 14 stars
architecture-decision-record SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/architecture-decision-record/SKILL.md · Document a significant technical decision with its context, alternatives, consequences, and status. Use for…
v1.0.0 · audit A · 14 stars
auto-skill-resolver SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/auto-skill-resolver/SKILL.md · Plan and coordinate skill-library improvements by identifying gaps, overlaps, and the safest next action. Use for…
v1.1.0 · audit A · 14 stars
auto-tester SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/auto-tester/SKILL.md · Runs validation tests on code, skills, or outputs after changes. Use for: run tests, auto test, validate changes, check…
v1.2.0 · audit A · 14 stars
autonomous-skill-forge SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/autonomous-skill-forge/SKILL.md · Feral-level autonomous skill creation, gap detection, research, unlocking, and workaround system. Combines and exceeds…
git:20260826.04dabb0 · audit A · 14 stars
beta-unlocker SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/beta-unlocker/SKILL.md · Feral-level discovery and activation of hidden modes, feature flags, experimental features, and undocumented…
git:20260826.8b5c351 · audit A · 14 stars
bottleneck-resolver SKILL.md skill
stijnman/grok-custom-skills · .grok/skills/bottleneck-resolver/SKILL.md · Identifies and resolves performance bottlenecks in agent workflows. Use for: find bottleneck, speed up, why so slow…
v1.2.0 · audit A · 14 stars

Every file in stijnman/grok-custom-skills

Browse by kind, by grade A, or by owner.