self-improve SKILL.md skillA
self-improve from nguyenthienthanh/aura-frog is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nguyenthienthanh/aura-frog/self-improve@git:20260819.03ddfe3Pins git:20260819.03ddfe3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nguyenthienthanh/aura-frog
- Path
aura-frog/skills/self-improve/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260819.03ddfe3, committed Aug 19, 2026
- First version recorded
- Apr 14, 2026
- Size
- 5,019 bytes
- Repository stars
- 25
- License
- MIT
Full learning loop for the Aura Frog plugin: analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends, then apply learned improvements — update rules, adjust agent routing, modify workflow configurations, and generate knowledge base entries.
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
> **AI-consumed reference.** Optimized for Claude to read during execution.
> Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md)
> or [docs/getting-started/](../../../docs/getting-started/) depending on topic.
# Self-Improve Skill
Full learning loop: **Analyze** collected learning data (success/failure patterns, optimization opportunities, agent performance) → **Apply** learned improvements (update rules, adjust agent routing, modify workflow configs, generate knowledge entries).
---
## Analyze
Analyze learning data from Supabase: success/failure patterns, optimization opportunities, agent performance. Runs before Apply — its `v_improvement_suggestions` output feeds the Apply process below.
### Analyze Usage
```bash
/af learn analyze # Full analysis
/af learn analyze --period 30d # Last 30 days
/af learn analyze --focus agents # Agent performance
/af learn analyze --focus workflows # Workflow patterns
/af learn analyze --focus feedback # User feedback
```
### Analyze Process
#### 1. Query Supabase Views
```toon
views[5]{view,purpose}:
…Read the whole file at its exact version.
How to install
mdr add nguyenthienthanh/aura-frog/self-improve@sha256:0066c536a1b7cc28The line at the top of this page pins the label git:20260819.03ddfe3, 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.
[](https://markdownregistry.com/a/art_7zonctd3vgm3fzbt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 14, 2026 and Aug 19, 2026, about one every 32 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260819.03ddfe3 latest | 2026-08-19 | 03ddfe3 | 5,019 B | A | view · diff |
| git:20260515.6be9f59 | 2026-05-15 | 6be9f59 | 2,406 B | A | view · diff |
| git:20260428.3e00277 | 2026-04-28 | 3e00277 | 2,115 B | A | view · diff |
| git:20260421.1fdc0f3 | 2026-04-21 | 1fdc0f3 | 2,093 B | A | view · diff |
| git:20260414.64964fd | 2026-04-14 | 64964fd | 2,069 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5019 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
nguyenthienthanh/aura-frog · 25 stars · license MIT · pushed 2026-10-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7zonctd3vgm3fzbt GET https://markdownregistry.com/api/v1/resolve?ref=nguyenthienthanh/aura-frog/self-improve GET https://markdownregistry.com/api/v1/blob/0066c536a1b7cc28c792a88b11bb8e8c5b5e898c05af610b651656dc87401322
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 nguyenthienthanh/aura-frog
Every file in nguyenthienthanh/aura-frog