Evolutionary mechanisms for the agent to rewrite its own prompts (Neuroplasticity). Use when: self improvement.
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-Improvement Skill
## Goal
> "The software that writes itself."
## Steps
## 1. Evolutionary Prompts (The Genome)
Treat the `system_prompt` and `skill.md` files as **DNA**.
- **Genes:** Individual instructions (e.g., "Always use TDD").
- **Phenotype:** The agent's actual behavior in a session.
- **Fitness Function:** Did the user accept the code? Did the tests pass?
## 2. The Mutation Cycle
When the agent encounters a novel failure or success:
1. **Selection:** Identify the "Gene" (Prompt Instruction) responsible.
2. **Mutation:** Rewrite the instruction.
- *Example:* Change "Write clean code" -> "Write clean code adhering to AIRBNB style guiding."
3. **Crossover:** Combine two successful skills into a new hybrid skill.
## 3. Recursive Self-Editing
The agent has permission to edit its own skill files.
**Protocol:**
1. **Trigger:** "I keep failing to import this library correctly."
2. **Analysis:** "My knowledge base is outdated."
3. **Action:** calling `replace_file_content` on `my-language.skill.md`.
4. **Commit:** "Updated skill memory with correct import syntax."
## 4. Safety Guardrails (Homeostasis)
To prevent "Cancer" (Runaway bad mutations):
…
The line at the top of this page pins the label git:20261014.de0823c, 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.
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 (5878 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
andreibesleaga/gabbe · 23 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sslhizlkylgcgceb
GET https://markdownregistry.com/api/v1/resolve?ref=andreibesleaga/gabbe/self-improvement
GET https://markdownregistry.com/api/v1/blob/bf976354e959956ee11f4556cb8037c48d8f17e6c5a132045b861829726b4e6c
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.
andreibesleaga/gabbe · plugins/gabbe-ai/skills/actor-agent-frameworks/SKILL.md · Implement and manage Actor and Agent Frameworks (e.g. LangGraph). Use when: setup langgraph, implement actor framework…
andreibesleaga/gabbe · plugins/gabbe-ai/skills/agent-ui/SKILL.md · Build specialized user interfaces for interacting with Agents. Use when: build agent ui, create tracing dashboard…
andreibesleaga/gabbe · plugins/gabbe-ai/skills/context-engineering/SKILL.md · Engineer what enters the model's context window for reliability and cost using Write, Select, Compress, and Isolate…
andreibesleaga/gabbe · plugins/gabbe-ai/skills/llm-as-judge/SKILL.md · Score open-ended LLM/agent outputs with another LLM as evaluator while controlling for known judge biases. Use when…
leoyeai/openclaw-master-skills · skills/aaaa/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
leoyeai/openclaw-master-skills · skills/12/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
leoyeai/openclaw-master-skills · skills/aditya/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
leoyeai/openclaw-master-skills · skills/1215656-self-improving-agent-3-0-6/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
leoyeai/agent-master-skills · skills/aaaa/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
leoyeai/agent-master-skills · skills/12/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
leoyeai/agent-master-skills · skills/1215656-self-improving-agent-3-0-6/SKILL.md · Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation…
devantler-tech/agent-skills · self-improvement/SKILL.md · How an autonomous AI engineer improves its OWN definition (its engineering contract, agent definitions, and skills)…