Agent Self Eval

Q: Why use Agent Self Eval on TypingMind?

Because you install it once and use it with any model. Agent Self Eval is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

Q: How do I install Agent Self Eval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coco-research/coco/tree/main/skills/agent-self-eval. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Agent Self Eval?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

Q: How many AI models can I use with Agent Self Eval?

As many as you like. As long as a model supports skills, you can use Agent Self Eval with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Agent Self Eval AI skill free?

It is published on GitHub by coco-research. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

Q: What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

Q: How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Community

coco-research

agent-self-eval

Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output quality.

Overview

Publisher	coco-research
Repository	`coco`
Skill name	`agent-self-eval`
Stars	550
Forks	12
Bundled files	Instructions only
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by coco-research on GitHub. Read the source before you install it.

Installation

Install the Agent Self Eval AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/coco-research/coco/tree/main/skills/agent-self-eval
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/coco-research/coco.git /tmp/coco
mkdir -p .claude/skills
cp -r /tmp/coco/skills/agent-self-eval .claude/skills/agent-self-eval

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Self Eval in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Self Eval on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Self Eval is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

@agents/PROMPT-DEFENSE.md

Agent Self-Evaluation

Score your own output (or another agent's output) across four axes to identify quality gaps and feed improvements into the learning system.

When to Use

After completing a /team:* pipeline run
After generating a deliverable (PRD, architecture doc, code review)
When user asks "how did I do?" or "evaluate this output"
Automatically at end of /gsd-execute-phase for quality tracking

Evaluation Axes

Axis	Question	Failure Signals
Correctness	Is the output factually accurate and technically sound?	Wrong APIs, broken references, hallucinated facts, logic errors
Clarity	Is the explanation understandable and well-structured?	Confusing structure, undefined jargon, missing context, rambling
Actionability	Can the user act on the output immediately?	Vague suggestions, missing steps, no verification path
Conciseness	Did it use the minimum tokens needed?	Redundancy, over-explanation, filler content, restating the question

Scoring Scale


5 — Exceptional: no reasonable improvement possible
4 — Good: minor nits only, no substantive gaps
3 — Adequate: meets request but has notable weakness on ≥1 axis
2 — Weak: clear gap affecting usability or correctness
1 — Poor: fundamentally misses request or contains significant errors

The Evidence Rule

Every score below 5 MUST cite specific evidence. A score of 3 cannot just say "could be better" — it must say exactly what is missing or wrong. "Show the gap, don't just name it."

Procedure

Step 1: Collect Raw Material

Gather:

Original user request
Final output/deliverable
Tool outputs verifying correctness (test results, exit codes, lint)
User feedback received during task (corrections, "try again")

Step 2: Score Each Axis Independently

Rate 1-5 with mandatory evidence for scores <5.

Step 3: Generate Eval Report


SELF-EVALUATION REPORT
======================
Task: {brief description}
Overall: {weighted average}/5

CORRECTNESS: {score}/5
  Evidence: {specific finding or "No issues found"}

CLARITY: {score}/5
  Evidence: {specific finding or "No issues found"}

ACTIONABILITY: {score}/5
  Evidence: {specific finding or "No issues found"}

CONCISENESS: {score}/5
  Evidence: {specific finding or "No issues found"}

IMPROVEMENT INSTINCTS:
- {trigger} → {action} (confidence: {0.3-0.9})

Step 4: Feed Learning System

If learning system is active (PR-27+), auto-generate instinct YAML from findings:

yaml
---
id: eval-{task-slug}-{axis-lowercase}
trigger: "when {task type}"
action: "{specific improvement}"
confidence: 0.6
domain: quality
source: self-eval
scope: project
---

Integration Points

/team:verify invokes self-eval on Layer 2 output before Layer 3 review
/gsd-execute-phase runs self-eval per subagent, aggregates in SUMMARY.md
High-confidence eval instincts (≥0.8) auto-update team-toolkit.md quality notes
Low scores (≤2) on correctness trigger automatic re-execution offer

Frequently asked questions

What does the Agent Self Eval AI skill do?

Why use Agent Self Eval on TypingMind?

Because you install it once and use it with any model. Agent Self Eval is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Self Eval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coco-research/coco/tree/main/skills/agent-self-eval. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Agent Self Eval?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Self Eval?

As many as you like. As long as a model supports skills, you can use Agent Self Eval with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Self Eval AI skill free?

It is published on GitHub by coco-research. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Auto Qa

openclaw

OrganizationPopular

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

Autoreview

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Claw Score

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Agent Self-Evaluation

When to Use

Evaluation Axes

Scoring Scale

The Evidence Rule

Procedure

Step 1: Collect Raw Material

Step 2: Score Each Axis Independently

Step 3: Generate Eval Report

Step 4: Feed Learning System

Integration Points

Frequently asked questions

Related AI Skills

Set up your own AI workspace now