autogpt-agents

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with abundant executable commands and clear structure, but the body is verbose with concept explanations Claude already knows, missing validation checkpoints on the risky setup, and bulk that belongs in the existing reference files.

Suggestions

Trim foundational explanations (graph/node definitions, 'Blocks are reusable functional components') and move Deployment, Forge, and Benchmarking sections into references/advanced-usage.md, keeping SKILL.md a lean overview that links out.

Add an explicit validation checkpoint after `docker compose up -d --build` (e.g., `docker compose ps` / health check) before directing the user to open the UI, since the warning notes setup may fail.

Move the time-sensitive caveat about the API evolving and examples possibly being outdated into a labeled 'Current state / caveats' note rather than the opening warning block, so it doesn't read as undated decay.

Dimension	Reasoning	Score
Conciseness	Mostly concrete and useful but lengthy (~400 lines) and includes foundational explanation Claude already knows ('Blocks are reusable functional components', graph/node basics); the upfront warning about possibly-outdated examples adds time-sensitive text outside any deprecated section.	2 / 3
Actionability	Provides copy-paste-ready commands throughout — docker compose install, git clone, REST/WebSocket examples, ./run forge commands, docker-compose.prod.yml — with only minor template placeholders in scaffolding examples.	3 / 3
Workflow Clarity	Steps are sequenced (install → access; numbered visual-builder steps) but lack validation checkpoints — the risky Docker/PostgreSQL/Redis/RabbitMQ setup has no verify-services-came-up step despite warning it 'may fail'.	2 / 3
Progressive Disclosure	References to references/advanced-usage.md and references/troubleshooting.md are real and well-signaled one level deep, but the SKILL.md body is monolithic with Deployment, Forge, Benchmarking, and Integrations detail inlined that could live in the existing advanced-usage.md.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, third-person description that states concrete capabilities and gives an explicit 'Use when' trigger with natural vocabulary, covering both what and when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'building and deploying continuous agents', 'creating visual workflow agents', 'deploying persistent autonomous agents', 'building complex multi-step AI automation systems' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ('Autonomous AI agent platform for building and deploying continuous agents') and when via an explicit 'Use when...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'visual workflow agents', 'persistent autonomous agents', 'multi-step AI automation systems', 'continuous agents' — with good variation rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (visual/continuous AutoGPT-style agents) with distinct triggers unlikely to fire for unrelated skills; the body further disambiguates via alternatives.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/autogpt/SKILL.md
Commit: 52845c3

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.