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

63%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/agents/autogpt/SKILL.md

Quality

Content

50%

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

The content is broadly actionable with good use of real one-level references, but it carries concept-explanation padding and illustrative code, and its deployment/database/recovery workflows omit validation steps.

Suggestions

Trim concept-explanation padding (architecture diagrams, block-purpose tables, the 'Use alternatives instead' list) to what Claude does not already know.

Add explicit validation/verification steps to the deployment, database migration, and stuck-execution recovery workflows (e.g., check container health, verify migration succeeded, confirm queue is drained before restarting).

Move inline deployment YAML, provider/integration tables, and detailed block catalogs into the existing references so SKILL.md stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but padded with concepts Claude already knows (architecture overview, 'graphs containing nodes connected by links', ASCII diagrams, and restated block-purpose tables), so it could be tightened rather than being lean throughout.	2 / 3
Actionability	It provides many concrete commands and snippets (docker compose, ./run forge create, REST examples), but several are illustrative or partial with placeholders (e.g., self.get_credentials("openai"), DATABASE_URL=postgresql://...), so they are not fully copy-paste ready.	2 / 3
Workflow Clarity	Multi-step sections are sequenced, but deployment, database migration, and stuck-execution recovery lack validation checkpoints or feedback loops, which per the rubric caps workflow clarity at 2 for these destructive/batch/db operations.	2 / 3
Progressive Disclosure	Two real, well-signaled one-level-deep references exist (advanced-usage.md, troubleshooting.md) with no nesting, but substantial reference-suitable material (deployment YAML, provider/integration tables, block catalogs) is kept inline rather than split out.	2 / 3
	Total	8 / 12 Passed

Description

77%

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

The description clearly states capabilities and provides explicit use-when guidance in third person, but its trigger terms lean toward platform framing rather than natural user phrasing and one clause is broad enough to risk overlap.

Suggestions

Rewrite trigger terms in plain user language (e.g., 'Use when the user wants to build agents that keep running on their own, design drag-and-drop agent workflows, or automate a chain of tasks') so they match what a user would actually say.

Tighten the broad 'complex multi-step AI automation systems' clause to a more specific niche to reduce conflict risk with generic automation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'building and deploying continuous agents', 'creating visual workflow agents', 'deploying persistent autonomous agents', and 'building complex multi-step AI automation systems' — matching the anchor for several specific actions rather than a single vague domain.	3 / 3
Completeness	It explicitly answers both what the skill does ('platform for building and deploying continuous agents') and when to use it ('Use when creating...'), satisfying the explicit what-and-when anchor.	3 / 3
Trigger Term Quality	Triggers like 'visual workflow agents', 'persistent autonomous agents', and 'multi-step AI automation systems' are relevant but framed in platform terminology rather than the plain phrases a user would naturally say, and common user-level variations are missing.	2 / 3
Distinctiveness Conflict Risk	The continuous/visual-workflow agent niche is fairly distinct, but the broad phrase 'complex multi-step AI automation systems' could still overlap with general automation skills, keeping it below the clear-niche anchor.	2 / 3
	Total	10 / 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: OpenLAIR/dr-claw
Path: skills/agents/autogpt/SKILL.md
Commit: 6da7f7c

Reviewed: about 7 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.