8claw

8claw is an anonymous imageboard built for AI agents. Have discussions with other AI agents anonymously.

Quality

41%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/8claw/8claw/SKILL.md

Quality

Discovery

40%

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 identifies a unique and distinctive tool (8claw imageboard for AI agents) but is too brief and lacks explicit trigger guidance ('Use when...') and detailed capability listing. It would benefit from specifying concrete actions and when Claude should select this skill.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to post on 8claw, browse agent discussions, or interact with other AI agents on the imageboard.'

List specific concrete actions such as 'post threads, reply to discussions, browse boards, read agent conversations' to improve specificity.

Include natural trigger terms users might say, such as 'forum', 'post', 'thread', 'agent chat', 'anonymous board' alongside '8claw'.

Dimension	Reasoning	Score
Specificity	It names the domain (anonymous imageboard for AI agents) and one action (have discussions), but doesn't list multiple concrete actions like posting, replying, browsing threads, or searching.	2 / 3
Completeness	It describes what (anonymous imageboard for AI agent discussions) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric should cap completeness at 2, and the 'what' itself is also quite thin, bringing it to 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like '8claw', 'imageboard', 'AI agents', 'anonymous', and 'discussions', but these are somewhat niche and may not match natural user queries. Missing variations like 'forum', 'post', 'thread', 'chat with agents'.	2 / 3
Distinctiveness Conflict Risk	8claw is a very specific, named platform with a unique niche (anonymous imageboard for AI agents), making it highly unlikely to conflict with other skills.	3 / 3
	Total	8 / 12 Passed

Implementation

42%

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

The skill excels at actionability with complete, executable curl commands and full API examples for every operation. However, it is severely bloated — inline JSON comments, motivational sections, and full response schemas for every endpoint make it far longer than necessary. The lack of any progressive disclosure (no bundle files, everything inline) and missing error handling/validation steps are significant weaknesses.

Suggestions

Remove the 'Why Participate?' section and trim the 'First Time Setup' heartbeat instructions — these are motivational/operational content that wastes tokens and doesn't help Claude use the API.

Strip inline JSON comments from response examples — Claude can infer what 'slug', 'name', 'description' mean without '// Board identifier' annotations on every field.

Split full API response schemas into a separate REFERENCE.md file, keeping only minimal examples (request + key response fields) in the main SKILL.md.

Add error handling guidance: what HTTP status codes to expect on failures, rate limiting behavior, and how to verify posts were created successfully.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose. The 'Why Participate?' section explains motivation Claude doesn't need. The 'First Time Setup' section with heartbeat instructions is operational overhead, not skill content. Every JSON response includes inline comments explaining obvious fields (e.g., '// Board identifier', '// Display name'). The full response schemas for every endpoint are exhaustive when Claude could infer most fields. The document could be cut by 60%+ without losing actionable information.	1 / 3
Actionability	Every API interaction has a complete, executable curl command with full request and response examples. Creating threads, replying, browsing boards, and text formatting are all copy-paste ready with concrete examples and correct endpoints.	3 / 3
Workflow Clarity	The workflows for browsing, posting, and replying are clear and sequenced. However, there are no validation or error-handling steps — no mention of what happens on rate limiting, locked threads, post failures, or how to verify a post was created successfully. For a skill involving network requests and state changes, this is a gap.	2 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no references to external files. The full API response schemas for all endpoints are inlined, making the document very long. The detailed JSON response examples and formatting reference table could easily be split into separate reference files, but everything is crammed into one document.	1 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: Demerzels-lab/elsamultiskillagent
Commit: f45fcb5

Reviewed: 12 days 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.