CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-discovery

Optimize websites, docs, and product surfaces for agent discoverability and operator UX. Use when working on agent SEO/AEO/GEO, crawl policy, markdown or JSON projections, llms.txt, sitemap.md, AGENTS.md guidance, content negotiation, accessibility for browser agents, or any request to make a site easier for pi, OpenCode, Claude Code, ChatGPT, Perplexity, or other agent harnesses to find and use.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

A strong, opinionated, well-structured body that is lean and assumes competence, with concrete verification commands and a clear layered thesis. Its main weakness is progressive disclosure — the long implementation map and verification recipes are inlined rather than split into referenced files.

Suggestions

Move the 'joelclaw Implementation Map' (the apps/web/... file-by-file listing) into a separate reference file (e.g. IMPLEMENTATION.md) and link to it from the body, keeping only a short pointer inline.

Extract the 'Verification Checklist' bash recipes into a references/verify.md or scripts/ file and reference it one level deep, so the main SKILL.md stays an overview.

Trim rhetorical filler ('Don't reduce this to AI SEO', 'is dogshit', 'not a framework fetish') to tighten conciseness without losing the opinionated tone.

DimensionReasoningScore

Conciseness

The body is dense and opinionated and largely assumes Claude's competence, but a few rhetorical flourishes ('Don't reduce this to AI SEO', 'A blank SPA shell is dogshit', 'not a framework fetish') are trimmable padding rather than load-bearing guidance.

4 / 5

Actionability

The Verification Checklist gives copy-paste curl/lynx/jq commands and the Implementation Map names concrete file paths and MIME types to check, but the Core Rules are mostly principle-oriented rather than executable steps, leaving minor gaps.

4 / 5

Workflow Clarity

The four-layer thesis and the four-question 'Use This Mental Shortcut' provide a clear sequenced mental model, and the verification checklist groups concrete checkpoints; it stops short of an ordered executable pipeline with explicit validate→fix→retry feedback loops.

4 / 5

Progressive Disclosure

The document is well-sectioned but monolithic at ~290 lines: the repo-specific Implementation Map (file paths in apps/web/...) and the bash verification recipes are inlined content that would read better as one-level-deep reference files, and no bundle files exist to offload them.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

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

An excellent frontmatter description: concise, concrete, and complete with both a clear 'what' and an explicit 'Use when...' trigger clause covering the natural vocabulary of the domain. It is distinctive and unlikely to fire for the wrong skill.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Optimize websites, docs, and product surfaces for agent discoverability and operator UX' plus crawl policy, markdown/JSON projections, content negotiation, and accessibility — giving near-comprehensive coverage of the skill's scope.

5 / 5

Completeness

It explicitly answers both 'what' ('Optimize websites, docs, and product surfaces for agent discoverability and operator UX') and 'when' ('Use when working on agent SEO/AEO/GEO, ... or any request to make a site easier ... to find and use') with concrete trigger phrases.

5 / 5

Trigger Term Quality

It packs in natural trigger terms and synonyms users actually say — 'agent SEO/AEO/GEO', 'llms.txt', 'sitemap.md', 'AGENTS.md', and named harnesses (ChatGPT, Perplexity, Claude Code, pi, OpenCode) — covering the full vocabulary including product names.

5 / 5

Distinctiveness Conflict Risk

The agent-discoverability framing (AEO/GEO, llms.txt, sitemap.md, AGENTS.md, harness-specific names) carves a clear niche with distinct triggers and minimal conflict risk against generic SEO skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
joelhooks/joelclaw
Reviewed

Table of Contents

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.