CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

page-agent

Embed an in-page natural-language GUI copilot in web apps.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/web-development/page-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The content is highly actionable with executable code for every path and strong verification checkpoints including failure recovery. Its only weaknesses are a few time-sensitive version pins that could drift and a modest amount of reference-grade detail inlined in SKILL.md.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence ("A panel appears. Type an instruction. Done.") with no explanation of concepts Claude already knows, but scattered time-sensitive version pins (page-agent@1.8.0, Node 22.13+, npm 10 vs 11) are minor trim-worthy instances per the version-number guideline; it is above 3 because nearly every token earns its place.

4 / 5

Actionability

All three paths provide copy-paste-ready code (CDN script tag, bookmarklet, npm import with full PageAgent config, .env examples, npm commands), plus a provider table with concrete baseURL/model values and curl verification commands; it cannot be below 5 since the common cases are fully covered.

5 / 5

Workflow Clarity

Three clearly sequenced paths each end in an explicit "Verifying it works" section with validation checkpoints (devtools console, Network-tab request check, curl -I expecting HTTP 200) and error-recovery guidance (CORS, wrong baseURL, bad API key, restarting the dev server after .env edits), matching the explicit-validation anchor.

5 / 5

Progressive Disclosure

Sections are well-organized with clear headers, external references (repo, docs) are one level deep and clearly signaled, and there are no nested references; it is not 5 because at ~175 lines with an inlined repo-layout table and provider table, some detail could live in separate reference files, though no bundle files exist to hold it.

4 / 5

Total

18

/

20

Passed

Description

53%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.

The description is concise and specific about what the skill does, but it omits any "when to use" trigger guidance and lacks synonym coverage, which limits both completeness and trigger-term quality. Adding an explicit use-when clause with natural user phrases would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to add an AI assistant, copilot, or natural-language agent inside their own web app, or mentions page-agent."

Include natural synonyms users would say, such as "in-app AI assistant", "chatbot widget", or "voice-driven UI", to broaden trigger coverage.

Mention the distinguishable direction (embedding an agent in a page vs. driving a browser from outside) briefly to reduce conflict with browser-automation skills.

DimensionReasoningScore

Specificity

"Embed an in-page natural-language GUI copilot" names the domain and one concrete action, matching the anchor for 1-2 concrete actions without comprehensive coverage; it does not reach 4 because only a single action is listed.

3 / 5

Completeness

The description gives a clear "what" but has no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3; it is above 2 because the "what" is specific, not vague.

3 / 5

Trigger Term Quality

Terms like "copilot", "GUI", "natural-language", and "web apps" are plausible user phrases, but common variations and synonyms (e.g. "AI assistant", "in-app agent", "chatbot", "browser automation") are missing, fitting the 3 anchor.

3 / 5

Distinctiveness Conflict Risk

"In-page natural-language GUI copilot" carves a mostly distinct niche with minor overlap risk against generic chatbot-widget or browser-automation skills, matching the 4 anchor; it is not 5 because the absence of explicit trigger phrases leaves some ambiguity versus adjacent embedding/assistant skills.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/web-development/page-agent/SKILL.md

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.