CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-page

The full-page Agent surface (/agent) with Context, Files, Connections, Automations, and Access tabs. Use when mounting the Agent page in a template, adding an app-specific tab, surfacing context transparency, MCP servers, A2A agents, recurring jobs, or external-client connect flows in the UI.

64

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-page/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, lean instruction skill with concrete paths, props, and a clear mounting procedure. It earns consistent 4s across dimensions, held back from 5s by minor over-explanation, lack of copy-paste snippets, and absent explicit verification steps.

Suggestions

Add an explicit verification checkpoint to the mounting workflow (e.g., 'Confirm /agent#context renders the X-Ray before linking nav') to push workflow_clarity toward 5.

Include one small copy-paste route snippet (e.g., a minimal AgentTabsPage mount in agent.tsx) to lift actionability from concrete-reference to fully executable.

Tighten the design-principles prose (e.g., merge the 'what can influence this agent' framing line into the bullet it restates) to move conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no padding about what a tab or MCP server is), but a few framing sentences like 'The page answers what can influence this agent, and why' could be trimmed, matching anchor 4 rather than 5.

4 / 5

Actionability

Concrete guidance with real component names, file paths (packages/core/src/shared/mcp-connect-content.ts), route patterns, and props (showMcpServers={false}, agentPageHref, extraTabs, hiddenTabs); as an instruction-only skill it is not penalized for lacking code blocks, but it stops short of copy-paste-ready snippets, sitting at anchor 4.

4 / 5

Workflow Clarity

'Mounting In A Template' is a clear 5-step sequence with specific files and props, but it lacks explicit validation/verification checkpoints (e.g., confirming the route renders), so it matches anchor 4; the destructive/batch cap does not apply since mounting a page is non-destructive.

4 / 5

Progressive Disclosure

Well organized into a Tabs table, Mounting, and Scope sections with one-level inline cross-skill references ('see context-xray skill', 'client-side-routing skill'); no bundle files exist to offload detail, and the parenthetical reference style keeps it at anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description that clearly identifies the Agent page surface and gives explicit, multi-trigger 'Use when' guidance. It is specific and complete, with only minor overlap risk against closely related sibling skills.

DimensionReasoningScore

Specificity

Names the domain ('full-page Agent surface (/agent)') and lists several concrete tabs/actions ('adding an app-specific tab', 'surfacing context transparency', 'MCP servers, A2A agents, recurring jobs, or external-client connect flows'), matching anchor 4 (several specific actions, minor gaps) rather than 5 since it leans on feature enumeration over fully distinct concrete actions.

4 / 5

Completeness

It explicitly states both what ('The full-page Agent surface (/agent) with Context, Files, Connections, Automations, and Access tabs') and when ('Use when mounting the Agent page in a template, adding an app-specific tab, surfacing context transparency...'), with concrete trigger phrases, matching anchor 5; not 4 because the 'when' is explicit and multi-trigger rather than vague.

5 / 5

Trigger Term Quality

The 'Use when mounting the Agent page... adding an app-specific tab... surfacing context transparency, MCP servers, A2A agents, recurring jobs, or external-client connect flows' clause gives good natural trigger coverage, but terms like 'MCP servers' and 'A2A agents' are technical jargon users may not always phrase that way, so it sits at anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche (the specific /agent page surface) with distinct triggers, but because the page re-hosts related capabilities also covered by sibling skills (context-xray, automations, recurring-jobs), there is minor overlap risk, placing it at anchor 4 rather than 5.

4 / 5

Total

17

/

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.

Validation13 / 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
BuilderIO/agent-native
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.