context-awareness

How the agent knows what the user is looking at. Use when exposing UI state to the agent, implementing view-screen or navigate actions, wiring navigation state, or debugging agent context issues.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/context-awareness/SKILL.md

Quality

Content

65%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 body delivers focused, framework-specific executable patterns with strong Do/Don't guardrails and minimal padding. Its main gaps are the absence of validation checkpoints in the navigation workflows and no progressive disclosure into bundle files for a 196-line skill.

Suggestions

Add an explicit validation/retry checkpoint for the navigate flow (e.g. verify the UI applied the command and the entry was deleted before proceeding) to raise workflow clarity.

Move the full code listings and the Gold-Standard Mail Template example into a references/ file, keeping SKILL.md a concise overview that links out one level deep.

Define or stub the helper functions used in examples (fetchEmailList, fetchThread) so the code is fully copy-paste executable.

Dimension	Reasoning	Score
Conciseness	Dense, framework-specific material Claude would not already know (useAgentRouteState, readAppState, __url__, ignoreSource jitter) with little padding; only minor trims possible (the motivational "Why" section and a few explanatory sentences).	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready code for useNavigationState, readAppState, writeAppState, the view-screen action, navigate, and useDbSync; minor gaps like undefined fetchEmailList/fetchThread helpers and `command: any` keep it just below fully executable (5).	4 / 5
Workflow Clarity	The read-before-act and write-navigate-then-consume sequences are clear and reinforced by Do/Don't guardrails, but there are no explicit validation checkpoints or feedback loops, which fits the sequence-present-but-checkpoints-missing anchor.	3 / 5
Progressive Disclosure	Well-organized into clear sections (Rule, Core Patterns 1-4, Jitter, Gold-Standard Example, Do/Don't, Related Skills), but at ~196 lines everything is inlined in SKILL.md with no one-level-deep references to bundle files, so content that could live in separate references is inline.	3 / 5
	Total	14 / 20 Passed

Description

67%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 cleanly states both purpose and explicit Use-when triggers with several concrete, domain-specific actions. It is held back from the top band by a slightly abstract opening clause and jargon-heavy trigger terms lacking synonyms.

Suggestions

Lead with a concrete action verb phrase (e.g. "Exposes the user's current view and navigation state to the agent") instead of the abstract "How the agent knows what the user is looking at".

Add natural-language trigger synonyms a developer might actually say (e.g. "agent context", "what the user is looking at", "current screen") alongside the framework jargon.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "exposing UI state to the agent, implementing view-screen or navigate actions, wiring navigation state, or debugging agent context issues" — though the opening clause "How the agent knows what the user is looking at" is somewhat abstract, keeping it just below comprehensive (5).	4 / 5
Completeness	Explicitly answers both what ("How the agent knows what the user is looking at") and when ("Use when exposing UI state... implementing view-screen or navigate actions...") with concrete triggers, but the "what" is more conceptual than action-oriented so not a clean 5.	4 / 5
Trigger Term Quality	Includes relevant developer-facing terms ("view-screen", "navigate actions", "navigation state", "agent context issues") but they are fairly jargon-heavy and lack common synonyms or variations a user might naturally say.	3 / 5
Distinctiveness Conflict Risk	Carves a clear niche around agent context awareness / navigation state with distinct triggers; minor overlap risk with closely related skills (real-time-sync, actions) it itself references.	4 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: .agents/skills/context-awareness/SKILL.md
Commit: d477ebc

Reviewed: 2 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.