context-xray

Inspect and manage the live agent context window with Context X-Ray. Use when context is getting large, the user asks what is in context, or stale tool results/files should be pinned, evicted, restored, or reported by an external host.

Quality

83%

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

Quality

Content

100%

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

The body is a tight, fully actionable overview with concrete commands and a clear install-to-run-to-summarize flow, appropriate for a simple single-purpose skill. No bundle files exist, and the sectioned organization is sufficient for progressive disclosure at this scale.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it teaches no background concepts and every line is an install/run command or a concrete post-run instruction, fitting the level-3 "every token earns its place" anchor.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands (npx install, context-xray --open/threads/trends) with specific flags (--scope project, --open) explained, matching the level-3 anchor.	3 / 3
Workflow Clarity	As a simple read-only report skill, the Setup → Run → summarize sequence is clear and unambiguous; no destructive or batch operation is present that would require validation checkpoints, so the simple-skill allowance applies.	3 / 3
Progressive Disclosure	At under 50 lines with no bundle files (references/scripts/assets are empty) and well-organized ## Setup / ## Run sections, it meets the guideline allowing progressive disclosure to score 3 on simple skills via organization alone.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 specific and well-differentiated with multiple concrete actions and a clear local-agent niche, but it lacks an explicit "Use when…" trigger clause and broader natural trigger-term coverage. Adding trigger phrasing and common user terms would lift the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when a Codex or Claude Code thread is getting large, the user asks where their context is going, or context/tokens feel limited."

Broaden natural trigger terms to include "context window", "running out of context", "token usage", and "context is full" alongside "context usage".

Keep the existing concrete action list; it already satisfies specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Visualize local Codex and Claude Code context usage, open a report, flag warnings, and suggest prompt/tooling optimizations" — matching the anchor for several specific concrete actions rather than the partial coverage at level 2.	3 / 3
Completeness	The description clearly answers what it does but contains no "Use when…" clause or equivalent explicit trigger guidance, which the guidelines cap at level 2.	2 / 3
Trigger Term Quality	"context usage" is a natural term, but common variations users would actually say ("context window", "running out of context", "tokens", "context is full") are missing, so coverage is partial rather than the broad set the level-3 anchor requires.	2 / 3
Distinctiveness Conflict Risk	Naming specific clients ("Codex and Claude Code") and the local context-usage niche gives it a clear, distinct trigger unlikely to overlap with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/context-xray/SKILL.md
Commit: c1ee18b

Reviewed: 5 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.