cx-coding-agents

Use this skill when the user asks about AI Center Coding Agents data, wants to reproduce or extend the Coding Agents dashboards, or asks questions about usage, cost, tokens, sessions, tools, code impact, users, models, spans, or logs for Claude Code, Codex, Cursor, Gemini CLI, or Copilot CLI.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

The body is well-structured and highly actionable, with executable commands, accurate label details, a clear workflow with an ask-before-query checkpoint, and excellent one-level-deep progressive disclosure. Its main weakness is mild redundancy across the repeated agent tables that slightly hurts conciseness.

Suggestions

Consolidate the agent/data-source information that currently repeats across 'Supported Agents', 'Loading References', and 'First Response' into a single canonical table to reduce redundancy and token cost.

Trim the longer prose caveats in 'Cross-Agent Questions' into tighter bullet form so each token earns its place.

Consider collapsing the 'Supported Agents' and 'Loading References' tables into one combined table keyed by agent, since each row already pairs a data source with its required references.

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with minimal concept-padding, but the agent list recurs across the 'Supported Agents', 'Loading References', and 'First Response' tables and the 'Cross-Agent Questions' caveats are somewhat verbose, so it could be tightened. It is not a 1 because it avoids explaining concepts Claude already knows and is mostly efficient.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands (e.g. `cx metrics search --name '<pattern>'`, `cx logs '<dataprime_query>'`) and executable PromQL/DataPrime snippets with exact label names, including the `$l.applicationName` vs `$l.applicationname` case distinction. It is not a 2 because the examples are complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	Sequences a clear workflow (identify agent → load references → confirm scope → query with the matching data source → answer with caveats) and includes an explicit checkpoint ('If any required scope is missing, ask before querying') plus an ambiguity clarification rule. No destructive/batch validation loop is required because the Safety section confirms all commands are read-only.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with a dedicated 'Loading References' table that signals exactly which one-level-deep reference files to load per agent; all 10 referenced files exist on disk and content is appropriately split into separate query-language and per-agent reference files.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, trigger-rich, and clearly scoped to a distinct niche, with an explicit 'Use when' clause covering both what and when. It uses correct third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Names the domain ("AI Center Coding Agents data") and multiple concrete actions ("reproduce or extend the Coding Agents dashboards", "asks questions about usage, cost, tokens, sessions, tools, code impact, users, models, spans, or logs") across five named agents, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states when to use the skill ("Use this skill when the user asks about...") and conveys what it handles via the enumerated data categories and agents; the combined action-plus-trigger framing matches the score-3 example. It is not capped at 2 because an explicit 'Use when...' clause is present.	3 / 3
Trigger Term Quality	Includes natural terms a user would actually say — "usage, cost, tokens, sessions, tools, users, models, spans, logs" plus agent names ("Claude Code, Codex, Cursor, Gemini CLI, or Copilot CLI") and "reproduce or extend the dashboards", giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Targets a clearly scoped niche ("AI Center Coding Agents" with five specific named agents and distinct data types), making it unlikely to trigger for the wrong skill. It does not use first or second person, so the voice penalty does not apply.	3 / 3
	Total	12 / 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_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: coralogix/cx-cli
Commit: 76b0766

Reviewed: 3 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.