agent-identifier

Use when creating or configuring Claude Code agents and their frontmatter.

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 ./skills/agent-identifier/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete field specs, validation rules, and templates, but it is verbose with repeated sections, lacks explicit validation feedback loops, and ships broken cross-references alongside an overly monolithic main file.

Suggestions

Consolidate the repeated DO/DON'T, Best Practices, and summary-table sections and drop explanations of concepts Claude already knows to reduce length.

Frame the validation/test steps as explicit checkpoints (validate -> fix -> re-validate -> only then proceed) to add a real feedback loop.

Create the missing examples/ files and scripts/test-agent-trigger.sh referenced in the body, or remove those references, and move detailed patterns into the existing reference files instead of inlining them.

Dimension	Reasoning	Score
Conciseness	The ~430-line body restates concepts Claude already knows (e.g. 'Agents are autonomous subprocesses that handle complex, multi-step tasks independently') and repeats guidance across multiple DO/DON'T, Best Practices, and summary-table sections that could be consolidated; it is mostly useful but noticeably padded.	2 / 3
Actionability	It gives concrete, copy-paste-ready guidance: exact frontmatter field formats with good/bad identifier examples, validation rules, enumerated model/color/tool options, a system-prompt template, and an AI-assisted generation prompt.	3 / 3
Workflow Clarity	Creation and testing steps are sequenced (e.g. the 9-step Implementation Workflow and a 'Validate with scripts/validate-agent.sh' step), but validation checkpoints are implicit with no explicit validate-fix-retry feedback loop.	2 / 3
Progressive Disclosure	References are clearly signaled and the three reference files exist, but several referenced paths are broken (examples/agent-creation-prompt.md, examples/complete-agent-examples.md, and scripts/test-agent-trigger.sh do not exist), and much reference-grade material is inlined rather than split out.	2 / 3
	Total	9 / 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 brief but functional: it states a clear capability and an explicit 'Use when' trigger, with a distinct niche. It is held back from a top score by terse specificity and limited coverage of natural trigger-term variations.

Suggestions

Expand the capability list to concrete actions such as writing system prompts, designing triggering examples, and selecting model/color/tools to lift specificity.

Add common user phrasings like 'add an agent', 'write a subagent', and 'configure agent tools' to broaden trigger-term coverage.

Optionally include 1-2 triggering example phrasings to reinforce the 'when' guidance.

Dimension	Reasoning	Score
Specificity	The phrase 'creating or configuring Claude Code agents and their frontmatter' names the domain and two concrete actions, but does not list multiple specific actions (e.g. writing system prompts, designing triggers, selecting models) to be comprehensive.	2 / 3
Completeness	It explicitly answers both what (create/configure agents and their frontmatter) and when (the explicit 'Use when ...' trigger clause), satisfying the anchor for clearly answering both with an explicit trigger.	3 / 3
Trigger Term Quality	It includes relevant natural terms ('creating', 'configuring', 'agents', 'frontmatter') but misses common variations users would say such as 'add an agent', 'write a subagent', or 'set up agent tools'.	2 / 3
Distinctiveness Conflict Risk	The niche of Claude Code agent creation and frontmatter configuration is distinct with specific triggers, making it unlikely to fire for unrelated 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/agent-identifier/SKILL.md
Commit: 2f7766f

Reviewed: about 14 hours 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.