agentic-evaluator

Evaluates any repository's agentic development maturity. Use when auditing a codebase for best practices in agents, skills, instructions, MCP config, and prompts. Produces a scored report with specific remediation steps.

1.50x

Quality

68%

Does it follow best practices?

Impact

93%

1.50x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/agentic-evaluator/SKILL.md

Quality

Content

52%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 is highly actionable with a clear phased workflow and concrete scoring criteria, but it suffers from significant verbosity and poor progressive disclosure: meta-discussion inflates the file while referenced bundle files are missing and reference-worthy material is inlined. Trimming the meta-sections and moving the report template/rubrics into real bundled files would materially improve it.

Suggestions

Trim the meta sections (Lean Context Principle tables, Skill Development Best Practices, Skill Quality Dimensions) that restate concepts Claude already knows; keep only the scoring rubric and workflow.

Create the referenced bundle files (checklist.md, report-template.md) and move the inlined report template, remediation patterns, and size-guidelines tables into them, referencing them by name from SKILL.md.

Consolidate the repeated SkillsBench citations into a single short note to reduce token overhead from repeated evidence blocks.

Dimension	Reasoning	Score
Conciseness	The ~470-line body is noticeably verbose: overlapping meta-sections (Lean Context Principle tables, Skill Development Best Practices, Skill Quality Dimensions) and repeated SkillsBench citations restate concepts Claude already knows and pad well beyond the core audit workflow.	2 / 5
Actionability	Concrete file paths to scan, point-valued scoring criteria, frontmatter schemas, and a copy-paste-ready report template give mostly executable guidance, with minor gaps where criteria are qualitative.	4 / 5
Workflow Clarity	A clear seven-phase sequence (Discovery → Foundation → Skills → Agents → Instructions → Consistency → Report) is laid out with per-phase criteria; as an audit skill it is non-destructive so the validation cap does not apply, though explicit completion checkpoints are thin.	4 / 5
Progressive Disclosure	No bundle files exist, yet the body references 'checklist.md' and 'report-template.md', and inlines content that belongs in separate files (the report template, remediation patterns, and the skill-quality rubric) rather than offloading it to bundled resources.	2 / 5
	Total	12 / 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.

The description is well-formed: it states a specific capability, gives an explicit 'Use when' trigger with natural keywords covering the relevant artifact types, and names the output deliverable. Its main limitation is generic action verbs and lack of synonym/extension coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Evaluates...maturity', 'auditing a codebase for best practices in agents, skills, instructions, MCP config, and prompts', 'Produces a scored report with specific remediation steps'), with minor gaps since the verbs are generic rather than distinct.	4 / 5
Completeness	Clearly answers both what ('Evaluates...maturity', 'Produces a scored report with specific remediation steps') and when ('Use when auditing a codebase for best practices...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'Use when auditing a codebase for best practices in agents, skills, instructions, MCP config, and prompts' provides good natural-term coverage, but lacks synonyms and file extensions to reach comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'agentic development maturity' auditing niche is mostly distinct with specific triggers, with only minor overlap risk against general code-audit or review skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: 0xrabbidfly/eric-cartman
Path: .github/skills/agentic-evaluator/SKILL.md
Commit: 0b8453f

Reviewed: 4 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.