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.

Install with Tessl CLI

npx tessl i github:0xrabbidfly/eric-cartman --skill agentic-evaluator

What are skills?

1.50x

Quality

81%

Does it follow best practices?

Impact

93%

1.50x

Average score across 3 eval scenarios

SKILL.md

Review

Evals

Discovery

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly articulates a specialized capability for evaluating agentic development practices. It excels at specificity and completeness with explicit 'Use when' guidance and concrete outputs (scored report with remediation steps). The main weakness is trigger term coverage, which could benefit from more natural user phrasings.

Suggestions

Add natural user phrasings to trigger terms, such as 'review my repo setup', 'check agent readiness', or 'evaluate my project's Claude integration'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Evaluates repository's agentic development maturity', 'auditing a codebase for best practices', 'Produces a scored report with specific remediation steps'. Names specific domains: agents, skills, instructions, MCP config, and prompts.	3 / 3
Completeness	Clearly answers both what ('Evaluates repository's agentic development maturity', 'Produces a scored report with specific remediation steps') AND when ('Use when auditing a codebase for best practices in agents, skills, instructions, MCP config, and prompts') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'auditing', 'codebase', 'best practices', 'agents', 'skills', 'MCP config', 'prompts'. However, missing common variations users might say like 'review my repo', 'check my project setup', 'agent readiness', or 'development standards'.	2 / 3
Distinctiveness Conflict Risk	Very specific niche focused on 'agentic development maturity' with distinct triggers like 'MCP config', 'skills', 'instructions'. Unlikely to conflict with general code review or documentation skills due to the specialized focus on agent-related infrastructure.	3 / 3
	Total	11 / 12 Passed

Implementation

77%

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

This is a comprehensive and highly actionable evaluation skill with excellent workflow clarity and concrete scoring criteria. Its main weakness is that it doesn't follow its own advice—at ~400 lines with extensive inline content, it exceeds the 100-300 line guideline it recommends for skills. The irony of an evaluator skill violating the standards it evaluates is notable.

Suggestions

Move the 'Lean Context Principle' section (with noise/signal tables) to a bundled file like `lean-context.md` and reference it with 'See: lean-context.md'

Extract 'Skill Development Best Practices' and 'Remediation Patterns' sections to separate bundled files, keeping only brief summaries in SKILL.md

Consolidate the two full example reports into `examples.md` to reduce SKILL.md length while preserving the actionable templates

Dimension	Reasoning	Score
Conciseness	The skill contains valuable content but is verbose at ~400 lines. The 'Lean Context Principle' section, while useful, is extensive and somewhat meta. The repeated SkillsBench citations and multiple example tables add bulk that could be condensed.	2 / 3
Actionability	Highly actionable with concrete scoring rubrics, specific point allocations, exact file paths to scan, clear criteria tables, and copy-paste ready report templates. The evaluation workflow phases provide step-by-step executable guidance.	3 / 3
Workflow Clarity	Excellent multi-phase workflow with clear sequencing (Discovery → Foundation → Skills → Agents → Instructions → Consistency → Report). Each phase has explicit criteria, point values, and validation checks. The report generation phase provides clear output structure.	3 / 3
Progressive Disclosure	References supporting files (checklist.md, report-template.md) and related skills appropriately. However, the SKILL.md itself is monolithic with extensive inline content (remediation patterns, best practices, examples) that could be moved to bundled files to follow its own advice about progressive disclosure.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: 1 day 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.