agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-eval/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.

A highly actionable, well-structured skill body with concrete code and a clear workflow, held back by implicit validation checkpoints, minor padding, and no progressive disclosure into separate reference files.

Suggestions

Add an explicit validation/feedback checkpoint in the workflow (e.g., 'If a judge run fails, inspect the worktree diff and re-run before reporting') to lift workflow clarity for batch operations.

Tighten the editorial tagline and the git-worktree rationale to remove explanation Claude already knows, improving conciseness.

Move detailed judge-type reference material and the full report-format spec into a references/ file linked from the body to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete examples, but includes mild padding such as the editorial tagline and a git-worktree rationale Claude already knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready YAML task definitions, bash run/report commands, and numbered run sub-steps with specific examples.	3 / 3
Workflow Clarity	The Define→Run→Compare sequence is clear, but the judge/validation step is implicit with no explicit checkpoint or error-recovery feedback loop for batch operations.	2 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single self-contained file with no reference files to offload detail into (judge-type specs and report format are all inline).	2 / 3
	Total	9 / 12 Passed

Description

72%

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

A specific, distinct description with strong natural trigger terms, weakened only by the absence of an explicit 'Use when…' clause. It clearly conveys the niche but leaves activation timing implicit.

Suggestions

Add an explicit 'Use when…' clause (e.g., 'Use when comparing or benchmarking coding agents on reproducible tasks') to lift completeness from 2 to 3.

Frame the action as multiple concrete verbs (e.g., 'compare, benchmark, and score coding agents') to strengthen specificity beyond a single 'comparison' action.

Dimension	Reasoning	Score
Specificity	Names the domain (coding-agent comparison) and concrete metrics (pass rate, cost, time, consistency), but the core action is a single comparison rather than multiple distinct concrete actions.	2 / 3
Completeness	Clearly answers what the skill does, but provides no 'Use when…' or equivalent explicit trigger guidance for when to use it, capping completeness at 2.	2 / 3
Trigger Term Quality	Includes natural terms users would say — named agents (Claude Code, Aider, Codex) plus pass rate, cost, time, consistency — giving good coverage of likely trigger phrases.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (head-to-head coding-agent benchmarking) with distinct triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

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.