agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

Quality

83%

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

Quality

Content

77%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.

A well-structured, actionable body with a clear validated workflow and strong worked examples. The chief weakness is progressive disclosure: a broken template link and an unlinked reference file whose content is duplicated inline.

Suggestions

Create the missing templates/evaluation-report.md file referenced in Step 3, or inline the report format and drop the reference.

Link references/evaluation-criteria.md from the body and move the 5-axis table and scoring scale there instead of inlining them.

Trim one of the two full scorecard examples or condense the anti-patterns section to reduce token weight without losing the concrete guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with each section earning its place, but the two full scorecard examples, four anti-pattern examples, and best-practices list together carry minor padding that could be trimmed.	4 / 5
Actionability	Provides a concrete 4-step workflow, an explicit scoring scale, an evidence rule, and good/weak worked examples; the referenced report template file is absent, leaving a minor executability gap.	4 / 5
Workflow Clarity	Clear 4-step sequence (collect → score → report → apply) with an explicit fix-or-flag feedback loop in Step 4 and a 'Would the user agree?' self-check checkpoint.	5 / 5
Progressive Disclosure	`references/hook-integration.md` is a real signaled link, but `templates/evaluation-report.md` is a broken reference (no templates/ directory) and the existing `references/evaluation-criteria.md` is never linked while its content is inlined.	3 / 5
	Total	16 / 20 Passed

Description

88%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.

A strong description that explicitly covers what the skill does and when to use it, with concrete actions and named axes. The main gap is missing the natural user-side trigger phrases ('rate yourself', 'how good was that') that live in the body.

Dimension	Reasoning	Score
Specificity	Names the five axes, the per-criterion evidence requirement, and the 1-5 scorecard with improvement suggestions — multiple concrete actions with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (self-rates on 5 axes, produces a 1-5 scorecard) and 'when' (after completing any non-trivial task) with concrete trigger phrasing.	5 / 5
Trigger Term Quality	The explicit 'Use after completing any non-trivial task' clause is a solid natural trigger, but common user phrases like 'rate yourself' appear only in the body, not the description.	4 / 5
Distinctiveness Conflict Risk	The self-evaluation framing is a clear niche, but 'after completing any non-trivial task' is broad and overlaps with related skills like verification-loop and agent-eval.	4 / 5
	Total	18 / 20 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: affaan-m/ECC
Path: skills/agent-self-evaluation/SKILL.md
Commit: 06c5e11

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.