agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Quality

76%

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 ./.agents/skills/agent-sort/SKILL.md

Quality

Content

68%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 skill body with concrete commands, a defined evidence-table format, and an explicit output format. Its main gaps are the missing fix-and-retry loop after verification in a batch install/removal workflow, and some duplicated output/bucket definitions that could be trimmed.

Suggestions

Add a feedback loop to step 6: if verification finds stale rules or missing DAILY files, fix and re-verify before returning the report.

Provide at least one executable verification command (e.g. an rg/ls check) instead of only describing the checks abstractly.

Merge the "Outputs" section into the "Output Format" section and reference the DAILY/LIBRARY definitions once to remove repetition.

Dimension	Reasoning	Score
Conciseness	Mostly lean imperative guidance with a concrete evidence-table example and real commands; minor redundancy remains ("Outputs" list duplicated by the "Output Format" section, DAILY/LIBRARY definitions repeated between Classification Model and step 3), so it fits anchor 4's "minor instances that could be trimmed" rather than anchor 5's every-token-earns-its-place.	4 / 5
Actionability	Concrete, executable guidance throughout: rg/cat commands, an exact evidence-table format with realistic rows, and precise paths like ".claude/skills/skill-library/SKILL.md". Falls short of anchor 5 because the rg keyword list and verification checks are illustrative rather than copy-paste-ready for an arbitrary stack.	4 / 5
Workflow Clarity	The six-step core workflow is clearly sequenced and ends with a verify step, but for a batch operation that installs and removes surfaces there is no validate-fix-retry feedback loop and no executable verification commands; per the rubric's batch-operation feedback-loop cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist and none are needed; the body is a well-organized single-level structure with no buried references or nested content. At ~200 lines it is not the sub-50-line simple-skill case that scores 5 on organization alone, leaving anchor 4's "good structure, minor organization gaps" as the best fit.	4 / 5
	Total	15 / 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.

A strong description with an explicit Use-when clause, concrete capability verbs, and a clearly bounded niche. Main weakness is keyword coverage that leans heavily on the ECC acronym and misses natural synonyms like curate, prune, or subset.

Suggestions

Add natural synonyms for the trigger condition, e.g. "Use when curating, pruning, or creating a subset ECC install for a repo".

Mention the verification report and optional skill-library router outputs so the capability list is comprehensive.

Reduce reliance on the ECC acronym alone by including a phrase users would say without knowing the term, such as "selective skill install".

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Build an evidence-backed ECC install plan", "sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets", "parallel repo-aware review passes" — with minor gaps (verification report and library router outputs unmentioned), matching anchor 4 rather than the comprehensive coverage of 5.	4 / 5
Completeness	Explicitly answers both what ("Build an evidence-backed ECC install plan... sorting... into DAILY vs LIBRARY buckets") and when ("Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle") with a concrete trigger clause, matching anchor 5.	5 / 5
Trigger Term Quality	Natural terms like "install plan", "trimmed", "full bundle", and "repo" appear alongside the domain term ECC; a few natural synonyms (curate, prune, subset, selective install) are missing, so it sits between anchors 3 and 4, noticeably above midpoint.	4 / 5
Distinctiveness Conflict Risk	The ECC install-curation niche with DAILY/LIBRARY terminology is clearly distinct, but minor overlap risk remains with closely related skills the body itself hands off to (configure-ecc, skill-stocktake), fitting anchor 4 rather than the minimal-conflict profile of 5.	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: affaan-m/ECC
Path: .agents/skills/agent-sort/SKILL.md
Commit: c70874f

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.