ecc-guide

Guide users through ECC's current agents, skills, commands, hooks, rules, install profiles, and project onboarding by reading the live repository surface before answering.

Quality

74%

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 ./skills/ecc-guide/SKILL.md

Quality

Content

82%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 a lean, highly actionable overview with concrete commands, clear sequenced workflows, and dry-run validation checkpoints for the destructive install operations. It is well-structured for progressive disclosure, with only minor trimming and organization opportunities.

Suggestions

Tighten the 'Response Style' section (Good first response shape / Avoid list) to remove minor over-explanation and push conciseness toward 5.

Add an explicit validate-fix-retry feedback loop to the Install Guidance flow (e.g., re-run --dry-run after resolving plan errors) to reach the workflow-clarity 5 anchor.

Consider moving the three Output Templates into a short referenced section or file so the core overview stays maximally scannable.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no explanations of what skills/hooks are), with only minor instances of over-explanation such as the 'Good first response shape' and 'Avoid' guardrails that could be trimmed, placing it just below the lean 5 anchor.	4 / 5
Actionability	Provides copy-paste ready, executable commands throughout (catalog.js --json, install-plan.js --list-profiles, rg searches, npm run harness:audit) plus concrete output templates covering the common cases, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	Clear multi-step sequences for Project Onboarding (5 steps) and Feature Discovery (4 steps) with validation via --dry-run and 'ask before applying changes', so the destructive-operation cap does not apply; minor validation gaps keep it just below the explicit feedback-loop 5 anchor.	4 / 5
Progressive Disclosure	Well-organized single overview file with clearly signaled one-level references to related commands in 'Related Surfaces'; at ~190 lines it exceeds the 50-line simple-skill exception, and the inline Output Templates represent a minor organization gap versus the cleanly-split 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

66%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 clearly scopes a distinct niche and names concrete domain surfaces, but it omits an explicit 'Use when' trigger clause, which caps completeness and limits trigger-term quality. Adding concrete trigger phrases would move it toward the top anchors.

Suggestions

Append a 'Use when the user asks what ECC includes, wants help finding a skill/command/agent/hook, is new to the repository, or asks how to do X with ECC' clause to satisfy the completeness 'when' requirement.

Add natural synonyms users say (e.g., 'slash commands', 'plugins', 'install profiles/modules') to lift trigger-term coverage toward 5.

Lead with one or two more concrete verbs (e.g., 'Navigate, recommend, and install ECC components...') to strengthen specificity beyond 'guide users through'.

Dimension	Reasoning	Score
Specificity	Enumerates seven concrete ECC surfaces (agents, skills, commands, hooks, rules, install profiles, project onboarding) plus the action 'by reading the live repository surface before answering', but only ~2 distinct verbs, so it falls short of the comprehensive multi-action 5 anchor.	4 / 5
Completeness	The 'what' is clear (guide users through ECC components by reading the live repo), but there is no 'Use when...' clause and 'when' is only weakly implied, which per the guideline caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural keywords users would say (skills, commands, hooks, rules, install profiles, project onboarding) with good coverage, but lacks 'Use when' trigger phrases and synonyms like 'slash commands' or 'plugins' that would reach 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to the distinct ECC onboarding/navigation niche, but the component terms (agents, skills, commands, hooks) overlap with general Claude Code skills, creating minor conflict risk rather than the minimal risk of a 5.	4 / 5
	Total	15 / 20 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
referenced_paths_exist	Referenced path issues: 9 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/ecc-guide/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.