ecc-guide

Answer questions about Everything Claude Code by reading the live repo surface — agents, skills, commands, hooks, rules, install profiles, and docs — instead of memory. Use when the user asks what ECC includes, how to install or reset it, which skill or command fits a task, or how project onboarding works.

Quality

88%

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

90%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.

An exemplary instruction-style skill body: token-efficient, dense with executable commands and exact file paths, and with well-structured sections and approval/dry-run checkpoints on the install and onboarding workflows. The only gaps are the absence of error-recovery loops and the lack of any offloaded reference files for the template material.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: terse bullet maps ("README.md: install paths, uninstall/reset guidance..."), copy-paste commands, and no explanation of concepts Claude already knows. Every line adds skill-specific information (ECC file layout, ECC-specific scripts, response shaping rules).	5 / 5
Actionability	Guidance is fully executable: copy-paste commands like "node scripts/ci/catalog.js --json", "node scripts/install-plan.js --profile minimal --target claude --json", "node scripts/install-apply.js --skills <skill-id> --target claude --dry-run", "rg -n \"<query>\" skills commands agents docs", plus concrete output templates covering the common response cases.	5 / 5
Workflow Clarity	Multi-step flows are clearly sequenced with checkpoints: onboarding is a numbered list including "resolve a dry-run install plan" and "ask before applying changes", and install guidance routes through --dry-run before apply. It falls short of the 5 anchor because there are no explicit error-recovery feedback loops (validate → fix → retry) for when audits or dry runs fail.	4 / 5
Progressive Disclosure	No bundle files exist, so all content is inline in a single SKILL.md; it is well organized into scannable sections (When To Use, Repository Map, Common Tasks, Output Templates, Related Surfaces) and points to real repo surfaces at one level of depth. Not a 5 because at ~190 lines some self-contained material (e.g., the three output templates) could be split into a reference file to slim the always-loaded body.	4 / 5
	Total	18 / 20 Passed

Description

87%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 third-person description that explicitly states both what the skill does (answer ECC questions from the live repo, not memory) and when to use it, with natural trigger phrasing and a distinct, well-scoped niche. It only narrowly misses top marks on specificity and trigger-term breadth.

Dimension	Reasoning	Score
Specificity	"Answer questions about Everything Claude Code by reading the live repo surface — agents, skills, commands, hooks, rules, install profiles, and docs — instead of memory" names the domain and a concrete method, and the when-clause enumerates specific action types ("how to install or reset it", "which skill or command fits a task"). It falls just short of the 5 anchor because the core capability ("answer questions") is more abstract than a list of multiple concrete operations like extract/fill/merge.	4 / 5
Completeness	Both questions are answered explicitly: the what is "Answer questions about Everything Claude Code by reading the live repo surface... instead of memory" and the when is a concrete "Use when the user asks..." clause listing four specific trigger scenarios. This matches the 5 anchor's structure (explicit what + concrete trigger phrases).	5 / 5
Trigger Term Quality	Natural user phrases are well covered: "what ECC includes", "how to install or reset it", "which skill or command fits a task", "how project onboarding works", plus both the full name and the "ECC" abbreviation. Not a 5 because a few plausible user phrasings (e.g., "troubleshoot my ECC setup", "uninstall", "navigate the repo") are absent.	4 / 5
Distinctiveness Conflict Risk	The description is scoped to a specific named project ("Everything Claude Code"/"ECC") with triggers about ECC's own components, install/reset, and onboarding — a clear niche with minimal overlap risk against generic skills.	5 / 5
	Total	18 / 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: 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.