engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

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

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a tight, well-structured TDD and coverage playbook: concise, actionable with real Go commands, a clear red-green-refactor feedback loop, and clean sectioning with no need for bundle files. It earns top marks across all four dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — every line (TDD loop steps, coverage rules, validation commands) earns its place with no explanation of concepts Claude already knows, matching 'lean and efficient; every token earns its place'.	3 / 3
Actionability	It provides executable, copy-paste-ready commands ('go test ./...', 'go test -cover ./...') plus concrete TDD steps; as an instruction skill with actionable guidance, it meets the 'fully executable commands; specific examples' anchor.	3 / 3
Workflow Clarity	The TDD Loop is a clear numbered sequence whose red→green→refactor progression is an explicit feedback loop, and the Validation Commands section supplies the verification checkpoint, matching 'clear sequence with explicit validation steps; feedback loops'.	3 / 3
Progressive Disclosure	The skill is under 50 lines, single-purpose, and needs no external references; it is organized into well-signaled sections (When to Use, TDD Loop, Coverage Rules, Validation Commands), which the rubric allows to score 3 for such simple skills.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 is concise and third-person with an explicit trigger covering both 'what' and 'when', but it lacks concrete action enumeration and its trigger phrasing is somewhat generic. It scores well on completeness and acceptably on the rest, with distinctiveness and trigger term quality as the weaker spots.

Suggestions

Enumerate concrete actions in the description, e.g. 'Write failing tests, implement to pass, and report coverage for Engram packages.'

Broaden trigger terms to include natural user phrasing like 'writing tests', 'adding coverage', or 'TDD' rather than only 'implementing behavior changes'.

Tie the trigger more tightly to the Engram-specific testing context to reduce overlap with generic testing skills.

Dimension	Reasoning	Score
Specificity	It names the domain ('TDD and coverage standards for Engram') but describes no concrete actions, matching 'names domain and some actions, but not comprehensive'; not a 3 because no specific behaviors are enumerated, and not a 1 because TDD/coverage are concrete domains rather than abstract filler.	2 / 3
Completeness	It explicitly states what ('TDD and coverage standards for Engram') and provides an explicit 'Trigger: When...' clause, satisfying the rubric's requirement for both 'what' and 'when' with explicit triggers.	3 / 3
Trigger Term Quality	'Trigger: When implementing behavior changes in any package' offers one relevant natural phrase, but coverage is limited — missing common variations like 'tests', 'TDD', or 'coverage' as trigger keywords, so it is not the full coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	Scoping to 'Engram' gives it a niche, but the trigger 'implementing behavior changes in any package' is generic and could overlap with other testing/refactoring skills, so it is not the clearly-conflict-free niche of a 3.	2 / 3
	Total	9 / 12 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: Gentleman-Programming/engram
Path: skills/testing-coverage/SKILL.md
Commit: 763a6ba

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.