craft

Implements a feature by executing a plan phase-by-phase — writes tests first, runs them red, then implements code to make them green, then validates nothing is broken. Use when you have a plan from /draft and are ready to implement, build, develop, create, or write code for a feature using TDD.

Quality

86%

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

85%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 orchestration skill with clear sequencing, explicit validation gates, and a real feedback loop. It is concise and actionable, with only minor redundancy and a modest reliance on the reference file for prompt-construction detail.

Suggestions

Consolidate the gate-failure handling so the Workflow loop and the 'Agent Isolation Discipline > Gate Failures' section do not restate the same RED/GREEN outcomes.

Inline the minimal agent-prompt construction skeleton (or a short inline example) so dispatch guidance is self-contained without requiring workflow-detail.md.

Dimension	Reasoning	Score
Conciseness	Mostly lean with concrete tool calls and templates that assume Claude's knowledge, but gate-failure handling is restated across the Workflow and Agent Isolation/Gate Failures sections, leaving minor trimmable redundancy.	4 / 5
Actionability	Concrete tool names, label conventions, and issue-title templates give executable guidance; the bulk of agent-prompt construction is deferred to workflow-detail.md, leaving a small gap in self-contained copy-paste readiness.	4 / 5
Workflow Clarity	Phases are numbered, the orchestration loop is laid out in explicit sub-steps, and RED/GREEN/VALIDATE gates plus a remediate→re-validate feedback loop with a 2-attempt cap provide clear validation checkpoints and error recovery.	5 / 5
Progressive Disclosure	The body is a well-organized overview that clearly signals a single one-level-deep reference (references/workflow-detail.md, verified to exist), splitting detail appropriately with easy navigation.	5 / 5
	Total	18 / 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 states concrete TDD actions and an explicit 'Use when...' trigger tied to a /draft plan. It is mostly distinct, though the breadth of the trigger synonyms introduces slight overlap risk with generic coding skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full TDD cycle — 'executing a plan phase-by-phase', 'writes tests first, runs them red', 'implements code to make them green', 'validates nothing is broken' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (the test-red/implement-green/validate sequence) and 'when' ('Use when you have a plan from /draft and are ready to implement...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural synonyms users say ('implement, build, develop, create, or write code') plus 'TDD', but leans slightly technical and omits file-extension/common-variant terms, sitting just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The /draft-plan + TDD linkage gives a clear niche, but the broad trigger list ('implement, build, develop, create, or write code') carries minor overlap risk with a generic code-writing skill, keeping it just below the minimal-conflict anchor.	4 / 5
	Total	18 / 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: ericjohnolson/tessl-test
Path: plugins/crafter/skills/craft/SKILL.md
Commit: 2a98cc1

Reviewed: 4 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.