dev-implementation

AI DevKit · Implementation phase guidance for executing feature plans and checking implementation against design. Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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, lean instruction-only skill with concrete commands, explicit validation steps, and clear phase sequencing plus navigation to sibling phases. Its main gaps are minor: duplicated lint instructions and missing failure-handling guidance when lint or verification fails.

Suggestions

State the lint command once (in the Phase Contract) and reference it from the phase sections instead of repeating 'npx ai-devkit@latest lint --feature <name>' three times.

Add a short failure path for validation: what to do when 'npx ai-devkit@latest lint' fails or the verify skill surfaces a mismatch (e.g., fix and re-run before proceeding, mirroring the explicit re-validate loop the workflow otherwise implies).

Make abstract guidance like 'Model the domain when implementation friction repeats' actionable with a concrete cue or example of replacing synchronized flags with a domain structure.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative with no explanations of concepts Claude already knows, but the lint command is repeated three times (Phase Contract items 1-2 and Execute Plan step 1) and a few prescriptive items ('Subtract before adding', 'Model the domain...') could be tightened — anchor 4, not 5's every-token-earns-its-place.	4 / 5
Actionability	Provides concrete executable commands ('npx ai-devkit@latest lint --feature <name>'), specific paths ('.ai-devkit.json', 'docs/ai'), and named sibling skills (tdd, verify, dev-testing, dev-review); a few steps like 'Model the domain when implementation friction repeats' stay abstract, keeping it at anchor 4 rather than 5.	4 / 5
Workflow Clarity	Both Phase 5 and Phase 7 have clear numbered sequences with explicit validation checkpoints (lint before work, tdd/verify skills during, doc updates after each task) and deviation feedback routing ('If major deviations exist, return to dev-design... Execute Plan'), but there is no guidance on what to do when lint or verification fails — anchor 4 with a minor validation gap.	4 / 5
Progressive Disclosure	The body is under 50 lines with no need for external references (none exist in the bundle), and it is organized into clear sections (Phase Contract, Execute Plan, Check Implementation) with 'Next:' navigation pointers — per the simple-skill guideline this matches anchor 5.	5 / 5
	Total	17 / 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: third-person, concise, with an explicit 'Use when...' clause covering multiple concrete triggers and a clearly framed AI DevKit niche. It is specific and complete, with only minor room to add synonyms or further distinguish itself from sibling dev-lifecycle phase skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('executing feature plans', 'checking implementation against design', 'update implementation docs', 'verify code matches design') with only minor gaps in coverage, matching anchor 4; it falls short of anchor 5's comprehensiveness and exceeds anchor 3's 1-2 concrete actions.	4 / 5
Completeness	Explicitly answers both what ('Implementation phase guidance for executing feature plans and checking implementation against design') and when ('Use when the user wants to implement planned tasks... or run dev-lifecycle phases 5 and 7') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('implement planned tasks', 'verify code matches design', 'update implementation docs', 'dev-lifecycle phases 5 and 7'), giving good keyword coverage with a few natural variations missing — anchor 4, not 5's comprehensive synonym coverage, and clearly above anchor 3.	4 / 5
Distinctiveness Conflict Risk	The 'AI DevKit' and 'dev-lifecycle phases 5 and 7' framing carves a clear niche with distinct triggers, but it overlaps slightly with sibling dev-lifecycle skills (dev-planning, dev-testing, dev-review) — anchor 4 rather than 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: codeaholicguy/ai-devkit
Path: skills/dev-implementation/SKILL.md
Commit: 7ef0cd5

Reviewed: 8 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.