Name: implementation-approach
Rating: 45.6 (1 reviews)
Author: shinpr

implementation-approach

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

Quality

56%

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

Fix and improve this skill with Tessl

tessl review fix ./dev-workflows-frontend/skills/implementation-approach/SKILL.md

The canonical home for this skill is implementation-approach in shinpr/claude-code-workflows

Quality

Content

35%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 skill lays out a coherent seven-phase decision framework with an explicit sequence and checklist, but it is written in dense abstract prose with zero concrete artifacts — no example decision record, no template, no executable step. It also spends significant tokens explaining patterns (Strangler, Facade, Adapter, etc.) Claude already knows. Splitting reference material into bundle files and adding one worked example would substantially raise its score.

Suggestions

Add a concrete worked example: a short filled-in decision record showing selected strategy, complexity basis, activated risks/constraints, and verification level for a realistic change.

Trim the 'Reference Strategy Patterns' catalog and other explanatory glosses of well-known patterns to a bare name-plus-when-to-use list, cutting roughly a third of the body.

Move the pattern catalog, verification-level definitions, and integration-point definitions into references/ files and link them one level deep from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is padded with meta-language Claude does not need ('Meta-cognitive Strategy Selection Process', 'Classify supporting claims as observed, inferred, or unknown') and catalogs well-known patterns (Strangler, Facade, Adapter, Decorator, Bridge) with textbook glosses, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	No code, commands, templates, or worked examples appear — only high-level directives. Phase 2's four ordered steps and the enumerated comparison dimensions are the most concrete guidance, keeping it above anchor 1, but nothing is directly executable or ready to apply.	2 / 5
Workflow Clarity	Phases 1-7 are clearly sequenced with a closing 'Quality Checks' checklist, but validation is abstract: checkpoints like 'Stop when another current-state fact cannot change...' are implicit and there is no validate-fix-retry loop, matching the 'sequence present but checkpoints missing or implicit' anchor.	3 / 5
Progressive Disclosure	Headers give the 167-line document decent structure, but content that belongs in separate files (the pattern catalog, verification-level and integration-point definitions) is fully inlined with no references at all, matching the 'could be better organized; content that should be separate is inline' anchor.	3 / 5
	Total	10 / 20 Passed

Description

58%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 correctly pairs a domain statement with an explicit 'Use when...' trigger clause, but the what is abstract ('selection framework') and trigger coverage misses common phrasings like 'implementation plan' or 'architecture decision'. It is serviceable but generic within the planning/strategy skill space.

Suggestions

Replace the abstract noun phrase 'Implementation strategy selection framework' with 2-3 concrete capabilities, e.g. 'Selects vertical-slice, horizontal-slice, or hybrid implementation approaches and defines verification levels and integration points'.

Broaden the 'Use when' clause with natural user phrasings such as 'planning how to implement a feature', 'deciding build order', or 'choosing an implementation approach'.

Sharpen distinctiveness by naming what this skill covers that adjacent planning skills do not (e.g., strategy selection plus verification-level assignment), to reduce overlap with generic design/planning skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('strategy selection framework') and a few actions ('planning implementation strategy, selecting development approach, defining verification criteria'), but the what is a single abstract noun phrase rather than several concrete capabilities, matching anchor 3 rather than 4.	3 / 5
Completeness	Both a what ('Implementation strategy selection framework') and an explicit 'Use when...' clause with three triggers are present. Not 5 because the what is a bare noun phrase with no capability breakdown; not 3 because the when is explicit, not merely implied.	4 / 5
Trigger Term Quality	Phrases like 'planning implementation strategy' and 'selecting development approach' are natural triggers, but common variations users would say (implementation plan, how to structure the build, architecture/approach decision) are missing, fitting the 'relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Implementation strategy selection' is somewhat specific but overlaps broadly with general planning, architecture, and design-decision skills, so it could still trigger for the wrong skill.	3 / 5
	Total	13 / 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: shinpr/claude-code-workflows
Path: dev-workflows-frontend/skills/implementation-approach/SKILL.md
Commit: a4ecd62

Reviewed: 6 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.