CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

implementation-approach

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

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

56%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 body presents a coherent, well-sequenced seven-phase decision framework with useful categories and verification definitions, but it is written in dense abstract prose without a worked example or template to ground it. Splitting the pattern catalog and level definitions into reference files would improve both conciseness and navigation.

Suggestions

Add a short worked example (a small feature request walked through Phases 1-7 ending in a Selected Design and decision record) to make the abstract convergence logic actionable.

Move the Reference Strategy Patterns, Verification Level Definitions, and Integration Point Definitions sections into one-level-deep reference files (e.g., references/patterns.md, references/verification.md) linked from the overview.

Tighten the longest passages — especially Phase 2 step 3 and the Subtraction Check — into shorter testable rules, and drop filler guidelines like "Apply 5 Whys" that add tokens without executable guidance.

DimensionReasoningScore

Conciseness

The body avoids explaining known concepts, but the abstract meta-process prose is dense and could be tightened — e.g., the run-on Phase 2 step 3 sentence spanning ~12 dimensions, repeated "meta-cognitive" framing, and filler guidelines like "Apply 5 Whys".

3 / 5

Actionability

Concrete elements exist (named strategy patterns, L1/L2/L3 verification definitions, risk/constraint category lists), but there is no worked example, template, or concrete decision case, so much of the guidance stays abstract with missing key details for execution.

3 / 5

Workflow Clarity

The seven phases are clearly ordered with core questions, explicit stop conditions ("Stop when the current-state facts..."), subtraction tests, and a closing Quality Checks checklist that serves as verification — minor checkpoint gaps keep it below 5.

4 / 5

Progressive Disclosure

No bundle files exist and the single file has reasonable section headers, but the strategy-pattern catalog, verification-level definitions, and integration-point definitions are all inlined content that could live in one-level-deep reference files, leaving the SKILL.md as a leaner overview.

3 / 5

Total

13

/

20

Passed

Description

65%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 has an explicit and reasonably natural trigger clause, but the capability statement is a single abstract phrase. It reads more like a title than a description of what the skill concretely does.

Suggestions

Replace the generic "Implementation strategy selection framework" lead with concrete capability actions, e.g., "Selects an implementation approach (vertical slice, horizontal slice, hybrid) by analyzing the existing codebase, converging on a minimal design, and defining L1/L2/L3 verification levels."

Add natural trigger variations users would actually say, such as "deciding how to structure a change", "build vs. refactor", or "choosing between vertical and horizontal slices".

Clarify the deliverable the skill produces (a Selected Design plus decision-rationale record) so the what-side answers what output the user gets.

DimensionReasoningScore

Specificity

"Implementation strategy selection framework" names the domain but the what-side is a single generic phrase with no enumerated capability actions, matching "Processes PDF files" more than the 1-2-concrete-actions anchor.

2 / 5

Completeness

Both parts are present — an explicit "Use when..." clause and a stated what — but the what ("Implementation strategy selection framework") is abstract rather than a concrete capability list, so it falls short of the level-5 anchor.

4 / 5

Trigger Term Quality

"planning implementation strategy, selecting development approach, or defining verification criteria" gives three natural trigger phrases with good coverage, though common variations like "how to structure this change" or "build vs. refactor" are missing.

4 / 5

Distinctiveness Conflict Risk

The implementation-strategy-selection niche is mostly distinct with specific triggers, though it could overlap with general planning, design, or code-review skills in edge cases.

4 / 5

Total

14

/

20

Passed

Validation

100%

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-skills/skills/implementation-approach/SKILL.md

Reviewed

Table of Contents

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.