implementation-approach
Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.
30
22%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/implementation-approach/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too abstract and buzzword-heavy to be effective. It fails to describe concrete actions the skill performs and uses generic terms that would overlap with many other development-related skills. While it includes a 'Use when...' clause, the trigger terms are not natural user language and the capabilities remain unclear.
Suggestions
Replace 'implementation strategy selection framework' with specific concrete actions, e.g., 'Compares implementation approaches (e.g., iterative vs. big-bang), evaluates tradeoffs, and generates step-by-step development plans.'
Add natural trigger terms users would actually say, such as 'how to build', 'what approach', 'project planning', 'architecture decision', 'build vs buy'.
Narrow the scope to a distinct niche to reduce conflict risk—clarify what kind of implementation strategies (e.g., software projects, data migrations, API integrations) and what distinguishes this from general project planning or architecture skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'implementation strategy selection framework', 'development approach', and 'verification criteria' without listing any concrete actions. There are no specific capabilities described—no verbs indicating what the skill actually does (e.g., compare approaches, generate plans, evaluate tradeoffs). | 1 / 3 |
Completeness | It has a 'Use when...' clause which addresses the 'when', but the 'what' is extremely weak—'implementation strategy selection framework' doesn't clearly explain what the skill does. The 'when' triggers are also vague and overlap heavily with the 'what'. | 2 / 3 |
Trigger Term Quality | Terms like 'implementation strategy', 'development approach', and 'verification criteria' are somewhat relevant but overly generic and not natural phrases users would typically say. Users are more likely to say things like 'how should I build this', 'what architecture should I use', or 'plan my project'. | 2 / 3 |
Distinctiveness Conflict Risk | Terms like 'implementation strategy', 'development approach', and 'planning' are extremely broad and would likely conflict with many other skills related to coding, architecture, project management, or software design. There is no clear niche carved out. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as an abstract planning methodology document rather than an actionable skill for Claude. It is verbose, lacks any concrete code or commands, and explains high-level software engineering concepts (design patterns, risk matrices, constraint analysis) that Claude already knows well. The phased structure provides some workflow clarity, but the absence of executable examples, concrete outputs, and progressive disclosure significantly limits its utility.
Suggestions
Replace abstract descriptions with concrete, actionable templates — e.g., provide a filled-out example of a Design Doc implementation approach section rather than just listing what should go in it.
Cut at least 50% of the content by removing explanations of well-known patterns (Strangler, Facade, Adapter, etc.) and instead provide a concise decision table mapping project characteristics to recommended strategies.
Add a concrete worked example showing the framework applied to a real scenario (e.g., migrating a monolith endpoint to a new service), with specific inputs and outputs at each phase.
Split detailed content (risk matrices, constraint checklists, pattern descriptions) into separate reference files and keep SKILL.md as a concise overview with clear links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is highly verbose and largely describes abstract frameworks and meta-cognitive processes that Claude already understands. Most of the YAML blocks are conceptual checklists rather than actionable instructions, and terms like 'meta-cognitive' and 'comprehensive current state analysis' add no operational value. The skill could be condensed to a fraction of its length. | 1 / 3 |
Actionability | The skill provides no concrete code, commands, or executable examples. It consists entirely of abstract frameworks, checklists, and conceptual descriptions ('Strangler Pattern: Gradual migration through phased replacement') without showing how to actually apply any of them. There is nothing copy-paste ready or directly executable. | 1 / 3 |
Workflow Clarity | The six phases are clearly sequenced and logically ordered, and the quality checks at the end serve as a form of validation checkpoint. However, the steps within each phase are abstract rather than concrete, there are no feedback loops for error recovery, and the verification levels (L1/L2/L3) are defined but not integrated into the workflow with explicit checkpoints. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no separation of overview from detail. All six phases, strategy patterns, risk matrices, and constraint checklists are inlined in a single document with no navigation aids or content splitting, despite the length and complexity warranting it. | 1 / 3 |
Total | 5 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- shinpr/claude-code-workflows
- Commit
adf2e4d
- 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.