sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
43
17%
Does it follow best practices?
Impact
90%
1.38xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/sparc-methodology/SKILL.mdQuality
Discovery
7%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 essentially a label rather than a functional description. It names a methodology (SPARC) and provides its acronym expansion but fails to describe what concrete actions Claude performs, when to use it, or what user requests should trigger it. It reads more like a title than a skill description.
Suggestions
Add concrete actions describing what this skill does, e.g., 'Breaks down complex software projects into specification, pseudocode, architecture, refinement, and completion phases. Generates structured development plans and coordinates multi-step implementation.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to plan a software project, design system architecture, break down a complex feature, or follow a structured development workflow.'
Include natural keywords users would actually say, such as 'project planning', 'system design', 'software architecture', 'development plan', 'step-by-step implementation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a methodology acronym and expands it, but does not describe any concrete actions Claude would perform. 'Multi-agent orchestration' and 'comprehensive development methodology' are abstract and vague. | 1 / 3 |
Completeness | There is no 'Use when...' clause or equivalent trigger guidance. The 'what' is only vaguely implied through the acronym expansion, and the 'when' is entirely missing. | 1 / 3 |
Trigger Term Quality | The terms 'SPARC', 'multi-agent orchestration', and the acronym expansion are technical jargon unlikely to be naturally used by users. Common trigger terms like 'build', 'develop', 'plan project', 'architecture design' are absent. | 1 / 3 |
Distinctiveness Conflict Risk | The SPARC acronym itself is somewhat distinctive, but 'comprehensive development methodology' is extremely broad and could overlap with any coding, planning, or architecture skill. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but extremely verbose reference document that reads more like product documentation than an actionable skill file. It explains many concepts Claude already knows (TDD, code review criteria, microservices), lists 17 modes with redundant capability descriptions, and packs everything into a single monolithic file. The actionable content (MCP tool syntax, CLI commands) is buried under excessive explanatory text, and workflows lack validation checkpoints.
Suggestions
Reduce content by 60-70%: Remove capability bullet lists for each mode, eliminate explanations of known concepts (TDD, code review, microservices), and keep only the MCP/CLI invocation syntax with brief mode descriptions.
Split into multiple files: Create MODES.md for detailed mode reference, PATTERNS.md for orchestration patterns, EXAMPLES.md for integration examples, and keep SKILL.md as a concise overview with links to each.
Add validation checkpoints to workflows: After each step, specify how to verify success (e.g., 'Check swarm_monitor output for agent status', 'Verify test coverage meets threshold before proceeding to review').
Remove marketing-style content: The 'Performance Benefits' section with benchmark claims, the 'Support and Resources' links, and the acronym redefinition at the bottom ('SPARC = Systematic, Parallel, Agile, Refined, Complete' contradicts the header definition) add no actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 600+ lines. Extensively explains concepts Claude already knows (what TDD is, what microservices are, what code review criteria are). Lists capabilities for 17 modes with redundant descriptions. The 'Core Philosophy' and 'Key Principles' sections are generic software engineering wisdom that adds no actionable value. Much of this could be reduced by 70%+ without losing useful information. | 1 / 3 |
Actionability | Provides concrete MCP tool call syntax and CLI commands which are useful, but the JavaScript code blocks are configuration/invocation examples rather than executable code. Many examples show API calls with options but don't show expected outputs or how to handle results. The mode descriptions list capabilities without showing concrete usage patterns. | 2 / 3 |
Workflow Clarity | Multi-step workflows are listed (e.g., TDD workflow, feature development pipeline) with clear sequencing, but there are no validation checkpoints or error recovery steps. No guidance on what to do when a step fails, how to verify a mode completed successfully, or feedback loops for error conditions. The Red-Green-Refactor cycle is described but lacks verification between steps. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the massive size. All 17 mode descriptions, multiple orchestration patterns, integration examples, and advanced features are crammed into a single file. This content desperately needs splitting into separate reference files (e.g., MODES.md, PATTERNS.md, EXAMPLES.md) with the SKILL.md serving as a concise overview. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1116 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- ruvnet/ruvector
- Commit
c2089c4
- 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.