Name: sparc-methodology
Rating: 62 (1 reviews)
Author: ruvnet

sparc-methodology

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

1.38x

Quality

46%

Does it follow best practices?

Impact

90%

1.38x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/sparc-methodology/SKILL.md

The canonical home for this skill is sparc-methodology in ruvnet/agentic-flow

Quality

Content

38%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 is rich in mode reference material and concrete CLI/MCP syntax, but it is heavily padded with concepts Claude already knows and structurally monolithic with no progressive disclosure. Workflow sequencing exists but lacks the validation checkpoints required for batch operations, keeping it at the midpoint or below across dimensions.

Suggestions

Move the per-mode capability lists, orchestration patterns, integration examples, and advanced features into separate reference files (e.g. MODES.md, PATTERNS.md) and link to them from SKILL.md to enable progressive disclosure.

Cut explanations of well-known concepts (TDD cycles, architecture patterns) and the marketing 'Performance Benefits' block to reduce verbosity, keeping only mode names, signatures, and commands.

Add explicit validation/verification checkpoints to batch and swarm workflows (e.g. verify outputs after batch execution, validate before proceeding) to lift workflow clarity above the batch-operation cap.

Dimension	Reasoning	Score
Conciseness	The ~1100-line body is noticeably verbose: it explains concepts Claude already knows (e.g. the red-green-refactor TDD cycle, microservices/CQRS/Event Sourcing capability lists) and repeats near-identical MCP call templates across many modes, alongside marketing-style 'Performance Benefits' such as '84.8% SWE-Bench solve rate'.	2 / 5
Actionability	Concrete CLI commands and MCP call signatures are provided, but many snippets are templates with placeholders like '<mode-name>' and the MCP JavaScript blocks are pseudo-syntax (no quotes/parens) rather than executable code, leaving key details incomplete.	3 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced (the five-phase model, numbered common workflows, a red-green-refactor loop), but the batch/swarm operations lack validation or verification checkpoints, and per the rubric missing validation in batch operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	There are no bundle files; the entire ~1100-line body is a monolithic SKILL.md with large sections (per-mode capability lists, advanced features, integration examples) that clearly belong in separate reference files and are inlined with no external references.	2 / 5
	Total	10 / 20 Passed

Description

53%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 clearly conveys what the skill is and uses a distinctive branded acronym, but it lacks an explicit 'Use when...' trigger clause and leans on methodology jargon rather than natural user phrasing. It is solid but not exemplary, landing at the midpoint on most dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural user phrases (e.g. 'Use when planning a feature with TDD, designing system architecture, or coordinating multi-agent development workflows').

Replace methodology jargon with user-facing trigger terms and synonyms so the description matches what a user would actually say.

Reframe the phase list as concrete actions (e.g. 'specify requirements, design architecture, implement via TDD, review, and deploy') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and expands the acronym into five named phases ('Specification, Pseudocode, Architecture, Refinement, Completion'), but states these as taxonomy rather than concrete actions and offers no enumerated verbs, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	It clearly answers 'what' (a comprehensive development methodology with multi-agent orchestration) but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Keywords like 'SPARC', 'multi-agent orchestration', and the five phase names are present, but they are mostly the methodology's own branded jargon rather than natural phrases a user would say, and common synonyms or variations are missing.	3 / 5
Distinctiveness Conflict Risk	The branded 'SPARC' acronym plus 'multi-agent orchestration' carve out a recognizable niche that is mostly distinct from unrelated skills, with only minor overlap risk against generic development-methodology skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/sparc-methodology/SKILL.md
Commit: 74d2a60

Reviewed: 3 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.