sparc-methodology

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

1.38x

Quality

17%

Does it follow best practices?

Impact

90%

1.38x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/sparc-methodology/SKILL.md

Quality

Discovery

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 very weak across all dimensions. It reads as a label or title rather than a functional description—it names a methodology acronym and uses abstract buzzwords ('comprehensive', 'multi-agent orchestration') without specifying concrete actions or when the skill should be selected. It lacks any explicit trigger guidance and would be nearly impossible for Claude to correctly select from a pool of skills.

Suggestions

Add concrete actions the skill performs, e.g., 'Generates specifications, writes pseudocode, designs system architecture, iteratively refines code, and completes implementation using a structured multi-step workflow.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for structured software development, wants to break a project into specification/pseudocode/architecture phases, or mentions SPARC methodology.'

Replace abstract buzzwords like 'comprehensive development methodology' and 'multi-agent orchestration' with plain descriptions of what actually happens, such as 'coordinates multiple development steps to build software from requirements to completion.'

Dimension	Reasoning	Score
Specificity	The description names a methodology acronym and expands it, but does not describe any concrete actions. 'Comprehensive development methodology with multi-agent orchestration' is abstract language without listing what the skill actually does (e.g., generate specs, write pseudocode, create architecture diagrams).	1 / 3
Completeness	The description weakly addresses 'what' (a development methodology) but provides no 'when' guidance whatsoever. There is no 'Use when...' clause or any explicit trigger guidance.	1 / 3
Trigger Term Quality	The only potential trigger term is 'SPARC', which is niche jargon most users would not naturally say. Terms like 'multi-agent orchestration' and 'comprehensive development methodology' are technical/abstract and unlikely to match natural user requests.	1 / 3
Distinctiveness Conflict Risk	The SPARC acronym itself is somewhat distinctive, but 'comprehensive development methodology' is generic enough to overlap with many coding/development skills. The mention of 'multi-agent orchestration' adds some distinctiveness but remains vague.	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 extremely verbose and monolithic, attempting to document an entire development methodology framework in a single file. While it provides some concrete MCP tool call syntax and CLI commands, much of the content is redundant capability listings and generic software engineering principles that Claude already knows. The lack of validation checkpoints in workflows and absence of progressive disclosure through external file references significantly reduce its effectiveness as a skill document.

Suggestions

Reduce content by 60-70%: remove all 'Capabilities' bullet lists that merely restate what mode names imply, eliminate the 'Core Philosophy' and 'Key Principles' sections, and cut redundant examples that show the same pattern with different task descriptions.

Split into multiple files: create separate files for mode reference (MODES.md), orchestration patterns (PATTERNS.md), integration examples (EXAMPLES.md), and TDD workflows (TDD.md), with SKILL.md serving as a concise overview with links.

Add validation checkpoints to workflows: after each step, include verification commands (e.g., 'check swarm status', 'verify test results') and error recovery instructions (e.g., 'if agent fails, restart with...').

Fix code example syntax to be truly executable or clearly label the calling convention—the current MCP tool call syntax uses neither valid JavaScript nor valid JSON, which could confuse execution.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 700+ lines. Extensively explains methodology philosophy, principles, and capabilities that Claude already understands. Lists like 'Capabilities' for each mode are largely redundant descriptions of what the mode name already implies. The 'Core Philosophy' and 'Key Principles' sections are generic software engineering wisdom that wastes tokens.	1 / 3
Actionability	Provides concrete MCP tool call syntax and CLI commands which are useful, but the JavaScript code blocks are not truly executable—they use a pseudo-call syntax (no function call parentheses, JSON-like object literals without proper syntax). Many examples show what to call but not what the actual output/response looks like, making it harder to verify correct usage.	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. For complex multi-agent orchestration involving batch operations and destructive changes, the absence of feedback loops ('if step fails, do X') caps this at 2.	2 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no references to external files. All 17 modes, multiple orchestration patterns, integration examples, and advanced features are inlined in a single massive document. Content like individual mode details, orchestration patterns, and integration examples should be split into separate referenced files.	1 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 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/agentic-flow
Commit: 8db2712

Reviewed: 26 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.