sparc-methodology

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

1.38x

Quality

57%

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and well-sequenced workflows, but it is overlong and padded with repetition, generic capability lists, and marketing claims, and it makes no use of progressive disclosure to separate reference material into bundle files.

Suggestions

Trim repeated mcp__claude-flow__sparc_mode blocks to a single canonical example per pattern and reference it, removing dozens of near-duplicate invocations.

Split the per-mode reference, orchestration patterns, and integration examples into separate files under references/ and link to them from a leaner overview, enabling progressive disclosure.

Add explicit validation/checkpoint steps to batch and deployment workflows (e.g., verify tests pass before review, confirm review passes before deploy).

Remove generic capability bullet lists that restate concepts Claude already knows and the performance-benefits marketing claims.

Dimension	Reasoning	Score
Conciseness	The body is ~1100 lines that repeat the same mcp__claude-flow__sparc_mode invocation pattern dozens of times, list generic capabilities Claude already knows, and include marketing claims, so it is padded and could be tightened considerably, though concrete content prevents a level-1 score.	2 / 3
Actionability	It provides concrete, copy-paste-ready CLI commands (e.g., 'npx claude-flow sparc run researcher "task"') and specific mode invocations with real options (coverage_target: 90, test_framework: "jest"), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Phases 1-5, TDD red-green-refactor, numbered common workflows), but explicit validation checkpoints for batch/destructive operations are missing or only implicit, capping this at 2.	2 / 3
Progressive Disclosure	It is a single monolithic file with no bundle files or external references; despite a table of contents and organized sections, all detail that could be split out (mode reference, examples) remains inline, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 identifies the domain and a distinctive acronym but relies on jargon and omits any explicit 'when to use' trigger guidance. It is adequate but generic, landing at the middle anchor across all dimensions.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g., 'Use when planning a feature end-to-end, structuring TDD work, or coordinating multiple agents on a build').

Replace jargon-heavy phrasing with concrete actions a user would recognize (e.g., 'decompose tasks, generate failing tests, review code, orchestrate parallel agents').

Tighten the acronym expansion so the description leads with capability rather than definition.

Dimension	Reasoning	Score
Specificity	Names the development domain and lists the five SPARC phases, but describes no concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multiple-concrete-actions level 3.	2 / 3
Completeness	It states what the skill is but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like 'multi-agent orchestration' and the acronym expansion are technical jargon; recognizable keywords ('development methodology') exist but natural user phrasings and common variations are missing, so it falls short of level 3.	2 / 3
Distinctiveness Conflict Risk	The SPARC acronym and orchestration framing give it a niche, but it could still overlap with general development or architecture skills, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 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/agentic-flow
Path: .claude/skills/sparc-methodology/SKILL.md
Commit: d069fff

Reviewed: about 10 hours 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.