CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-sparc-coordinator

Agent skill for sparc-coordinator - invoke with $agent-sparc-coordinator

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agent-sparc-coordinator
What are skills?

25

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

33%

Real-Time Notifications Feature Planning

Full SPARC phase structure and quality gates

Criteria
Without context
With context

All five phases present

70%

100%

Correct phase order

87%

100%

Quality gates present

100%

100%

Gate 1: Specification Complete

28%

100%

Gate 2: Algorithms Validated

28%

100%

Gate 3: Design Approved

42%

100%

Gate 4: Code Quality Met

42%

100%

Specification content

75%

100%

Pseudocode content

75%

100%

Architecture content

100%

100%

Refinement includes TDD

0%

100%

Completion content

100%

100%

Decision documentation

100%

100%

Without context: $0.3116 · 2m 25s · 12 turns · 19 in / 7,117 out tokens

With context: $0.5870 · 3m 15s · 23 turns · 30 in / 10,015 out tokens

96%

22%

Loan Calculation Bug Fix Planning

Bug fix SPARC pattern application

Criteria
Without context
With context

Light specification

75%

91%

Refinement emphasis

50%

75%

Regression testing present

100%

100%

TDD in Refinement

30%

100%

Refinement content elements

40%

100%

All phases present

100%

100%

Quality gates enforced

100%

100%

Pattern differentiation

100%

100%

Decision documentation

100%

100%

Iteration within Refinement

50%

100%

Without context: $0.2347 · 1m 43s · 8 turns · 11 in / 4,968 out tokens

With context: $0.4864 · 2m 27s · 21 turns · 27 in / 7,333 out tokens

100%

3%

Monolith Decomposition Planning

Refactoring SPARC pattern and Architecture phase depth

Criteria
Without context
With context

Architecture phase emphasis

75%

100%

Preservation testing

100%

100%

Documentation updates

100%

100%

Component definition

100%

100%

Interface contracts

100%

100%

Integration planning

100%

100%

All phases present

100%

100%

Quality gates present

100%

100%

Pattern differentiation

100%

100%

Decision documentation

100%

100%

Completion content

100%

100%

Without context: $0.3445 · 2m 20s · 17 turns · 72 in / 6,276 out tokens

With context: $0.3968 · 2m 49s · 17 turns · 21 in / 7,743 out tokens

Evaluated
Agent
Claude Code

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.