CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-code-goal-planner

Agent skill for code-goal-planner - invoke with $agent-code-goal-planner

42

2.28x
Quality

13%

Does it follow best practices?

Impact

89%

2.28x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-code-goal-planner/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

98%

44%

Notification Service Implementation Plan

SPARC-GOAP feature implementation planning

Criteria
Without context
With context

Specification phase present

66%

100%

Pseudocode phase present

0%

71%

Architecture phase present

57%

100%

Refinement phase present

42%

100%

Completion phase present

85%

100%

claude-flow sparc commands

0%

100%

Milestone id field

100%

100%

Milestone preconditions field

100%

100%

Milestone deliverables field

100%

100%

Milestone success_criteria field

0%

100%

Milestone estimated_hours field

0%

100%

Milestone dependencies field

60%

100%

Milestone SPARC phase mapping

25%

100%

Risk assessment technical dimension

100%

100%

Risk assessment multi-dimensional

85%

100%

Definition of done

100%

100%

71%

32%

Engineering Health Dashboard: Current State vs Target State Analysis

GOAP state analysis with quality metrics

Criteria
Without context
With context

current_state object

50%

100%

goal_state object

50%

100%

test_coverage field

100%

100%

tech_debt field

0%

100%

bugs_open field

100%

100%

Coverage target >= 80%

0%

100%

Complexity target < 10

100%

100%

Duplication target < 3%

0%

100%

p99 latency target

0%

0%

Throughput target

0%

0%

Error rate target

0%

50%

MTTR target

100%

100%

Test pyramid breakdown

0%

20%

Milestone state transitions

100%

100%

100%

75%

Automated Multi-Agent Development Workflow Setup

MCP tool integration for development swarm

Criteria
Without context
With context

swarm_init call

37%

100%

swarm_init topology

0%

100%

swarm_init maxAgents

28%

100%

agent_spawn call

25%

100%

sparc-coder agent type

0%

100%

sparc-coder capabilities

0%

100%

task_orchestrate call

25%

100%

task_orchestrate strategy

0%

100%

memory_usage store call

0%

100%

memory namespace code-patterns

0%

100%

Sequential ordering

66%

100%

Inline comments

100%

100%

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.