agent-planner
Agent skill for planner - invoke with $agent-planner
45
Quality
17%
Does it follow best practices?
Impact
92%
1.43xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-planner/SKILL.mdEvaluation results
80%
46%CI/CD Pipeline Setup Plan
YAML plan output format and task fields
Top-level plan key
0%
100%
Objective field
0%
100%
Phases structure
62%
100%
Task id field
100%
100%
Task description field
100%
100%
Task agent field
0%
0%
Task dependencies field
100%
100%
Task estimated_time field
0%
0%
estimated_time format
0%
0%
Task priority field
0%
100%
Priority values
0%
100%
Critical path field
0%
100%
Risks section
50%
100%
Risk description and mitigation
50%
100%
Success criteria
75%
100%
Without context: $0.2767 · 1m 38s · 11 turns · 18 in / 5,520 out tokens
With context: $0.5028 · 2m 14s · 23 turns · 312 in / 7,333 out tokens
100%
24%Database Migration Planning
Critical path identification and risk mitigation planning
critical_path field present
70%
100%
critical_path is array of IDs
10%
100%
Dependencies mapped
100%
100%
Bottlenecks identified
100%
100%
Parallel tasks present
100%
100%
Risks section present
100%
100%
Risk description field
100%
100%
Risk mitigation field
100%
100%
Success criteria present
100%
100%
Measurable success criteria
100%
100%
Logical phases
0%
100%
YAML top-level plan key
0%
100%
Without context: $0.2084 · 1m 31s · 8 turns · 13 in / 5,067 out tokens
With context: $0.3240 · 1m 45s · 14 turns · 19 in / 5,598 out tokens
98%
15%API Product Launch Planning
Task decomposition into phases with documented planning decisions
Atomic tasks
87%
75%
Clear task inputs/outputs
100%
100%
Multiple named phases
100%
100%
Agent assignment
87%
100%
Parallel execution indicated
100%
100%
Time-bound tasks
87%
100%
Success criteria
0%
100%
planning-decisions.md present
100%
100%
Sequencing rationale documented
100%
100%
Parallelism rationale documented
100%
100%
Risks documented
0%
100%
Plan is specific and actionable
100%
100%
Without context: $0.3854 · 2m 21s · 18 turns · 24 in / 7,125 out tokens
With context: $0.5227 · 2m 38s · 23 turns · 433 in / 8,301 out tokens
- Repository
- ruvnet/claude-flow
- Commit
b2618f9
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.