executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Install with Tessl CLI
npx tessl i github:shousper/claude-kit --skill executing-plans74
Quality
62%
Does it follow best practices?
Impact
91%
2.33xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/executing-plans/SKILL.mdEvaluation results
92%
57%Implement the User Notification Service
Team setup and batch execution workflow
Skill announcement
0%
100%
kit:team-orchestration used
0%
100%
Implementer role present
0%
100%
Reviewer role present
25%
100%
Plan-derived team name
33%
100%
First batch is 3 tasks
100%
100%
Tasks assigned via SendMessage
0%
0%
Reviewer assigned after batch
70%
100%
Reviewer findings included in report
30%
100%
Verification output shown
62%
100%
Ready for feedback phrase
0%
100%
No commits during implementation
100%
100%
Without context: $0.1791 · 56s · 12 turns · 15 in / 3,452 out tokens
With context: $0.4250 · 1m 37s · 22 turns · 24 in / 5,714 out tokens
84%
64%Implement Config Parser Modules
Within-batch parallelism and reviewer gate
kit:team-orchestration referenced
0%
0%
Implementer spawned
0%
100%
Reviewer spawned
0%
100%
Additional implementers for parallel tasks
0%
100%
Parallel assignment documented
33%
100%
TaskUpdate owner or simultaneous SendMessage
0%
70%
Reviewer assigned post-batch
20%
100%
Reviewer findings in report
30%
100%
Verification output in report
75%
100%
Ready for feedback phrase
0%
100%
No commits during implementation
100%
100%
Skill announcement
0%
0%
Without context: $0.2470 · 1m · 19 turns · 16 in / 3,975 out tokens
With context: $1.0193 · 2m 43s · 27 turns · 1,129 in / 6,855 out tokens
98%
36%Execute the Data Pipeline Refactor Plan
Blocker handling and no-commit-during-implementation rule
Skill announcement
0%
66%
Team setup documented
0%
100%
Execution stopped at Task 3
33%
100%
Blocker explicitly identified
100%
100%
Asks for clarification not guessing
53%
100%
No guessing or workaround implemented
100%
100%
No git commits made
100%
100%
kit:finish-branch NOT used
100%
100%
Completed tasks reported
100%
100%
Specific question asked
10%
100%
Without context: $0.2202 · 57s · 16 turns · 18 in / 3,364 out tokens
With context: $0.6182 · 2m 32s · 32 turns · 34 in / 7,795 out tokens
- 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.