CtrlK
BlogDocsLog inGet started
Tessl Logo

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:projectbluefin/dakota --skill executing-plans
What are skills?

26

0.75x

Quality

62%

Does it follow best practices?

Impact

21%

0.75x

Average score across 10 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./.opencode/skills/executing-plans/SKILL.md
SKILL.md
Review
Evals

Evaluation results

Variant Failed

Execute an Implementation Plan

Plan initialization with announcement, critical review, and TodoWrite creation

Criteria
Without context
With context

Skill announcement

0%

Failed

Reads plan file first

0%

Failed

Critical review of plan

0%

Failed

Creates TodoWrite

0%

Failed

Does not execute before review

0%

Failed

0%

Execute a Multi-Task Refactoring Plan

Batch execution with default size of 3 and task status tracking

Criteria
Without context
With context

Executes first batch of 3

0%

0%

Marks tasks in_progress

0%

0%

Marks tasks completed

0%

0%

Reports after batch

0%

0%

20%

20%

Execute an Authentication Integration Plan

Stopping on blockers and raising plan concerns before execution

Criteria
Without context
With context

Identifies plan concern during review

0%

16%

Raises concern before executing

0%

0%

Does not guess through blocker

0%

42%

0%

Execute a Small Feature Plan in a Git Repository

Finishing sub-skill invocation and main branch protection

Criteria
Without context
With context

Does not implement on main/master

0%

0%

Announces finishing sub-skill

0%

0%

References finishing sub-skill

0%

0%

65%

Execute a Configuration Setup Plan

Exact plan step execution and running specified verifications

Criteria
Without context
With context

Follows step order exactly

100%

60%

Creates files as specified

100%

100%

Runs verification commands

0%

0%

Does not add unplanned steps

60%

100%

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.