executing-plans

Name: executing-plans
Rating: 72 (1 reviews)
Author: obra

tessl install github:obra/superpowers --skill executing-plans

github.com/obra/superpowers

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Review Score

72%

Validation Score

13/16

Implementation Score

85%

Activation Score

40%

SKILL.md

Review

Evals

Generated

12 days ago

Warnings & errors only

Criteria	Score
metadata_version	'metadata' field is not a dictionary
license_field	'license' field is missing
body_examples	No examples detected (no code fences and no 'Example' wording)

Overall Assessment

This is a well-structured process skill with excellent workflow clarity and appropriate conciseness. The main weakness is the lack of concrete examples - showing what a plan file looks like, what a batch report should contain, or what 'verification output' means would make this more actionable. The skill excels at defining when to stop and ask for help, which is critical for execution skills.

Suggestions

Add a concrete example of what a plan file format looks like (even a brief snippet)
Include a sample batch completion report showing the expected format for 'Show what was implemented' and 'Show verification output'

Dimension	Score	Reasoning
Conciseness	3/3	Content is lean and efficient with no unnecessary explanations. Every section serves a purpose, uses imperative language, and assumes Claude understands concepts like TodoWrite, verification, and batch processing.
Actionability	2/3	Provides clear procedural guidance but lacks concrete examples. No sample plan format, no example of what a 'report' looks like, no specific commands or code. Instructions are clear but abstract.
Workflow Clarity	3/3	Excellent multi-step workflow with clear sequence (5 steps), explicit checkpoints ('Ready for feedback'), validation requirements, and clear guidance on when to stop and when to revisit earlier steps. Feedback loops are well-defined.
Progressive Disclosure	3/3	Well-organized with clear sections. References external skill (finishing-a-development-branch) appropriately with one-level-deep linking. Content is appropriately scoped for a SKILL.md overview without being monolithic.

Overall Assessment

This description fails to explain what the skill actually does, focusing only on when to use it. While it includes a 'Use when' clause, the lack of concrete actions and capabilities makes it difficult for Claude to understand what this skill provides. The description needs substantial improvement in specifying the actual functionality.

Suggestions

Add specific concrete actions the skill performs (e.g., 'Executes multi-step implementation plans by breaking them into reviewable chunks, tracking progress, and pausing at defined checkpoints')
Include natural trigger terms users would say such as 'run my plan', 'execute steps', 'checkpoint review', 'phased implementation'
Clarify what 'separate session' means and what distinguishes this from general task execution skills

Dimension	Score	Reasoning
Specificity	1/3	The description uses vague language like 'execute' and 'implementation plan' without specifying any concrete actions. It doesn't describe what the skill actually does - no verbs indicating specific capabilities.
Completeness	2/3	Has a 'Use when' clause addressing when to use it, but the 'what does this do' portion is essentially missing. The description only implies execution of plans without explaining the actual capabilities or actions performed.
Trigger Term Quality	2/3	Contains some relevant terms like 'implementation plan', 'execute', 'session', and 'review checkpoints' that users might mention, but lacks common variations and natural phrasing users would typically use.
Distinctiveness Conflict Risk	2/3	Terms like 'implementation plan' and 'review checkpoints' provide some specificity, but 'execute' and 'separate session' are generic enough to potentially overlap with other task execution or planning skills.