executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
50
55%
Does it follow best practices?
Impact
44%
1.69xAverage score across 8 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/executing-plans/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily weighted toward the 'when' but almost entirely neglects the 'what'. It fails to describe any concrete actions or capabilities, making it difficult for Claude to understand what this skill actually does. The trigger terms are somewhat relevant but not comprehensive enough to reliably match user intent.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Breaks an implementation plan into discrete steps, executes each step sequentially, and pauses at defined review checkpoints for user approval before continuing.'
Expand trigger terms to include natural phrases users might say, such as 'execute plan', 'run through steps', 'phased implementation', 'step-by-step execution', 'multi-step task'.
Clarify the domain or context — is this for code implementation, infrastructure changes, document creation, or general task execution? Specificity here would reduce conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not list any concrete actions. 'Execute' an 'implementation plan' is extremely vague — it doesn't say what kind of plan, what domain, or what specific operations are performed. There are no concrete capabilities described. | 1 / 3 |
Completeness | It has a 'Use when...' clause addressing when to use the skill, but the 'what does this do' part is essentially absent — it only says to 'execute' a plan with 'review checkpoints' without explaining what the skill actually does or how it works. | 2 / 3 |
Trigger Term Quality | It includes some relevant terms like 'implementation plan', 'review checkpoints', and 'separate session', which could match certain user requests. However, these are somewhat niche and miss common variations users might say (e.g., 'execute plan', 'step-by-step', 'multi-step task', 'phased execution'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'separate session' and 'review checkpoints' provides some distinctiveness, but 'implementation plan to execute' is broad enough to overlap with many coding, project management, or task execution skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid orchestration/workflow skill that clearly sequences a plan execution process with good stop conditions and cross-references to related skills. Its main weakness is the lack of concrete examples (what does a plan file look like? what does a TodoWrite call look like?) and some redundancy between the process steps and the 'Remember' summary section.
Suggestions
Add a brief concrete example showing what a plan file looks like and how to create a TodoWrite from it, so Claude knows the expected format.
Remove or significantly trim the 'Remember' section since it mostly restates guidance already covered in the process steps and stop conditions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy - the 'Remember' section largely repeats guidance already stated in the process steps and 'When to Stop' sections. The note about subagents is useful but slightly verbose. | 2 / 3 |
Actionability | Provides a clear process with specific steps but lacks concrete examples - no example plan format, no example TodoWrite usage, no specific commands. It's instructional rather than executable, relying heavily on references to other skills without showing what actual execution looks like. | 2 / 3 |
Workflow Clarity | Clear three-step sequence with explicit validation checkpoints (run verifications, mark as completed), well-defined stop conditions, and feedback loops (stop when blocked, return to review when plan updates). The 'When to Stop' and 'When to Revisit' sections provide excellent error recovery guidance. | 3 / 3 |
Progressive Disclosure | Well-structured overview with clear references to related skills (writing-plans, finishing-a-development-branch, using-git-worktrees). Content is appropriately scoped - this skill covers execution while pointing to other skills for adjacent concerns. References are one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- obra/superpowers
- Commit
b7a8f76
- Reviewed
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.