executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
51
55%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 skewed toward the 'when' and almost entirely neglects the 'what'. It provides no concrete actions or capabilities, making it difficult for Claude to understand what the skill actually does. The trigger terms are somewhat relevant but not comprehensive, and the lack of specificity creates moderate conflict risk with other execution-oriented skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Breaks down implementation plans into discrete steps, executes code changes incrementally, and pauses at defined review checkpoints for user approval.'
Include natural trigger terms users might say, such as 'execute plan', 'step-by-step implementation', 'phased coding', 'checkpoint-based execution', or 'multi-step task'.
Clarify what 'separate session' means and what domain this applies to (e.g., code implementation, infrastructure changes, document creation) to improve distinctiveness.
| 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 the 'when' question, but the 'what does this do' part is essentially absent. The description tells Claude when to use it but never explains what the skill actually does beyond vaguely 'executing a plan'. | 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' adds 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 well-structured workflow orchestration skill with clear sequencing and good stop/escalation conditions. Its main weakness is the lack of concrete, executable examples—there's no sample plan format, no example TodoWrite call, and no illustration of what a task execution cycle looks like in practice. Some content in the 'Remember' section is redundant with the main process steps.
Suggestions
Add a 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 consolidate the 'Remember' section since it mostly restates guidance from the process steps, improving conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy. The 'Remember' section largely repeats guidance already stated in the process steps. The note about subagents is useful but slightly verbose. The 'When to Revisit Earlier Steps' section adds little value. | 2 / 3 |
Actionability | Provides a clear process structure with concrete steps, but lacks executable examples. There are no code commands, no example plan file format, no example TodoWrite usage, and no concrete examples of what 'review critically' means in practice. The skill relies heavily on references to other skills without showing what the actual execution looks like. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (Load → Execute → Complete) with explicit validation checkpoints (run verifications, mark as completed), clear stop conditions, and feedback loops (stop when blocked, return to review when plan updates). The 'When to Stop' and 'When to Revisit' sections provide good error recovery guidance. | 3 / 3 |
Progressive Disclosure | The skill is well-organized as an overview that references three other skills (using-git-worktrees, writing-plans, finishing-a-development-branch) at one level deep with clear signaling. The Integration section cleanly lists dependencies. For a skill of this size with no bundle files, the structure is appropriate. | 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
f2cbfbe
- 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.