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 only provides a 'when' clause without explaining what the skill actually does, leaving the 'what' dimension almost entirely empty. The trigger terms are somewhat relevant but not comprehensive, and the lack of concrete actions makes it hard to distinguish from other execution-oriented skills. It needs a clear statement of capabilities and more natural trigger keywords.
Suggestions
Add a concrete 'what' statement listing specific actions, e.g., 'Executes multi-step implementation plans by writing code, creating files, and making changes according to a predefined plan.'
Include more natural trigger terms users might say, such as 'execute plan', 'run implementation', 'continue building', 'follow the plan', 'step-by-step coding'.
Clarify what 'review checkpoints' means in practice—e.g., 'Pauses at defined checkpoints for user review before proceeding to the next phase.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions—it doesn't say what the skill actually does (e.g., write code, generate files, refactor). 'Execute' and 'review checkpoints' are vague and abstract. | 1 / 3 |
Completeness | It provides a 'Use when...' clause addressing when to use the skill, but the 'what does this do' part is essentially absent—there is no description of the skill's capabilities or actions. | 2 / 3 |
Trigger Term Quality | Terms like 'implementation plan', 'separate session', and 'review checkpoints' are somewhat relevant but niche. Users are more likely to say things like 'execute my plan', 'run the next step', or 'continue implementation', which are not covered. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'written implementation plan', 'separate session', and 'review checkpoints' provides some distinctiveness, but 'execute an implementation plan' is broad enough to overlap with general coding, task execution, or project management 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 orchestration skill with clear workflow sequencing and good stop/escalation conditions. Its main weakness is moderate verbosity with some repeated guidance (the 'Remember' section echoes earlier content) and a lack of concrete executable examples—though as a process-coordination skill rather than a code skill, the absence of code is partially justified. The progressive disclosure and workflow clarity are strong.
Suggestions
Remove or significantly trim the 'Remember' section since it largely duplicates guidance already provided in the process steps above it.
Add a brief concrete example showing what a plan file looks like and how TodoWrite should be structured, to make the skill more actionable.
| 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 and the announcement lines add some overhead, though they serve a purpose. | 2 / 3 |
Actionability | Provides a clear process with concrete steps (load plan, use TodoWrite, mark tasks), but lacks executable examples. No concrete code or commands are shown—it's all procedural instruction. The references to sub-skills are specific but the skill itself relies heavily on external skills for actual execution details. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (Load/Review → Execute → Complete) with explicit validation checkpoints ('run verifications as specified'), clear stop conditions for blockers, and feedback loops (return to Step 1 when plan updates). The 'When to Stop' and 'When to Revisit' sections provide excellent error recovery guidance. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and appropriate references to external skills (using-git-worktrees, writing-plans, finishing-a-development-branch). The Integration section provides a clean one-level-deep reference map. For a skill with no bundle files, the structure is appropriately concise with clear navigation to related skills. | 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
- lucianghinda/superpowers-ruby
- Commit
c037ce3
- 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.