executing-plans
Coordinates batch execution of a written implementation plan by spawning implementer and reviewer teammates, executing tasks in batches with automated review gates, and pausing for human feedback between batches. Use when handed a plan file to execute, resuming plan work in a new session, or running a standalone plan outside the brainstorming flow. DO NOT TRIGGER for same-session execution after brainstorming — use kit:team-dev instead.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is an excellent skill description that clearly articulates specific capabilities (batch execution with spawning teammates, review gates, human feedback pauses), provides explicit trigger conditions with a 'Use when' clause covering three scenarios, and proactively disambiguates from a related skill with a negative trigger. The description is concise yet comprehensive, using third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'spawning implementer and reviewer teammates', 'executing tasks in batches with automated review gates', 'pausing for human feedback between batches'. These are detailed, concrete operational steps. | 3 / 3 |
Completeness | Clearly answers both 'what' (coordinates batch execution by spawning teammates, executing in batches with review gates, pausing for feedback) and 'when' (explicit 'Use when' clause with three trigger scenarios plus a negative trigger for disambiguation). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms like 'plan file', 'execute', 'resuming plan work', 'new session', 'batch execution', 'implementation plan'. Also includes a negative trigger ('DO NOT TRIGGER for same-session execution after brainstorming') which helps disambiguation. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit negative trigger ('DO NOT TRIGGER for same-session execution after brainstorming — use kit:team-dev instead') that directly addresses potential conflict with a sibling skill. The specific niche of cross-session plan execution with batch coordination is clearly carved out. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured multi-step workflow with good validation checkpoints and clear sequencing, which is its strongest aspect. However, it lacks concrete executable examples (no actual tool invocation syntax) and contains some redundancy between the Remember section and the main workflow steps. The actionability would benefit significantly from showing actual command/message formats rather than describing them abstractly.
Suggestions
Add concrete examples of actual tool invocations — e.g., show the exact SendMessage format for assigning a task to an implementer, or the team creation command syntax
Remove or significantly trim the 'Remember' section since most points are already stated in the workflow steps — keep only truly novel reminders like the branch/commit rules
Consolidate 'When to Stop and Ask for Help' and 'When to Revisit Earlier Steps' into a single concise section or integrate these conditions directly into the relevant workflow steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the 'When to Use' section repeats information from the description/frontmatter, 'Remember' section largely restates points already made in the workflow steps, and some guidance like 'Ask for clarification rather than guessing' is unnecessary for Claude. | 2 / 3 |
Actionability | Provides a clear process with named steps and references to specific skills/tools, but lacks concrete executable examples — no actual command syntax for SendMessage, TaskUpdate, or team creation. The instructions are procedural but remain at a descriptive level rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints (automated review gate in Step 4, human review in Step 5), feedback loops (Step 6 for fixes), and clear stop conditions. The 'When to Stop' and 'When to Revisit' sections provide good error recovery guidance. | 3 / 3 |
Progressive Disclosure | References external skills clearly in the Integration section with one-level-deep links, but the main content could benefit from better organization — the 'Remember' section is a flat list that duplicates earlier content, and the 'When to Stop' and 'When to Revisit' sections could be consolidated. No overly long inline content, but structure is merely adequate. | 2 / 3 |
Total | 9 / 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
- shousper/claude-kit
- Commit
a01bac9
- 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.