how-to-delegate
Scientific delegation framework for orchestrators — provide observations and success criteria while preserving agent autonomy. Use when assigning work to sub-agents, before invoking the Agent tool, or when preparing delegation prompts for specialist agents.
89
Quality
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-crafted description with strong completeness and distinctiveness. It clearly identifies its niche (multi-agent delegation) and provides explicit trigger conditions. The main weakness is that the specific capabilities could be more concrete—listing actual actions like 'structure task prompts', 'define acceptance criteria', or 'scope agent boundaries' would strengthen specificity.
Suggestions
Add 2-3 more concrete actions to improve specificity, e.g., 'structure task prompts, define acceptance criteria, scope agent boundaries'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('scientific delegation framework for orchestrators') and mentions some actions ('provide observations and success criteria', 'preserving agent autonomy'), but lacks concrete specific actions like examples of what observations or criteria look like. | 2 / 3 |
Completeness | Clearly answers both what ('Scientific delegation framework... provide observations and success criteria while preserving agent autonomy') and when ('Use when assigning work to sub-agents, before invoking the Agent tool, or when preparing delegation prompts'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'sub-agents', 'Agent tool', 'delegation prompts', 'specialist agents', 'orchestrators'. These are terms someone working with multi-agent systems would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting multi-agent orchestration and delegation. The explicit mention of 'Agent tool', 'sub-agents', and 'orchestrators' creates a clear, distinct trigger space unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured delegation framework with excellent workflow clarity and actionability. The 10-step process with verification checkpoints and concrete templates makes it highly usable. The main weakness is moderate verbosity—the repeated 'Why' explanations and some redundant guidance could be trimmed to improve token efficiency.
Suggestions
Consolidate the 'Why' explanations into a single 'Core Principles' section at the top rather than repeating rationale after each step
Remove redundant statements about not pre-gathering data (mentioned in principles, Step 3, Step 8, and Step 10)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some redundancy with repeated 'Why' explanations for each step and verbose template structures. While the content is relevant, it could be tightened—Claude doesn't need explanations like why pre-gathering is bad repeated multiple times. | 2 / 3 |
Actionability | Highly actionable with concrete templates, specific checkboxes, exact prompt structures to copy, and clear Agent tool invocation syntax. Each step has explicit ACTION directives with fill-in-the-blank examples. | 3 / 3 |
Workflow Clarity | Excellent 10-step sequential workflow with explicit verification checkpoint (Step 8), conditional execution flowchart, and final pre-flight checklist (Step 10). Clear feedback loop for validation before delegation. | 3 / 3 |
Progressive Disclosure | Well-structured with clear reference to external agent-orchestration skill at the top, mermaid diagrams for visual flow, and logical section organization. Content is appropriately self-contained while pointing to related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
fd243f9
- 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.