delegation-check
Check workflow delegation prompts against agent role definitions for content separation violations. Detects conflicts, duplication, boundary leaks, and missing contracts. Triggers on "check delegation", "delegation conflict", "prompt vs role check".
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/delegation-check/SKILL.mdQuality
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 a strong skill description that clearly defines a specific niche (delegation prompt validation against agent roles), lists concrete detection capabilities (conflicts, duplication, boundary leaks, missing contracts), and provides explicit trigger terms. The description is concise, uses third-person voice, and would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: checking delegation prompts against role definitions, detecting conflicts, duplication, boundary leaks, and missing contracts. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (checks workflow delegation prompts against agent role definitions for content separation violations, detects conflicts/duplication/boundary leaks/missing contracts) and 'when' (explicit triggers: 'check delegation', 'delegation conflict', 'prompt vs role check'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms like 'check delegation', 'delegation conflict', 'prompt vs role check', plus domain-specific terms like 'workflow delegation prompts', 'agent role definitions', 'boundary leaks', and 'missing contracts' that users in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focusing specifically on delegation prompt validation against agent role definitions. The combination of 'delegation', 'agent role definitions', 'content separation violations', and 'boundary leaks' creates a very specific domain unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill defines a thorough and well-structured delegation conflict checking process with clear sequencing and comprehensive coverage of 7 conflict dimensions. However, it is significantly over-verbose—much of the content (block type tables, section parsing guides, pattern lists) could be condensed or moved to reference files. The actionability is moderate: while grep commands and output templates are concrete, the core analysis logic remains descriptive rather than executable.
Suggestions
Reduce inline content by 50%+: move the 7 dimension definitions to a separate reference file (e.g., `dimensions.md`) and keep only a summary table in SKILL.md with dimension name, one-line description, and severity levels.
Remove explanatory tables like 'Block | What It Contains' and 'Section | Key Content' — Claude can parse XML tags and markdown sections without being told what they contain.
Add executable code snippets for the core analysis logic (e.g., a concrete bash/python script for detecting role re-definition patterns) rather than just listing what to scan for in prose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It over-explains parsing structures, block definitions, and detection patterns that Claude could infer from much shorter descriptions. Tables like 'Block | What It Contains' and 'Section | Key Content' enumerate things Claude already understands. The 7 dimensions each contain extensive prose that could be condensed significantly. | 1 / 3 |
Actionability | The skill provides concrete grep commands and structured output formats, but much of the guidance is descriptive rather than executable. The 'parse delegation prompts' and 'run conflict checks' sections describe what to look for conceptually but lack executable code for the actual analysis logic. The pair map and reporting are pseudocode/templates rather than copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | The 7-step process is clearly sequenced from scope determination through discovery, parsing, conflict checking, aggregation, and reporting. Each step has explicit inputs and outputs. The verdict system (CLEAN/REVIEW/CONFLICT) provides clear decision points, and the fix priority section creates a feedback loop for remediation. The success criteria checklist at the end serves as validation. | 3 / 3 |
Progressive Disclosure | The skill references `separation-rules.md` as required reading, which is good progressive disclosure. However, the massive amount of inline content (all 7 dimension definitions, all parsing tables, full report templates) should be split into separate reference files. The monolithic structure makes this hard to navigate despite having clear section headers. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
227244f
- 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.