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".
62
73%
Does it follow best practices?
Impact
—
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, and provides explicit trigger terms. It effectively communicates both what the skill does and when it should be activated, with terminology distinct enough to avoid conflicts with other skills.
| 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 clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (check workflow delegation prompts against agent role definitions for content separation violations, detect conflicts/duplication/boundary leaks/missing contracts) and when (explicit 'Triggers on' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms like 'check delegation', 'delegation conflict', 'prompt vs role check', plus domain-specific terms like 'content separation violations', 'boundary leaks', and 'missing contracts' that users in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche around delegation prompt validation against agent role definitions. The combination of 'delegation', 'agent role definitions', 'content separation violations', and 'boundary leaks' creates a very distinct profile 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 has excellent workflow structure with a clear 7-step process, well-defined verdict system, and good output formatting. However, it is significantly over-verbose — the 7 conflict dimensions alone consume the majority of the document and could be compressed or split into a referenced file. The actionability is moderate: while the workflow is clear, the actual conflict detection relies on prose descriptions rather than executable logic.
Suggestions
Compress the 7 conflict dimensions into a compact reference table (dimension | what to scan for | severity rules) and move detailed examples/exceptions to a separate specs file like `conflict-dimensions.md`.
Replace prose-based detection descriptions with concrete executable patterns — e.g., provide actual regex patterns for role re-definition detection, or a script that performs the dimension checks.
Remove the 'Block | What It Contains' table in Step 3 — Claude can infer XML tag semantics from context; instead just list the tag names to extract.
Move the detailed output format template (the ASCII box report) to a separate `report-template.md` file to reduce main skill length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It over-explains parsing structures, block definitions, and detection patterns that Claude could infer from concise rules. Tables like 'Block | What It Contains' and extensive anti-pattern lists add significant token overhead. The 7 dimensions each contain repetitive structure (Question/Check/Allowed/Severity) that could be compressed into a compact table. | 1 / 3 |
Actionability | The skill provides some concrete guidance (grep commands for discovery, structured output format) but most of the 'checking' logic is described abstractly rather than with executable code. The conflict detection dimensions describe what to look for in prose but don't provide concrete parsing scripts or executable validation logic. The grep examples are useful but insufficient for the full workflow. | 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. The success criteria checklist serves as a validation checkpoint. The AskUserQuestion fallback for ambiguous scope is a good feedback loop. | 3 / 3 |
Progressive Disclosure | The skill references `@.claude/skills/delegation-check/specs/separation-rules.md` in required_reading, which is good progressive disclosure. However, no bundle files were provided to verify this reference exists. The main content is monolithic — the 7 conflict dimensions and their detailed checks could be split into a separate reference file, keeping the SKILL.md as an overview with the workflow and linking to dimension details. | 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
5ff5e86
- 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.