debug-orchestrator
Use when facing complex, multi-layered debugging issues that require coordinated investigation across different domains (frontend, backend, database, network, etc). Spawns specialized debug expert agents to handle specific aspects of the investigation.
74
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/product-design/skills/debug-orchestrator/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively communicates when to use the skill (complex multi-domain debugging) and its unique approach (spawning specialized agents). However, it lacks specific concrete actions and natural trigger terms users would actually say when encountering bugs. The description would benefit from more user-facing language and explicit capability examples.
Suggestions
Add natural trigger terms users would say: 'bug', 'error', 'crash', 'not working', 'broken', 'fix', 'investigate issue'
Include specific concrete actions: 'analyze stack traces', 'trace API calls', 'inspect logs', 'correlate errors across services'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (debugging) and mentions spawning specialized agents across domains (frontend, backend, database, network), but lacks concrete actions like 'analyze stack traces', 'trace API calls', or 'inspect database queries'. | 2 / 3 |
Completeness | Explicitly answers both what ('Spawns specialized debug expert agents to handle specific aspects') and when ('Use when facing complex, multi-layered debugging issues that require coordinated investigation'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'debugging', 'frontend', 'backend', 'database', 'network', but misses common user phrases like 'bug', 'error', 'crash', 'not working', 'broken', or 'fix'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'multi-layered' and 'coordinated investigation' qualifiers help distinguish from simple debugging, but 'debugging issues' is broad enough to potentially conflict with single-domain debug skills. | 2 / 3 |
Total | 9 / 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 skill provides comprehensive orchestration guidance with excellent workflow clarity and good progressive disclosure. However, it suffers from verbosity in explaining when to use/not use the skill, and the actionability is limited by pseudocode rather than executable commands for agent spawning. The content would benefit from trimming explanatory sections and providing actual tool invocation syntax.
Suggestions
Remove or significantly condense the 'When to Use' and 'Do NOT Use For' sections - Claude can infer appropriate usage from the skill description
Replace pseudocode bash blocks with actual tool invocation syntax (e.g., actual Task tool parameters or command format)
Consolidate the 'Usage Pattern' and 'Workflow Example' sections to reduce redundancy while maintaining the concrete example
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places. The 'When to Use' and 'Do NOT Use For' sections explain concepts Claude can infer. The extensive tables and examples, while helpful, could be more condensed. | 2 / 3 |
Actionability | Provides structured guidance and markdown templates, but lacks truly executable code. The 'bash' block is pseudocode describing intent rather than actual commands. Agent spawning syntax is illustrative rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | Excellent workflow structure with clear phases (Analysis → Selection → Protocol → Synthesis). Includes both parallel and sequential execution patterns, explicit output format expectations, and a complete workflow example demonstrating the full process. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and appropriate references to external examples in `examples/` directory. Content is structured from overview to details without deep nesting. Tables provide quick reference without overwhelming. | 3 / 3 |
Total | 10 / 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
- jpoutrin/product-forge
- Commit
0ebe7ae
- 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.