gstack-openclaw-investigate
Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.
58
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/gstack-openclaw-investigate/SKILL.mdQuality
Discovery
54%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 description excels at trigger term coverage, providing a rich set of natural phrases users would say when needing debugging help. However, it is essentially all 'when' and no 'what'—it never describes the concrete actions or capabilities the skill provides (e.g., analyzing logs, tracing code paths, suggesting fixes). Adding specific capability descriptions would significantly improve it.
Suggestions
Add concrete capability descriptions at the start, e.g., 'Analyzes stack traces, traces code execution paths, identifies root causes, and suggests targeted fixes for software bugs.'
Specify the scope or domain more precisely (e.g., languages, frameworks, or types of systems) to reduce potential overlap with general coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists no concrete actions or capabilities—it only describes when to use the skill ('debug, fix a bug, investigate an error') but never says what the skill actually does (e.g., 'analyzes stack traces, sets breakpoints, traces code paths'). The verbs used are trigger conditions, not capability descriptions. | 1 / 3 |
Completeness | The 'when' is thoroughly covered with explicit trigger conditions, but the 'what does this do' is essentially absent. The description never explains what concrete steps or methods the skill employs to accomplish debugging tasks. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural user terms: 'debug', 'fix a bug', 'investigate an error', 'root cause analysis', 'errors', 'stack traces', 'unexpected behavior', 'stopped working'. These are all phrases users would naturally say when they need debugging help. | 3 / 3 |
Distinctiveness Conflict Risk | The debugging/error domain is reasonably specific, but without specifying what kind of debugging (e.g., language, environment, tooling), it could overlap with general coding assistance skills or language-specific troubleshooting skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
77%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 debugging skill with excellent workflow clarity and actionability. The phased approach with explicit validation checkpoints, escalation rules, and structured output format gives Claude clear, concrete guidance. Minor weaknesses include some motivational/explanatory text that doesn't add actionable value and the lack of progressive disclosure for reference material like pattern catalogs and report templates.
Suggestions
Trim motivational commentary (e.g., 'Fixing symptoms creates whack-a-mole debugging', 'there is no for now') to save tokens while keeping the actionable rules they support.
Extract the pattern analysis catalog (race conditions, nil propagation, etc.) into a separate PATTERNS.md reference file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and well-structured, but includes some unnecessary elaboration (e.g., 'Fixing symptoms creates whack-a-mole debugging' is motivational rather than instructional, and some pattern descriptions could be tighter). The red flags section and some commentary like 'there is no for now' add personality but consume tokens without adding actionable value. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific git commands, clear step-by-step processes, explicit output formats (root cause hypothesis, debug report), specific thresholds (3-strike rule, >5 files), and actionable completion statuses. The regression test criteria (fails without fix, passes with fix) are precise and copy-paste ready as a checklist. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (Phases 1-5), explicit validation checkpoints (reproduce before fixing, verify hypothesis before implementing, fresh verification after fix, run full test suite), and a well-defined feedback loop (hypothesis fails → return to Phase 1). The 3-strike rule provides a clear escalation path with concrete options. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear phases and sections, but it's a single monolithic file with no references to supporting materials. The pattern analysis section and debug report template could be split into separate reference files. For a skill of this length (~120 lines of substantive content), some progressive disclosure into bundle files would improve token efficiency. | 2 / 3 |
Total | 10 / 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
- garrytan/gstack
- Commit
19770ea
- 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.