Diagnostic and repair workflow that analyzes error logs, traces root causes, implements fixes, and verifies with regression tests. Use when fixing bugs, debugging runtime errors or exceptions, investigating test failures or crashes, or submitting bug-fix pull requests. Activated by commands: /unattended, /assess, /diagnose, /reproduce, /fix, /test, /review, /document, /pr, /feedback, /start.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 articulates what the skill does (diagnostic and repair workflow with specific steps) and when to use it (debugging, bug-fixing, test failures). The inclusion of both natural language trigger terms and explicit slash commands provides excellent discoverability. The description is concise yet comprehensive, covering the full workflow from diagnosis through PR submission.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'analyzes error logs', 'traces root causes', 'implements fixes', 'verifies with regression tests'. Also enumerates specific workflow commands. | 3 / 3 |
Completeness | Clearly answers both 'what' (diagnostic and repair workflow that analyzes error logs, traces root causes, implements fixes, verifies with regression tests) and 'when' (explicit 'Use when...' clause covering bugs, debugging, test failures, crashes, and bug-fix PRs, plus activation commands). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'fixing bugs', 'debugging', 'runtime errors', 'exceptions', 'test failures', 'crashes', 'bug-fix pull requests'. Also lists explicit slash commands as triggers. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to bug diagnosis and repair workflows with distinct triggers like error logs, root cause tracing, and specific slash commands. Unlikely to conflict with general coding, testing, or documentation skills. | 3 / 3 |
Total | 12 / 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 well-structured orchestrator skill that provides clear workflow sequencing, concrete examples with real commands and artifact templates, and good progressive disclosure to sub-skills. The main weakness is moderate redundancy between the example session, the phases list, and the /diagnose example appearing in two forms, which could be tightened to save tokens.
Suggestions
Consolidate the /diagnose example — it appears both in the Quick Start section and as a standalone example; merge into one location to reduce redundancy.
The Phases list and Example Session convey overlapping information; consider combining them into a single section that shows both the phase names and their outputs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy — the example session and the phases list overlap significantly, and the /diagnose example is shown twice (once in Quick Start area and once as a standalone example). Some tightening is possible. | 2 / 3 |
Actionability | Provides concrete, executable commands (mkdir, rg, git blame, git log), a complete artifact template with realistic content, and specific file paths. The example session shows exactly what each phase produces. | 3 / 3 |
Workflow Clarity | Clear phase sequencing with explicit exit criteria for each phase, feedback loops (test fail → return to /fix, review inadequate → return to /diagnose or /fix), and validation checkpoints. The phase transitions section is well-defined with specific conditions for proceeding. | 3 / 3 |
Progressive Disclosure | Excellent structure: SKILL.md serves as an overview with clear one-level-deep references to skills/controller.md, skills/diagnose.md, skills/unattended.md, commands/{command}.md, and guidelines.md. Content is appropriately split between overview and detailed phase files. | 3 / 3 |
Total | 11 / 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.
81213f2
Table of Contents
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.