he-fix-bugs
Restore broken behavior by reproducing failures, identifying root cause, and delivering verified fixes. Use when the user needs regression debugging, incident triage, or bug repair from tracker or direct reports.
62
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-fix-bugs/SKILL.mdQuality
Discovery
77%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 solid description that clearly communicates both what the skill does and when to use it, with a well-structured 'Use when' clause. Its main weakness is that trigger terms lean toward formal/process terminology ('regression debugging', 'incident triage') rather than the more casual language users might naturally use ('fix this bug', 'something broke'). The scope is also broad enough that it could overlap with general debugging or code-fixing skills.
Suggestions
Add more natural user-facing trigger terms like 'fix bug', 'something broke', 'not working', 'error', 'crash', or 'failing test' to improve keyword coverage.
Consider narrowing the scope or adding distinguishing details (e.g., specific tools, languages, or methodologies) to reduce potential overlap with general debugging or code-fixing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'reproducing failures', 'identifying root cause', and 'delivering verified fixes'. These are distinct, actionable steps in a debugging workflow. | 3 / 3 |
Completeness | Clearly answers both what ('reproducing failures, identifying root cause, delivering verified fixes') and when ('Use when the user needs regression debugging, incident triage, or bug repair from tracker or direct reports') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'regression debugging', 'incident triage', 'bug repair', 'tracker', and 'direct reports', but misses common natural user phrases like 'fix bug', 'broken', 'not working', 'error', 'crash', 'issue', or 'defect'. | 2 / 3 |
Distinctiveness Conflict Risk | The scope of 'bug repair' and 'incident triage' is fairly broad and could overlap with general coding/debugging skills. However, the emphasis on 'reproducing failures', 'regression debugging', and 'tracker' reports provides some distinctiveness. It could still conflict with a general code-fixing or troubleshooting skill. | 2 / 3 |
Total | 10 / 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 is a well-structured process-oriented skill with strong workflow clarity and excellent progressive disclosure via conditional 'Read when' references. Its main weaknesses are moderate verbosity (some redundancy between sections) and a lack of concrete executable examples—no sample Linear payloads, log commands, or test templates are provided, which limits actionability for an otherwise thorough debugging workflow.
Suggestions
Add at least one concrete example of a Linear issue payload or root-cause analysis output to make the Outputs section actionable and copy-paste ready.
Include a concrete example command for log evidence collection (e.g., a grep/tail command for [ERROR] markers) to strengthen actionability in step 4.
Consolidate the 'Full Context' and 'Subagent Routing' sections to eliminate duplicated references (e.g., subagent-routing.md appears in both) and improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some redundancy (e.g., 'Subagent Routing' section partially duplicates 'Full Context' references, and some constraints/anti-patterns overlap). Several bullet points could be tightened, and the 'Progressive Disclosure Entry' header and preamble add little value. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The procedure provides a clear ordered sequence of steps and the constraints are specific, but there are no concrete code examples, commands, or copy-paste-ready snippets. The guidance is specific enough to follow but remains at the level of process instructions rather than executable actions (e.g., no example Linear issue payload, no example log grep command, no test template). | 2 / 3 |
Workflow Clarity | The 9-step procedure is clearly sequenced with explicit validation gates (reproduce before diagnosing, diagnose before fixing, verify before marking fixed). The Validation section provides explicit checkpoints including a 'fail fast' directive. Feedback loops are present (e.g., step 7's hypothesis testing with prediction/falsification, step 8's present-before-remediate gate). | 3 / 3 |
Progressive Disclosure | The skill explicitly positions itself as a 'Progressive Disclosure Entry' with a concise overview and well-signaled one-level-deep references to canonical contracts, eval cases, task profiles, domain model routing, QA intake routing, and runtime evidence intake. Each reference includes 'Read when' conditions that help Claude decide when to load additional context. | 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
4c78f98
- 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.