autofix
Apply approved fixes for unresolved CodeRabbit review comments, Codex P1-P3 findings, PR feedback, and code review issues with validation evidence. Use when asked to address review comments, fix review findings, clear unresolved comments, or autofix PR feedback.
64
75%
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 ./Skills/agent-ops/autofix/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 its purpose, lists specific capabilities with named tools and severity levels, and includes an explicit 'Use when' clause with multiple natural trigger phrases. It is well-differentiated from other skills due to its focus on the specific workflow of fixing code review comments from named tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Apply approved fixes for unresolved CodeRabbit review comments, Codex P1-P3 findings, PR feedback, and code review issues with validation evidence.' These are concrete, named actions with specific tools and severity levels mentioned. | 3 / 3 |
Completeness | Clearly answers both 'what' (apply approved fixes for unresolved CodeRabbit review comments, Codex findings, PR feedback, code review issues with validation evidence) and 'when' (explicit 'Use when' clause with multiple trigger scenarios: address review comments, fix review findings, clear unresolved comments, autofix PR feedback). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'review comments', 'fix review findings', 'unresolved comments', 'autofix PR feedback', 'CodeRabbit', 'Codex', 'P1-P3'. These cover multiple natural variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool names (CodeRabbit, Codex), severity levels (P1-P3), and a clear niche around applying fixes for code review findings. Unlikely to conflict with general coding or documentation skills due to the specificity of the review-fix workflow. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive framework for handling PR review autofixes with good safety boundaries and clear scope definitions. Its main weaknesses are the lack of concrete, executable examples (no actual CLI commands, API calls, or code snippets) and some redundancy across sections like Constraints, Gotchas, Anti-Patterns, and Failure mode. The workflow is well-structured conceptually but would benefit from specific validation commands and explicit feedback loops.
Suggestions
Add concrete, executable examples for key workflow steps — e.g., actual CodeRabbit CLI commands for inventory, specific GitHub API calls for fetching review threads, and exact validation commands with expected output formats.
Consolidate overlapping sections (Constraints, Gotchas, Anti-Patterns, Failure mode) to reduce redundancy and improve token efficiency — for instance, merge Anti-Patterns into Constraints and Failure mode into Validation.
Add an explicit feedback loop in the workflow (e.g., 'If validation fails: inspect error → fix → re-validate → only proceed when all gates pass') rather than leaving it implicit.
Make the Outputs section actionable by providing a concrete JSON schema or example output structure rather than a comma-separated list of field names.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some redundancy (e.g., the 'Inputs' and 'Outputs' sections are vague lists that don't add much actionable value, and several sections like 'Failure mode' and 'Anti-Patterns' overlap with 'Constraints' and 'Gotchas'). Some content like the Discovery Interview section explains general interviewing principles Claude already knows. | 2 / 3 |
Actionability | The workflow provides a clear sequence of steps and the constraints are specific, but there are no concrete code examples, exact CLI commands, or copy-paste-ready snippets. Guidance like 'Inventory CodeRabbit via CodeRabbit CLI/plugin first' and 'run the smallest command or test' remains abstract without showing actual commands or API calls. | 2 / 3 |
Workflow Clarity | The 11-step workflow is well-sequenced and includes validation steps and failure-mode handling ('stop and report the blocker'). However, the validation section lacks specific commands or concrete checkpoints, and the feedback loop for fix-validate-retry is only implicitly present rather than explicitly structured with clear decision points. | 2 / 3 |
Progressive Disclosure | The skill references multiple external files (references/discovery-interview.md, references/contract.yaml, references/evals.yaml, Infrastructure/references/) with a dedicated Progressive Disclosure section. However, no bundle files were provided to verify these references exist, and some referenced paths are deeply nested (Infrastructure/references/deferred-skill-context/agent-ops-autofix/), suggesting potential multi-level navigation issues. | 2 / 3 |
Total | 8 / 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
- 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.