qodo-pr-resolver
Use when the user wants to review Qodo PR feedback or fix code review comments. Capabilities: view issues by severity, apply fixes interactively or in batch, reply to inline comments, post fix summaries (GitHub, GitLab, Bitbucket, Azure DevOps, Gerrit)
81
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/qodo-pr-resolver/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 well-crafted skill description that clearly communicates both what the skill does and when to use it. It uses third-person voice, lists concrete capabilities, names specific platforms, and includes the distinctive 'Qodo' identifier that makes it easy to distinguish from other skills. The trigger terms are natural and comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: view issues by severity, apply fixes interactively or in batch, reply to inline comments, post fix summaries. Also specifies supported platforms (GitHub, GitLab, Bitbucket, Azure DevOps, Gerrit). | 3 / 3 |
Completeness | Explicitly answers both 'what' (view issues, apply fixes, reply to comments, post summaries) and 'when' ('Use when the user wants to review Qodo PR feedback or fix code review comments'). The 'Use when...' clause is present and clear. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'PR feedback', 'code review comments', 'Qodo', 'fix', 'issues', 'severity', 'inline comments', plus platform names. These cover the natural language users would use when dealing with PR review workflows. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Qodo' branding and the narrow focus on PR code review feedback workflows. The combination of Qodo + PR feedback + specific platforms creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
54%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity and progressive disclosure — the multi-step process is thoroughly documented with clear branching, validation, and error handling, and provider-specific details are well-delegated to reference files. However, it is extremely verbose, with extensive repetition (Gerrit notes in every step, repeated references to the same resource files) and over-explanation of concepts Claude could handle with much less guidance. The actionability suffers because nearly all concrete commands are deferred to external files, leaving the main skill body as mostly procedural prose.
Suggestions
Reduce verbosity by consolidating Gerrit-specific notes into a single 'Gerrit differences' section rather than repeating them in Steps 3, 6, 7, 8, and 9.
Simplify the severity mapping section — the current two detailed examples and multi-paragraph explanation could be replaced with a concise lookup table and one example.
Include at least the most common provider's (GitHub) concrete commands inline for key operations (fetch comments, post reply) rather than deferring everything to providers.md, so the skill is more self-contained and actionable.
Remove explanatory text that Claude doesn't need, such as 'Qodo (formerly Codium AI) is an AI-powered code review tool that analyzes PRs/MRs with compliance checks, bug detection, and code quality suggestions' — this context adds tokens without aiding task execution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines with significant redundancy. Many sections repeat information (e.g., Gerrit notes appear in nearly every step, the same provider.md references are repeated dozens of times). Concepts like how to check git status, what Qodo is, and how deduplication works are over-explained. The severity mapping section alone with its examples is excessively detailed for something Claude could infer from simpler rules. | 1 / 3 |
Actionability | The skill provides a detailed step-by-step workflow with specific tool names and git commands, but almost all concrete commands are deferred to external files (providers.md, gerrit.md). The main skill body contains very few executable commands — mostly just `git --version`, `git remote get-url origin`, and `git push`. The severity mapping and display format are concrete, but the core operations (fetching comments, posting replies, creating PRs) are all 'See [providers.md]'. | 2 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced with 10 clearly numbered steps, explicit branching scenarios (A/B/C), validation checkpoints (Step 3a wait/poll logic, Step 0 push status check), error recovery paths (timeout handling, failed replies), and clear decision points with AskUserQuestion options. The feedback loop for waiting on Qodo review with Monitor tool polling is well-specified. | 3 / 3 |
Progressive Disclosure | The skill effectively delegates provider-specific details to providers.md and gerrit.md with clear, well-signaled references using section anchors (e.g., '[providers.md § Find Open PR/MR]'). The main file serves as the workflow orchestrator while keeping implementation details one level deep. Navigation is clear and references are consistently formatted. | 3 / 3 |
Total | 9 / 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
- qodo-ai/qodo-skills
- Commit
8fb6b55
- 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.