CtrlK
BlogDocsLog inGet started
Tessl Logo

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)

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, well-sequenced workflow with strong validation and feedback loops for a batch/destructive operation. The main weaknesses are repeated oscillation-guard explanations that inflate length and referenced resource files that are absent from the bundle.

Suggestions

Consolidate the oscillation/convergence guard logic into a single description (e.g. in convergence.md) and reference it from Steps 6, 7, and 8 instead of restating the tagged-issue handling each time.

Include the referenced bundle files (resources/providers.md, resources/gerrit.md, resources/convergence.md) so the well-signaled one-level-deep references actually resolve.

Tighten the 'Understanding Qodo Reviews' taxonomy section by moving the shield.io badge slug parsing detail into a reference file, keeping only the rendering rule inline.

DimensionReasoningScore

Conciseness

The 423-line body is mostly necessary domain-specific procedure rather than general-knowledge padding, but the oscillation/convergence guard logic is restated across Steps 3c, 6, 7, and 8 and could be consolidated into one reference.

3 / 5

Actionability

Provides many concrete, executable commands (git diff --name-only, git commit --amend --no-edit, git push origin HEAD:refs/for/<target-branch>) and exact tool parameters, but a sizable portion of provider-specific commands is delegated to resources files that are not present, leaving gaps.

4 / 5

Workflow Clarity

Steps 0 through 10 are explicitly sequenced with validation checkpoints and feedback loops: push-status checks, the Monitor polling loop with || true resilience, AskUserQuestion approval gates, and the oscillation hard-stop, satisfying the destructive/batch validation requirement.

5 / 5

Progressive Disclosure

SKILL.md is a well-structured overview with clearly signaled, one-level-deep references (providers.md, gerrit.md, convergence.md) and descriptive anchors, but none of the referenced resource files exist in the bundle, partially breaking navigation.

4 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both capabilities and an explicit Use-when trigger, scoped tightly to Qodo PR resolution. Minor gaps in action specificity and synonym coverage keep specificity and trigger_term_quality at 4 rather than 5.

DimensionReasoningScore

Specificity

"view issues by severity, apply fixes interactively or in batch, reply to inline comments, post fix summaries" lists several concrete actions with a multi-provider list, but "view issues by severity" is slightly generic, leaving minor coverage gaps short of fully comprehensive.

4 / 5

Completeness

Explicitly answers both what (the Capabilities list) and when ("Use when the user wants to review Qodo PR feedback or fix code review comments") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users say ("review Qodo PR feedback", "fix code review comments") with good keyword coverage, but omits synonyms like PR/MR and has no file extensions, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

The Qodo-specific niche ("Qodo PR feedback", "code review comments" plus named providers) gives it distinct triggers with minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 25 missing

Warning

Total

14

/

16

Passed

Repository
qodo-ai/qodo-skills
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.