qodo-review-resolver

Read or resolve a pull request's Qodo review with the qodo CLI — fetch structured status, reviewed commit SHA, and findings for ANY PR as JSON, with optional extended details and citation evidence for audits, then optionally resolve open findings and record outcomes, once or until clean. Use this — never `gh`/`curl` scraping of review comments — for "is the review clean on PR

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%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.

The body is exceptionally actionable — exact commands, enums, error semantics, and a worked example — with a well-sequenced workflow and genuine validation checkpoints. Its weakness is token efficiency: heavy repetition of the same rules and inlined edge-case detail that should be offloaded to reference files.

Suggestions

State the "read the review via qodo, never scrape comments; forge metadata reads are fine" rule once (e.g. in Preflight or the Instructions blockquote) and reference it elsewhere instead of restating it in the Description, Watch-mode, and Configuration sections.

Move the qodo-not-on-PATH fallback and the sandbox auth diagnostic out of the Quick start into a dedicated references file (e.g. references/troubleshooting.md), keeping only a one-line pointer inline.

Consolidate the freshness guidance (commit_sha vs PR head) into the existing "Read the session state FIRST" section and drop its restatements in Two modes, Example, and Guardrails, which blur the mainline sequence.

Dimension	Reasoning	Score
Conciseness	The ~400-line body restates the "don't scrape comments but forge metadata is fine" rule four times (Description, Instructions blockquote, Watch-mode step 1, Configuration) and repeats the commit_sha/head freshness check in at least four places. The content is domain-specific rather than concepts Claude already knows, but the repetition is unnecessary padding that could be tightened.	3 / 5
Actionability	Quick-start block with exact commands and flags, concrete write commands with the --reason enum, a precise error taxonomy distinguishing terminal (not_found, conflict) from idempotent (reconciled: false) outcomes, and a fully worked end-to-end example — copy-paste ready throughout.	5 / 5
Workflow Clarity	Clear ordered pipeline (version gate → preflight → fetch → session-state-first check → present → triage → modes → resolve → record) with real validation checkpoints and feedback loops (freshness check before acting, per-finding results reads on batch writes, bounded watch loops). Held below 5 because overlapping sections and repeated restatements blur the mainline sequence.	4 / 5
Progressive Disclosure	One real, well-signaled one-level reference (references/skill-updates.md, linked once from the update-notice section), but the body inlines ~400 lines whose edge-case material (PATH fallback, sandbox auth diagnostic, extended-results schema detail) clearly belongs in separate reference files.	3 / 5
	Total	15 / 20 Passed

Description

96%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 highly specific, complete description with excellent natural-language trigger coverage and explicit what/when guidance. Its only weakness is that a handful of trigger phrases are generic enough to overlap with non-Qodo PR-review skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — fetch structured status, reviewed commit SHA, and findings as JSON, optional extended details with citation evidence, resolve open findings, record outcomes — in third-person voice, comprehensively covering the read and resolve paths.	5 / 5
Completeness	Explicitly answers both what the skill does (first sentence enumerates capabilities) and when to use it ("Use this — never gh/curl scraping — for ..." with concrete trigger phrases).	5 / 5
Trigger Term Quality	Ten quoted natural user phrasings spanning read, audit, fix, gate, and watch intents (e.g. "is the review clean on PR #N", "what did Qodo flag", "babysit this PR until it's clean"), covering synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The Qodo niche is clear and the anti-scraping boundary is drawn, but several trigger phrases ("check before merging", "fix the review findings", "resolve my PR review") are generic and could contend with general PR-review or merge-gate skills.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: qodo-ai/qodo-skills
Path: packages/qodo/skills/qodo-review-resolver/SKILL.md
Commit: 7f619ec

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.