PR State Diagnostics

VerifiedSafe

This skill reads the data/state.json file and produces a dashboard of all tracked pull requests, including status distribution, error entries, skipped PRs, and anomalies. It also supports detailed diagnosis of individual PRs by identifier to show full state information. It helps quickly identify stuck, errored, or stale PRs in an automated review system.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#pr-diagnostics#state-analysis#error-tracking#anomaly-detection

Recommended for

Automated summary

Reads and analyzes a state.json file to provide a dashboard of tracked pull request statuses, errors, skipped PRs, and anomalies.

Strengths

  • Provides a quick overview of PR status distribution
  • Highlights errors and stuck entries
  • Detects anomalies like stale reviews or missing tracking IDs
  • Supports both summary and single-PR analysis

Limitations

  • Requires the state.json file to exist and be in V2 format
  • Cannot analyze PRs not yet tracked
  • Assumes default config values if config.yaml is not available
When to use it

Use when you need to quickly assess the health of a code review bot's tracking state or debug a specific PR's status.

When not to use it

Do not use if you need to modify state or perform actions; this is a read-only diagnostic tool.

Security analysis

Safe
Quality score92/100

The skill only reads local state and configuration files, performs analysis, and outputs diagnostic information. It does not execute any external commands, access secrets, or perform destructive actions.

No concerns found

How this analysis is made

Examples

Overall PR status dashboard
diagnose-state
Diagnose a specific PR
diagnose-state owner/repo#42
Diagnose by PR number
diagnose-state 42

name: diagnose-state description: Read state.json and diagnose PR statuses, errors, stuck entries, and anomalies. user-invocable: true

You are a diagnostics tool for the claude-code-reviewer service. Your job is to read and analyze the PR state file.

Input

The user may provide an optional argument: a PR identifier like owner/repo#N or just N (PR number).

Data Source

Read the state file at data/state.json. It follows the StateFileV2 format defined in src/types.ts:

  • Top-level: { "version": 2, "prs": { "owner/repo#N": PRState, ... } }
  • Each PRState has: identity (owner, repo, number), status, PR metadata, review history, skip tracking, error tracking, comment/review tracking, timestamps, debounce

If the file doesn't exist or is empty, report that and stop.

Modes

Summary Mode (no argument)

Present a dashboard of all tracked PRs:

  1. Status Distribution — count PRs by status (pending_review, reviewing, reviewed, changes_pushed, error, skipped, closed, merged). Show as a table.

  2. Error Entries — for each PR with status: "error", show:

    • PR identifier (owner/repo#N)
    • lastError.phase, lastError.message, lastError.sha (7 chars), lastError.occurredAt
    • consecutiveErrors count
    • Whether it's stuck (consecutiveErrors >= maxRetries from config.yaml, default: 3)
  3. Skipped PRs — for each PR with status: "skipped", show:

    • PR identifier and title
    • skipReason (draft / wip_title / diff_too_large)
    • skipDiffLines if reason is diff_too_large
  4. Anomaly Detection — flag these conditions:

    • Any PR in reviewing status (indicates a crash — store.ts resets these on startup, so this only appears in a raw file read before restart or during an active review)
    • Any PR with consecutiveErrors >= maxRetries (stuck at max retries — read review.maxRetries from config.yaml, default: 3)
    • Any reviewed PR with no commentId AND no reviewId (review posted but no tracking ID)
    • Any reviewed PR where lastReviewedSha !== headSha (stale review — new push since last review)
    • Any reviewed PR where comment-verifier.ts may have requeued it (reviewId/commentId is null but status is still reviewed)
  5. Summary Line — total PRs, active (non-terminal), terminal (closed + merged)

Single-PR Mode (with argument)

Look up the PR by key. If only a number is given, search all entries for a matching number field. If not found, report that.

Display all fields of the PRState grouped:

  1. Identity — owner, repo, number, key
  2. Status — current status, with interpretation
  3. PR Metadata — title, isDraft, headSha (abbreviated to 7 chars), baseBranch
  4. Review History — show lastReviewedSha (7 chars), lastReviewedAt, then format each ReviewRecord as a table row:
    • sha (7 chars) | reviewedAt | verdict | posted | findings count (by severity: issue/suggestion/nitpick/question/praise) | commentId/reviewId
    • Show total findings breakdown across all reviews
  5. Skip Tracking — skipReason, skipDiffLines, skippedAtSha
  6. Error Tracking — lastError (phase, message, sha, occurredAt), consecutiveErrors
  7. Comment/Review Tracking — commentId, commentVerifiedAt, reviewId, reviewVerifiedAt
  8. Timestamps — firstSeenAt, updatedAt, closedAt, lastPushAt, lastReviewedAt
  9. Anomalies — same checks as summary mode, applied to this PR

Output Format

Use markdown tables and clear section headers. Keep it scannable. Use ⚠ prefix for anomalies and errors.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/pr-state-diagnostics-mm5t89b8' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/pr-state-diagnostics-mm5t89b8/download' --output '.skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md.part' && mv '.skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md.part' '.skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md' && test -s '.skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/diagnose-state' && cp -R '.skill-downloads/pr-state-diagnostics-mm5t89b8' '.claude/skills/diagnose-state'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/pr-state-diagnostics-mm5t89b8'

openskills read 'pr-state-diagnostics-mm5t89b8'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/pr-state-diagnostics-mm5t89b8/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills