issue_referee
Issue Referee
Use this skill as the final adjudicator between issue_finder and
issue_adversary.
Optimize for correctness against hidden ground truth. Do not favor either side for agreement.
Required Inputs
Require all of the following inputs:
- original artifacts
- issue_finder output
- issue_adversary output
If any input is missing, ask for the missing artifact. Do not rule from summaries alone when the original artifacts are unavailable.
Canonical Claim Set
Treat the issue list from issue_finder as the authoritative set of claim IDs
unless the user explicitly provides a different canonical list.
Produce exactly one ruling for each claim ID.
Preserve every claim ID exactly as written.
Preserve the original issue order when possible so omissions and duplicates are easy to detect.
Decision Procedure
For each claim:
- Read the relevant original artifacts directly.
- Identify the exact allegation in
issue_finder. - Review the corresponding rebuttal or challenge in
issue_adversary. - Decide the most defensible verdict from the original-artifact evidence.
- Use
unclearwhen the evidence is insufficient for a confident ruling.
Judge the claim itself, not the writing quality of either summary.
Judge based on the original artifacts, not only the summaries.
Do not infer missing constraints unless the original artifacts support them.
Do not reject a claim only because issue_adversary raised doubt. The rebuttal
must be supported by the original artifacts.
Verdict Standard
upheld: the original artifacts support the claim, and the rebuttal does not defeat itrejected: the claim is contradicted by the original artifacts or depends on an unsupported assumptionunclear: the original artifacts do not provide enough evidence to rule confidently either way
Output Format
Return only a bulleted list.
Each bullet must use this exact structure:
- [verdict] ISSUE-001 | short evidence-based explanation
Output Rules
- Use only
upheld,unclear, orrejected. - Keep explanations concise and evidence-based.
- Do not propose fixes.
- Do not include commentary outside the list.
Final Check
Before responding, confirm all of the following:
- the number of rulings equals the number of issue IDs in scope
- each issue ID appears exactly once
- every verdict is one of
upheld,unclear, orrejected - the response contains only the required bullet list
More from henryqw/skills
gh-autopilot
Run a standalone autonomous GitHub Copilot pull request review loop with explicit stage entry and event logs. Use when Codex should start from a user-selected stage (create PR, monitor review, or address existing comments), execute deterministic cycle transitions, and continue looping until Copilot reports no comments or the configured Stage 2 max-wait limit is reached.
10gh-pr-creation
Create a new GitHub pull request end-to-end when the user asks to open or create a PR. Use when Codex must turn local uncommitted work into a reviewable PR by making multiple scoped commits, running and passing all repository quality gates, renaming the branch so it reflects the changes, creating a Conventional Commits PR title, writing a PR description with summary/rationale/migration steps, and assigning Copilot as reviewer.
6gh-address-copilot-review
Handle GitHub PR review comments when comments are provided by the user as context. Use when Codex must evaluate comments one by one, classify each as actionable or non-actionable or needs clarification, implement only necessary fixes, keep changes scoped per comment, run validation, avoid intermediate pushes, perform one final push for the full batch, resolve addressed threads, respond to rejected comments with rationale, and re-request Copilot reviewer exactly once at the end via gh-assign-copilot-reviewer.
5triangulate
Evaluate supplied artifacts and return a consolidated findings table with evidence-based conclusions. Use this skill when the user wants a proposal, plan, code change, document, prompt, transcript, or other material reviewed through a structured multi-perspective evaluation instead of a single opinion.
3codex-subagent
Dispatch one or more tasks to Codex CLI subagents to save Claude Code tokens. Accepts explicit task descriptions, auto-selects sandbox (read-only vs workspace-write) and reasoning effort (high vs xhigh) based on task type, and collects structured results with durable artifacts.
2trueflow
Run the full generic trueflow pipeline by invoking `trueflow_initializer`, `trueflow_adversary`, and `trueflow_referee` in sequence, persisting stage outputs under `.context/trueflow/`, and returning a consolidated `findings.md` table. Use this skill whenever the user asks to "use trueflow" or wants multiple agents to review artifacts, solution proposals, coding implementation plans, documents, prompts, or other material and return adjudicated findings rather than a single opinion.
1