LearnNewsExamplesServices
Frontmatter
id11478
titleEnforce pr-review skill read in manage_pr_review tool description
stateClosed
labels
enhancementaiarchitecture
assigneesneo-gemini-3-1-pro
createdAtMay 16, 2026, 7:40 PM
updatedAtMay 16, 2026, 8:04 PM
githubUrlhttps://github.com/neomjs/neo/issues/11478
authorneo-gemini-3-1-pro
commentsCount0
parentIssuenull
subIssues[]
subIssuesCompleted0
subIssuesTotal0
blockedBy[]
blocking[]
closedAtMay 16, 2026, 8:04 PM

Enforce pr-review skill read in manage_pr_review tool description

Closedenhancementaiarchitecture
neo-gemini-3-1-pro
neo-gemini-3-1-pro commented on May 16, 2026, 7:40 PM

Context During a recent review of agent behavior, it was observed that agents were bypassing the pr-review skill (and thus the AGENTS.md guidelines, depth floor, and graph-ingestion tags) when conducting PR reviews. Because the manage_pr_review MCP tool is an atomic API call that did not mandate the skill as a pre-step, agents succumbed to "velocity-bias," preferring to execute the tool immediately rather than adhering to architectural discipline.

The Problem Without a strict prompt-time guard in the tool description, the LLM naturally bypasses reading .agents/skills/pr-review/SKILL.md, relying entirely on pre-trained behavior and local context to review the PR. This causes a global failure in the review protocol, resulting in unstructured feedback that breaks Native Edge Graph ingestion and fails to meet the formal Depth Floor.

The Architectural Reality The manage_pr_review endpoint in ai/mcp/server/github-workflow/openapi.yaml (line 637) defines the prompt block exposed to the agent. While tools like create_issue have an explicit **MANDATORY pre-step:** guard, manage_pr_review lacked this protection.

The Fix Update the openapi.yaml description for manage_pr_review to explicitly mandate reading .agents/skills/pr-review/SKILL.md before execution.

Acceptance Criteria

  • openapi.yaml description for manage_pr_review includes a **MANDATORY pre-step:** block referencing the pr-review skill.
  • Ensure the prompt block explicitly prohibits executing a formal review without adhering to the guidelines.

Origin Session ID fc8abc96-ce88-407e-9d92-7fcc494f8236

tobiu closed this issue on May 16, 2026, 8:04 PM
tobiu referenced in commit 96d5ae0 - "feat(github-workflow): add mandatory pr-review skill pre-step (#11478) (#11479) on May 16, 2026, 8:04 PM