mcpField
F
fable-review

fable-review

github.com/davidondrejTesting & quality4.2k122 installsUpdated today
Repository

About fable-review

A code-review skill that runs Fable 5.1 Extra High through Claude Code, orchestrated by Cloudroom. It guides a neutral review of code and tests without modifying files, then returns the reviewer’s complete final response.

Key features

  1. 01Run Fable via Claude Code and Cloudroom
  2. 02Prepare a neutral review brief
  3. 03Review related code and tests
  4. 04Verify review completion and report blockers
  5. 05Return the full final response

Use cases

  1. 01Assess production merge readiness
  2. 02Find serious issues in a proposed change
  3. 03Identify uncertainty and validation gaps

MCP support

This skill coordinates a review through Cloudroom using `room-cli` or the selected harness’s equivalents. It does not describe an MCP server or MCP-specific behavior.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/davidondrej/skills --skill fable-review

After installing, type/fable-reviewin Claude Code to confirm it loaded.

Bundled filesagents/openai.yaml

Details

From the project README

Fable Review

Use Fable 5.1 Extra High through Claude Code, orchestrated by Cloudroom.

Run

Read /room-cli and follow its launch checks. Discover provider/model/effort IDs rather than guessing. Reuse the current environment, including uncommitted work, and use --parent-self when coordinating.

If the user names another harness, read its skill and use it with the same model, effort, workspace, brief, and output requirements. Report unavailable model/effort as blockers; never silently downgrade.

Review brief

Give neutral context: scope, paths, intended behavior, and diff/base revision. Ask for a thorough senior-developer review, including related code and tests, without steering toward suspected bugs, solutions, or verdicts. Review only; do not change files. Request a concise plain-English report of serious or critical issues, fixes, and production merge readiness. Distinguish verified findings from uncertainty and identify validation gaps.

Result

Use room-cli thread wait and room-cli thread output (or the selected harness's equivalents). Verify this review actually completed; idle status, timeouts, and queued retries are not completion. Report blockers rather than presenting partial output as a finished review.

Return the completed reviewer's full final response verbatim.

Comments

Markdown supported