codify-jumbo-goal
Use when a Jumbo goal has been approved by QA review and needs architectural reconciliation…
Use when a Jumbo goal needs QA review after implementation. Runs the review protocol, verifies every objective, criterion, and related entity constraint, and approves the goal for codification or rejects it with feedback.
$ npx -y skills add jumbocontext/cli --skill review-jumbo-goal --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/review-jumbo-goalContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a Jumbo goal needs QA review after implementation. Runs the review protocol, verifies every objective, criterion, and related entity constraint, and approves the goal for codification or rejects it with feedback.
name: review-jumbo-goal description: Use when a Jumbo goal needs QA review after implementation. Runs the review protocol, verifies every objective, criterion, and related entity constraint, and approves the goal for codification or rejects it with feedback.
**Prompt:** Review a completed Jumbo goal implementation against its objective, success criteria, scope, and all related architectural context. Approve the goal if no issue are found, otherwise document the issues and reject the goal.
`jumbo goal review` assembles the goal's full context — objective, criteria, scope, architecture, components, decisions, invariants, and guidelines — into a QA verification prompt. A thorough review catches deviations before they compound. A lazy review lets defects ship.
jumbo goal review --id <goal-id>
Read the entire output carefully. It contains the verification criteria assembled from the goal's relations.
For each success criterion listed in the output:
1. Locate the implementation artifacts that satisfy it 2. Read the relevant code 3. Confirm the criterion is **fully** met — not partially, not approximately
If ANY criterion is not met: add the issues to a list for feedback.
If the review output includes scope sections:
If scope is violated: add the issues to the feedback list.
If the review output includes architecture:
If architecture is misaligned: add the issues to the feedback list.
For each category in the review output:
If ANY entity constraint is violated: add the issues to the feedback list.
Discover the project's verification commands from its repository instructions, build manifests, and CI configuration. Run the tests and other checks that apply to the changed scope using the project's own tooling.
Record failures from applicable verification in the feedback list. Do not require verification commands that the project does not define as applicable. If the project defines no automated verification for the changed scope, record that fact as review evidence rather than a failure.
**If ALL checks pass** (criteria, scope, architecture, entities, tests):
jumbo goal approve --id <goal-id>
**If ANY check failed**:
jumbo goal reject --id <goal-id> --audit-findings <list of issues>
1. **Never approve with unresolved failures.** Every criterion, invariant, and applicable verification must pass before approving. 2. **Never skip entity categories.** Review output includes entities for a reason — each was registered during refinement as essential context. 3. **Always run applicable verification.** Use the project's defined tools and commands; do not assume a package manager or ecosystem. 4. **Document issues clearly.** When rejecting a goal, provide detailed feedback for each failure. 5. **Read the code, don't assume.** Verify each criterion by reading actual implementation, not by recalling what you wrote.
Repo: jumbocontext/jumbo.cli
Use when a Jumbo goal has been approved by QA review and needs architectural reconciliation…
Use when a project has Architecture data that needs migrating to fine-grained entities…
Add Jumbo goals liberally to decompose objectives into finite units of work with bounded…
Use when the user's prompt is delivered outside the execution context of an existing Jumbo…
Use liberally when you create, discover, or modify a software component. Registers the…
Use liberally when you make an architectural choice, select a technology, or reject an…