codify-jumbo-goal
Use when a Jumbo goal has been approved by QA review and needs architectural reconciliation…
Use when starting a Jumbo goal. Loads goal context, scope, and architectural constraints, then guides the agent through disciplined execution within defined boundaries.
$ npx -y skills add jumbocontext/cli --skill start-jumbo-goal --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/start-jumbo-goalContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when starting a Jumbo goal. Loads goal context, scope, and architectural constraints, then guides the agent through disciplined execution within defined boundaries.
name: start-jumbo-goal description: Use when starting a Jumbo goal. Loads goal context, scope, and architectural constraints, then guides the agent through disciplined execution within defined boundaries.
**Prompt:** Start a Jumbo goal by loading its full context — objective, criteria, scope, architecture, components, decisions, invariants, and guidelines — then execute within the defined boundaries.
When `jumbo goal start` is run, it assembles the goal's registered relations into structured implementation instructions. The objective defines what to build. The criteria define how success is measured. The scope defines boundaries. The architectural context (components, decisions, invariants, guidelines) defines constraints. Deviating from these instructions produces work that fails QA review.
jumbo goal start --id <goal-id>
This loads the full goal context. Read and internalize every section of the output before writing any code.
The goal start output contains structured sections. Each section carries binding instructions:
The single purpose of this goal. All work must serve this objective.
The specific, measurable conditions that determine whether the objective is met. Implementation is not complete until every criterion is satisfied.
If the goal was previously started, review what has already been accomplished and continue from there. Do not redo completed work.
Components that will be modified, created, or depended upon. Consider these while implementing.
External libraries involved in the implementation. Consider version constraints and contracts.
Previous architectural decisions that inform or constrain this change. The solution must remain consistent with these decisions.
Non-negotiable constraints. You MUST adhere to ALL invariants while implementing.
Coding standards, testing requirements, and process practices. You SHOULD follow these while implementing.
jumbo goal update-progress --id <goal-id> --task-description "<description>"
Register decisions, components, and corrections as they happen — not as a cleanup step after implementation.
jumbo decision add --title "Chose X over Y" --rationale "Because Z" --context "Background"
jumbo component add --name "ComponentName" --description "What it does" jumbo relation add --from-type goal --from-id <goal-id> --to-type component --to-id <component-id> --type involves --description "Created during implementation"
jumbo invariant add --category "architecture" --description "Never do X because Y" jumbo guideline add --category "codingStyle" --description "Prefer X over Y"
Context registered now is served to future sessions. What you skip is lost.
When all success criteria are met and implementation is complete:
jumbo goal submit --id <goal-id>
1. **Never deviate from the objective.** All code changes must serve the stated objective. 2. **Never violate scope boundaries.** In-scope files are your workspace. Out-of-scope files are off limits. 3. **Never violate invariants.** Invariants are non-negotiable constraints — no exceptions. 4. **Always track progress.** Use `jumbo goal update-progress` to document completed sub-tasks so future agents can resume if needed. 5. **Always submit when done.** Do not close or codify the goal yourself. Submit it for QA review. 6. **Do not enter plan mode for refined goals.** The goal context IS the plan. Execute immediately.
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…