/jumbo-add-decision
Use liberally when you make an architectural choice, select a technology, or reject an alternative. Records the decision so future sessions understand why the codebase looks the way it does.
$ npx -y skills add jumbocontext/jumbo.cli --skill jumbo-add-decision --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/jumbo-add-decision
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use liberally when you make an architectural choice, select a technology, or reject an alternative. Records the decision so future sessions understand why the codebase looks the way it does.
SKILL.md
jumbo-add-decision.SKILL.mdname: jumbo-add-decision
description: Use liberally when you make an architectural choice, select a technology, or reject an alternative. Records the decision so future sessions understand why the codebase looks the way it does.
Add Decision
Register an architectural decision with Jumbo when you choose one approach over alternatives. Decisions explain **why** the codebase looks the way it does — without them, future agents may reverse your choices or repeat your analysis.
Before Adding
Check for an existing decision to avoid duplication. Consider reversing, updating, or superseding a previously registered decision before registering a new one.
Use the search subcommand to locate previously registered decisions:
jumbo decisions search -q <query>
Command Syntax
jumbo decision add \
--title "<Decision title>" \
--context "<Problem statement and background>" \
--rationale "<Why this choice was made>" \
--alternative "<Rejected option>" \
--consequences "<Trade-offs accepted>"
Bad Example
jumbo decision add \
--title "Use events" \
--context "Need to track changes"
Title is too vague to be useful. Missing rationale means a future agent has no basis for understanding the choice. Missing alternatives means they cannot evaluate whether the context has changed.
Good Example
jumbo decision add \
--title "Use event sourcing over state-based persistence for domain aggregates" \
--context "Domain aggregates need audit history and the ability to rebuild state at any point in time" \
--rationale "Event sourcing provides a complete audit trail and enables temporal queries without additional infrastructure" \
--alternative "State-based persistence with a separate audit log table" \
--consequences "Requires projection rebuilding for read models; increases storage for high-frequency aggregates"
Title names both the chosen and rejected pattern. Context explains the problem. Rationale connects the choice to the problem. Alternatives and consequences give future agents the information they need to judge whether the decision still holds.
Read more
name: jumbo-add-decision description: Use liberally when you make an architectural choice, select a technology, or reject an alternative. Records the decision so future sessions understand why the codebase looks the way it does.
Add Decision
Register an architectural decision with Jumbo when you choose one approach over alternatives. Decisions explain **why** the codebase looks the way it does — without them, future agents may reverse your choices or repeat your analysis.
Before Adding
Check for an existing decision to avoid duplication. Consider reversing, updating, or superseding a previously registered decision before registering a new one.
Use the search subcommand to locate previously registered decisions:
jumbo decisions search -q <query>
Command Syntax
jumbo decision add \ --title "<Decision title>" \ --context "<Problem statement and background>" \ --rationale "<Why this choice was made>" \ --alternative "<Rejected option>" \ --consequences "<Trade-offs accepted>"
Bad Example
jumbo decision add \ --title "Use events" \ --context "Need to track changes"
Title is too vague to be useful. Missing rationale means a future agent has no basis for understanding the choice. Missing alternatives means they cannot evaluate whether the context has changed.
Good Example
jumbo decision add \ --title "Use event sourcing over state-based persistence for domain aggregates" \ --context "Domain aggregates need audit history and the ability to rebuild state at any point in time" \ --rationale "Event sourcing provides a complete audit trail and enables temporal queries without additional infrastructure" \ --alternative "State-based persistence with a separate audit log table" \ --consequences "Requires projection rebuilding for read models; increases storage for high-frequency aggregates"
Title names both the chosen and rejected pattern. Context explains the problem. Rationale connects the choice to the problem. Alternatives and consequences give future agents the information they need to judge whether the decision still holds.
Repo: jumbocontext/jumbo.cli
Other skills on jumbocli.
- /codify-jumbo-goal
Use when a Jumbo goal has been approved by QA review and needs architectural reconciliation before closing. Captures new learnings, updates stale entities, and ensures documentation reflects the work performed.
Open skill - /decompose-architecture-aggregate
Use when a project has Architecture data that needs migrating to fine-grained entities (Decisions, Invariants, Components, Dependencies). Guides the agent through reading, mapping, confirming, and executing the migration with user oversight.
Open skill - /define-jumbo-goals
Add Jumbo goals liberally to decompose objectives into finite units of work with bounded context. Use when defining new Jumbo goals from user requests, or to augment your own work to maintain scope while ensuring complementary work is registered.
Open skill - /formalize-objectives
Use when the user's prompt is delivered outside the execution context of an existing Jumbo goal, the prompt is imbued with an objective that is not already defined as a Jumbo goal.
Open skill - /jumbo-add-component
Use liberally when you create, discover, or modify a software component. Registers the component with Jumbo so future sessions have accurate architectural context.
Open skill - /jumbo-add-dependency
Use liberally when you introduce, discover, or upgrade a third-party package or external service. Registers the dependency so future sessions know what the project relies on.
Open skill

