/jumbo-add-guideline
Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
$ npx -y skills add jumbocontext/jumbo.cli --skill jumbo-add-guideline --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-guideline
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
SKILL.md
jumbo-add-guideline.SKILL.mdname: jumbo-add-guideline
description: Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
Add Guideline
Register a guideline with Jumbo when the user states a preference about how work should be done. Guidelines shape agent behavior across all future sessions.
**Important:** Guidelines must be **generally applicable** to the project. Do not word them for a specific use case, goal, or task. A guideline that only applies to one situation belongs in a goal's criteria, not in the guideline registry.
Before Adding
Check for an existing guideline to avoid duplication. Consider removing, or updating, a previously registered guideline before registering a new one.
Use the search subcommand to locate previously registered guidelines:
jumbo guidelines search -q <query>
Command Syntax
jumbo guideline add \
--category "<testing|codingStyle|process|communication|documentation|security|performance|other>" \
--title "<Guideline title>" \
--description "<What to do and when>" \
--rationale "<Why this matters>"
Bad Example
jumbo guideline add \
--category codingStyle \
--title "Use arrow functions in the auth module" \
--description "All functions in src/auth/ should be arrow functions" \
--rationale "Consistency in auth code"
Too narrow — scoped to one module and one task. This is a goal criterion, not a project guideline.
Good Example
jumbo guideline add \
--category codingStyle \
--title "Prefer arrow functions for non-method declarations" \
--description "Use arrow functions for callbacks, inline handlers, and standalone function expressions. Use function declarations for exported named functions and class methods." \
--rationale "Consistent lexical scoping and concise syntax across the codebase"
Applies project-wide. States when to use and when not to use. Rationale explains the benefit.
Read more
name: jumbo-add-guideline description: Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
Add Guideline
Register a guideline with Jumbo when the user states a preference about how work should be done. Guidelines shape agent behavior across all future sessions.
**Important:** Guidelines must be **generally applicable** to the project. Do not word them for a specific use case, goal, or task. A guideline that only applies to one situation belongs in a goal's criteria, not in the guideline registry.
Before Adding
Check for an existing guideline to avoid duplication. Consider removing, or updating, a previously registered guideline before registering a new one.
Use the search subcommand to locate previously registered guidelines:
jumbo guidelines search -q <query>
Command Syntax
jumbo guideline add \ --category "<testing|codingStyle|process|communication|documentation|security|performance|other>" \ --title "<Guideline title>" \ --description "<What to do and when>" \ --rationale "<Why this matters>"
Bad Example
jumbo guideline add \ --category codingStyle \ --title "Use arrow functions in the auth module" \ --description "All functions in src/auth/ should be arrow functions" \ --rationale "Consistency in auth code"
Too narrow — scoped to one module and one task. This is a goal criterion, not a project guideline.
Good Example
jumbo guideline add \ --category codingStyle \ --title "Prefer arrow functions for non-method declarations" \ --description "Use arrow functions for callbacks, inline handlers, and standalone function expressions. Use function declarations for exported named functions and class methods." \ --rationale "Consistent lexical scoping and concise syntax across the codebase"
Applies project-wide. States when to use and when not to use. Rationale explains the benefit.
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-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.
Open skill

