gambit

Use when an epic Task exists and subtasks are ready to implement, when resuming work after a previous checkpoint, when iteratively building a feature, or when implementation has revealed unexpected work that needs a new task. User phrases like "continue the plan", "next task", "resume where we left off", "pick up the epic".

Use after all tasks in an epic complete, after refactoring verifies, or before merging to main. Triggers when independent validation is needed that code meets requirements, has no security gaps, passes quality standards, and has no performance regressions. User phrases like "review this", "is this ready to merge", "validate the implementation".

Use when an epic Task exists and subtasks are ready to implement, when resuming work after a previous checkpoint, when iteratively building a feature, or when implementation has revealed unexpected work that needs a new task. User phrases like "continue the plan", "next task", "resume where we left off", "pick up the epic".

Use after all tasks in an epic complete, after refactoring verifies, or before merging to main. Triggers when independent validation is needed that code meets requirements, has no security gaps, passes quality standards, and has no performance regressions. User phrases like "review this", "is this ready to merge", "validate the implementation".

Use when user has a new feature idea, rough concept, or unexplored approach. Include when planning before code, breaking a design into tasks, creating an implementation plan, laying out tasks and dependencies, exploring architectural options, or requirements are vague. User phrases like "I want to build X", "should we do this", "let's think through Y", "explore approaches", "break this into tasks", "make an implementation plan". Do NOT use for executing existing plans, fixing bugs, refactoring, or when requirements and an epic already exist.

Use when user has a new feature idea, rough concept, or unexplored approach. Include when planning before code, breaking a design into tasks, creating an implementation plan, laying out tasks and dependencies, exploring architectural options, or requirements are vague. User phrases like "I want to build X", "should we do this", "let's think through Y", "explore approaches", "break this into tasks", "make an implementation plan". Do NOT use for executing existing plans, fixing bugs, refactoring, or when requirements and an epic already exist.

Use when user has a new feature idea, rough concept, or unexplored approach. Include when planning before code, breaking a design into tasks, creating an implementation plan, laying out tasks and dependencies, exploring architectural options, or requirements are vague. User phrases like "I want to build X", "should we do this", "let's think through Y", "explore approaches", "break this into tasks", "make an implementation plan". Do NOT use for executing existing plans, fixing bugs, refactoring, or when requirements and an epic already exist.

Use when a test is failing, when a bug is reported, when behavior is unexpected or intermittent, when a build or integration step fails, or when a flaky test keeps resurfacing. Especially when "the fix seems obvious", when multiple previous fixes haven't stuck, or when under time pressure to ship.

Use when an approved epic contract and native wave plan exist in the current root session, when resuming work after a previous checkpoint, or when iteratively building a feature and execution learnings require a later wave. User phrases like "continue the plan", "next wave", "resume where we left off", "pick up the epic".

Use when every native epic wave is completed, when ready to integrate after review approval, when choosing between merge / PR / keep / discard for a branch, when tests need final verification before integration, or when a merge produced conflicts that require re-testing. User phrases like "ready to merge", "open a PR", "done with this branch", "ship it".

Use this implementation mechanic to restructure covered code without changing behavior only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use after every native wave in the current root session is complete, after refactoring verifies, or before merging to main. Triggers when independent validation is needed that code meets requirements, has no security gaps, passes quality standards, and has no performance regressions. User phrases like "review this", "is this ready to merge", "validate the implementation".

Use this implementation mechanic to refine prepared work briefs only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic for new behavior or bug fixes requiring test coverage only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to audit an existing test suite only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use only when the user explicitly asks Gambit to route a concrete software task and has not already named a public workflow owner.

Use this implementation mechanic to substantiate a completion or readiness claim only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use when creating a new skill, modifying an existing skill, writing or rewriting a SKILL.md file, auditing a skill's description for discoverability, or when user mentions "create a skill", "write a skill", "new skill", "modify skill", "improve skill", "edit the skill".

Use this implementation mechanic to substantiate a completion or readiness claim only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to substantiate a completion or readiness claim only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use when a test is failing, when a bug is reported, when behavior is unexpected or intermittent, when a build or integration step fails, or when a flaky test keeps resurfacing. Especially when "the fix seems obvious", when multiple previous fixes haven't stuck, or when under time pressure to ship.

Use when all epic tasks show completed, when ready to integrate after review approval, when choosing between merge / PR / keep / discard for a branch, when tests need final verification before integration, or when a merge produced conflicts that require re-testing. User phrases like "ready to merge", "open a PR", "done with this branch", "ship it".

Use this implementation mechanic to restructure covered code without changing behavior only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to refine prepared work briefs only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic for new behavior or bug fixes requiring test coverage only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to audit an existing test suite only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to restructure covered code without changing behavior only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to refine prepared work briefs only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use this implementation mechanic to audit an existing test suite only when explicitly invoked by name or called by an active Gambit workflow owner; do not select it implicitly as a peer workflow.

Use only when the user explicitly asks Gambit to route a concrete software task and has not already named a public workflow owner.

Use when creating a new skill, modifying an existing skill, writing or rewriting a SKILL.md file, auditing a skill's description for discoverability, or when user mentions "create a skill", "write a skill", "new skill", "modify skill", "improve skill", "edit the skill".

Use when creating a new skill, modifying an existing skill, writing or rewriting a SKILL.md file, auditing a skill's description for discoverability, or when user mentions "create a skill", "write a skill", "new skill", "modify skill", "improve skill", "edit the skill".

Use when all epic tasks show completed, when ready to integrate after review approval, when choosing between merge / PR / keep / discard for a branch, when tests need final verification before integration, or when a merge produced conflicts that require re-testing. User phrases like "ready to merge", "open a PR", "done with this branch", "ship it".