taproot

Assist when a developer cannot confidently answer a domain question during a skill session — scan the project for evidence, apply domain knowledge, and propose a concrete answer with reasoning and alternatives

Collaborative requirement exploration — think through a vague idea before speccing it; asks one focused question at a time and hands off to the right skill when ready

Run a comprehensive review of an entire subtree — an intent and all its descendants, or the entire `taproot/` root

Stress-test a single Taproot artifact — an `intent.md`, `usecase.md`, or `impl.md` — by challenging it from multiple angles

Capture ideas, findings, and deferred work mid-session with a single command — without interrupting current flow

Define a UseCase (observable system behaviour) under an intent or another behaviour

Read a taproot hierarchy document section by section in the terminal — without opening an external editor

Diagnose a defect through structured root cause analysis (5-Why) and delegate to the right fix skill

Execute the full commit procedure: classify the commit type, run the appropriate gate proactively, resolve all conditions before staging, and commit

Create or update a free-form truth entry in `taproot/global-truths/` — a fact, rule, term, convention, or decision that applies across the project

Reverse-engineer an existing project into a taproot hierarchy — from source code, existing requirements artifacts (PRDs, stories, ADRs), or both

Scan the taproot hierarchy for implicit facts — recurring terms, business rules, and conventions — that are not yet captured as global truths

Interview the user relentlessly about a plan or design, resolving each decision branch with a recommendation until shared understanding is reached

Present a tailored onboarding guide for the Taproot workflow

Implement a behaviour spec: write the code, write the tests, create the `impl.md` traceability record, and commit with the conventional tag format

Route a natural language requirement to the right place in the taproot hierarchy — clarifying vague requirements through structured discovery before placing and delegating them

Create a new business intent or refine an existing one

Create a cross-repo link file (`link.md`) that references a spec — intent, behaviour, or global truth — in another repository

Surface the next independently-implementable work item from the requirement hierarchy

Analyse `taproot/plan.md` before execution: check each pending item for readiness, flag ambiguous specs, unresolved dependencies, and missing prerequisites, and produce a per-item report so the developer knows what needs fixing before executing

Execute items from `taproot/plan.md` one at a time (step-by-step) or in sequence (batch), with optional filters to process only `spec`+`refine` items (specify mode) or only `implement` items (implement mode)

Build or modify the persistent implementation plan (`taproot/plan.md`)

Escalate a significant finding from implementation or behaviour level up to the intent

Update a behaviour spec (`usecase.md`) based on what was learned during or after implementation

Research any domain or technical subject before writing a behaviour spec — by scanning local resources, searching the web, and drawing on expert knowledge

Generate a health dashboard for the requirement hierarchy

Apply a uniform task to a filtered set of hierarchy files — enumerate matching items, confirm with the developer, then process each file in-session with live progress marking

Navigate the requirement hierarchy in any direction: from code to intent (bottom-up), from intent to code (top-down), laterally across siblings, or scan for unlinked code