Wira Delta Indonesia

Skills Directory

Skills Directory

WDI Method installs 22 skills: 7 gate skills, 5 for the daily tier (including wdi-autopilot), and 10 you run any time.

How a Skill Starts

  • You type it: the four daily tier skills and wdi-explain-to-me (they carry disable-model-invocation: true).
  • You type it, or the agent names it and waits for your go-ahead: the other skills.
  • The agent may run it on its own (read-only): wdi-help.
  • Fired by /loop under an accepted mandate: wdi-autopilot. Under a mandate, wdi-autopilot also runs the other skills.

Gate Skills

SkillWhat It DoesHow It Starts
/wdi-init Use for anything that must exist before work can start or continue: scaffolding the registries at install, birthing Product Components after G2, setting or changing a component's mode, setting or reviewing its risk_accepted, refreshing the two structure maps, repairing the engines after an install or update, and writing this product's inventory readers. Seven intents. Never writes .what/ or .how/ content beyond a skeleton. You type it, or the agent names it and waits for your go-ahead
/wdi-problem G1. Runs BMad's product brief skill, then checks the brief against the method's guide. Never writes the brief itself. You type it, or the agent names it and waits for your go-ahead
/wdi-product G2. Runs BMad's PRD skill for a new PRD or a changed promise, then checks it against the PRD guide. Never writes the PRD itself. You type it, or the agent names it and waits for your go-ahead
/wdi-ux Use when UX is produced or landed: dispatching bmad-ux for a PRD scope, then landing DESIGN.md, EXPERIENCE.md, the design system, and the screen registry into the layers they belong to. Optional, and it rides on G2. Never writes UX content itself. You type it, or the agent names it and waits for your go-ahead
/wdi-blueprint G3, once per product. The whole-product picture: use cases, actors, domain model, business rules, glossary, the architecture spine, C4, and the API, table, and screen inventories. You type it, or the agent names it and waits for your go-ahead
/wdi-component G4. The depth of one component, as deep as its mode and no deeper. Skipped at mode: catalog. You type it, or the agent names it and waits for your go-ahead
/wdi-build G5. One spec from open to closed: you run to-spec and to-tickets, each ticket goes to a green PR, then the spec closes. It never merges. You type it, except when run by wdi-autopilot or wdi-daily-autopilot

Daily Tier

SkillWhat It DoesHow It Starts
/wdi-daily-what-to-build Turns hand-testing notes into a reviewed spec or ticket for a later autopilot run. Stops before code, commit, or push. You type it
/wdi-daily-autopilot Checks for an accepted mandate (runs the preflight if there is none), resolves reviewers from local config, and starts the loop, every 10 minutes by default. You type it
/wdi-autopilot The loop itself: works through every FR under one accepted mandate, on one branch with one PR, and writes every decision to one ledger. Fired by /loop under an accepted mandate
/wdi-daily-what-to-test After a merge: syncs the development branch, prunes merged branches and worktrees, prepares the app for hand-testing, and builds a checklist from the closed tickets. You type it
/wdi-prune-or-archive Moves closed specs to .archive/specs/ or removes them with git rm, through lifecycle.py, which checks first and rolls back on failure. The spec row stays in specs.yaml. You type it

Any Time

SkillWhat It DoesHow It Starts
/wdi-help Reads the status registry and tells you the current gate, the open specs, and the next skill. The agent may run it on its own (read-only)
/wdi-explain-to-me Does the reading before you decide: investigates, then briefs you in six fixed sections. Writes no file. You type it
/wdi-decision Opens, accepts, and applies a numbered decision (DEC-), and carries it into the documents it governs. You type it, or the agent names it and waits for your go-ahead
/wdi-question Files something that cannot be decided now into one of four lists in .control/questions/, and closes it when the answer arrives. You type it, or the agent names it and waits for your go-ahead
/wdi-log Use when a fact from outside the code has to be recorded: a meeting that finished, or a non-technical fact that constrains what may be built. Two intents, meeting and fact. Routes decisions and open questions to their own skills. You type it, or the agent names it and waits for your go-ahead
/wdi-report Use when someone needs numbers about this project: progress for a client update, an estimate before the work is committed, task rows ready to paste into a tracker, or a self-contained brief/PRD deliverable. Four intents, progress and estimate and dispatch and render. Never invents a number. You type it, or the agent names it and waits for your go-ahead
/wdi-reconcile Before a gate or after a batch of changes: reports drift between .what, .how, .control, and the method's rules. Read-only. You type it, or the agent names it and waits for your go-ahead
/wdi-review Use to review any corpus document at any time, and always before a gate on the four artifacts no doc_standards covers: the architecture spine, SRS, SDD, and SPEC. Reads the lens set from the component's risk_accepted, dispatches bmad-review, and stamps the review-trace trace on those four only. Not for code review. You type it, or the agent names it and waits for your go-ahead
/wdi-systematic-debugging For any bug, failing test, or failed build, before a fix is proposed: find the root cause and test one hypothesis at a time. You type it, or the agent names it and waits for your go-ahead
/wdi-upgrade Right after wdi-method update: moves documents and registry files still in the old shape into the new one, then checks that validation is green. You type it, or the agent names it and waits for your go-ahead