Agent
Data-discipline agent — authors the PII-classified data-contract, the data-readiness assessment (advisory), and the lineage-audit for a feature or spec. PII is a risk-tier driver; readiness gaps become decision-log items. Runs standalone, as the driver of /sdlc-data, or as the /sdlc-review Data lens (Phase 2).
Agent
Cross-document analysis for discovery — finds contradictions across an intake corpus and generates the pre-workshop question list. Runs standalone or as Phase 0 Step 0d.
Agent
Product-discipline agent for the featuring hop — decomposes one epic into channel-aware features and specs, drafts feature-brief.md, proposes the decomposition and risk tiers, and opens decision-log items. Runs standalone or as the driver of /sdlc-feature (Phase 1).
Agent
Attempts to fix simple gate failures (missing templates, incomplete sections, placeholder content) before escalating to human.
Agent
Multi-perspective review agent with adversarial, edge-case, and council modes for challenging phase artifacts.
Agent
Transforms technical SDLC artifacts into prose-rich stakeholder-friendly companion documents.
Agent
Guides discovery interviews and decomposes problems into structured requirements with acceptance criteria.
Agent
SDLC phase coordinator that manages phase transitions, skill invocation, and lifecycle orchestration.
Agent
Evaluates completed section implementations against their section plan's Verification Criteria and Evaluator Contract.
Agent
Design-discipline agent for web/visual surfaces (the ag-ui channel) — authors the user journey, surface layout (screens), and the channel-interaction-spec that is the AG-UI event contract. Runs standalone, as the /sdlc-experience designer for ag-ui, or as the /sdlc-review Design lens (Phase 2).
Command
Audit the content of your pre-Build artifacts: which ones have gone stale relative to the things they depend on, what a change would put at risk, and the full change trail of any one artifact.
Command
Analyze gate results across completed phases in the current project's state.yaml to identify which gates are useful and which are candidates for adjustment.
Command
Run cross-document analysis on the intake corpus and draft the one-page workshop brief, with the human curating what makes the page. Works inside an SDLC project or standalone against any folder of documents.
Command
Bind one spec to its delivery channel and overlay that channel's acceptance dimensions onto the spec's existing ## Acceptance Checks. This is the bind beat after /sdlc-feature (decompose) and /sdlc-experience (author): decompose → author → bind. It reads the channel descriptor and the Phase-2 interaction spec, injects…
Command
Start or continue a coaching conversation for the current SDLC phase. Coaching mode uses adaptive dialogue instead of rigid step lists to guide the user through phase requirements.
Command
Give Data a first-class drafting seat: the data contract (PII-classified), the data-readiness assessment, and the lineage / audit design for a feature or spec. It sharpens Scope, surfaces the PII that drives risk tier, and turns readiness gaps into tracked decisions. Interview-driven like /sdlc-coach: the data-analyst…
Command
Verify that the installed harness will actually run in this repo, and tell the developer exactly what to do about anything that won't.
Command
Generate stakeholder-friendly narrative companions for SDLC artifacts.
Command
Author the golden set — the acceptance criteria for probabilistic behavior — for a spec on an llmpowered channel. Bizreq owns the scenarios, Data owns the data; the two are authored collaboratively. This command is a thin wrapper around the existing eval-builder harness skill: it adds no new script, authors no CI…
Command
Author the craft of a surface — the user journey, the surface layout, and the channel interaction spec — for one channel-bound spec. This is the author beat between /sdlc-feature (which decomposes) and /sdlc-channel (which binds): decompose → author → bind. It routes by the feature's channel to the right designer …
Command
Drive the epic → feature → spec decomposition that the plugin lacks today — the "featuring" hop where you decide how a feature is delivered (which customer channels, which personas) and carve it into buildable specs. Output is feature-brief.md, authored on every channel-bound feature. This is interview-driven like…
Command
Run the 7-gate validation system for the current (or specified) SDLC phase without advancing.
Command
Install (or refresh) the standard-aligned delivery harness in the current repo, independent of a full /sdlc-setup. Use this to add the harness to a repo that already has .sdlc/, or to pull the latest harness after a plugin update (the harvest loop).
Command
Process external reference documents (RFPs, API specs, vendor docs, decks) into a cataloged, token-budgeted set of summaries for use across the engagement. This is the Phase 0 Step 0c workflow wrapped as one command, so no one runs the cataloger script by hand.