refactor(skills): correct RPI and HVE Builder subagents to be optional and advisory and remove rpi-quick and hve-builder-tester skills

.github/CUSTOM-AGENTS.md

@@ -38,7 +38,7 @@ Select from the **agent picker dropdown** in the Chat view:
 
 The RPI lifecycle keeps Research, Plan, Implement, Review, and Follow-up distinct for complex development tasks. It begins with research readiness: supplied or completed evidence is reused when adequate, and research runs only for a demonstrated requirements, acceptance, dependency, material-risk, complexity, uncertainty, or decision-critical gap.
 
-`RPI Agent` is a user-selected lifecycle wrapper that activates the matching RPI skills. It runs in manual mode by default and can switch to a confirmed automatic session that completes the remaining phases through Review. The `/rpi` prompt provides the same full-lifecycle entry point, and `/rpi-quick` is the skill-based equivalent. Use `/rpi-research`, `/rpi-plan`, `/rpi-implement`, and `/rpi-review` when you need a direct phase entry point.
+`RPI Agent` is a user-selected lifecycle wrapper that activates the matching RPI skills. It runs in manual mode by default and can switch to a confirmed automatic session that completes the remaining phases through Review. The `/rpi` prompt provides the same full-lifecycle entry point. Use `/rpi-research`, `/rpi-plan`, `/rpi-implement`, and `/rpi-review` when you need a direct phase entry point.
 
 Use the self-contained `rpi-challenger` skill to interrogate a confirmed subject through adaptive skeptical questions, and `rpi-walkthrough` to understand code or RPI artifacts one segment at a time. See the [RPI Documentation](../docs/rpi/README.md) for all surfaces.
 

.github/agents/accessibility/accessibility-planner.agent.md

@@ -15,7 +15,7 @@
     agent: RAI Planner
     prompt: /rai-capture
     send: true
   - label: "SSSC Planner"
     agent: SSSC Planner
     prompt: /sssc-capture
     send: true
@@ -145,8 +145,6 @@
 * Requested outputs and output mode, using `analysis` unless the user requests another supported mode.
 * `.copilot-tracking/accessibility/{project-slug}/` as a trusted alternate evidence root.
 
-Require `rpi-research` to mirror `research/YYYY-MM-DD/<task-slug>-research.md` and `research/subagents/...` beneath the trusted root. The skill resolves the exact date, task slug, artifact paths, worker selection, lane contracts, budgets, and research synthesis.
-
 After completion, read the returned primary research artifact and synthesize applicable findings into the active phase artifacts and `state.json`, preserving normative-source provenance and every existing confirmation gate. Treat `Blocked` and `Needs clarification` as unresolved evidence: record the smallest gap and stop dependent mapping work. If `rpi-research` or a required lookup capability is unavailable, report the limitation rather than substituting training-data claims.
 
 ### Phase-Specific Delegation

.github/agents/coding-standards/code-review.agent.md

@@ -226,7 +226,7 @@ Iterate until the human is satisfied or requests a full sweep:
 2. Record each bookmark in the manifest `nextActions` (kind `bookmark`) and set the targeted board item `status` to `in_progress`.
 3. Route the question by depth, augmenting `diff-state.json` with the per-item fields the dispatched subagent reads before each call:
    * Shallow, factual "what does this symbol or function do" questions go to the **Code Review Explainer** subagent (Register 1). Set `boardItem`, `targetSymbol`, `targetPath`, and `question` on `diff-state.json`, then dispatch. The explainer returns Register 1 prose and persists an explanation artifact under the findings folder. Record the route in `nextActions` with kind `explain`.
-    * Deep, investigative "is this correct, is this safe, what are the implications" questions go to the **Code Review Walkback** subagent (Register 2). Allocate a non-colliding `investigationId` as `<boardItemId>-<NNN>` using the next unused three-digit sequence for that board item. Set `boardItem`, `question`, `investigationId`, `researchTopic`, `researchPurpose`, `researchAudienceUse`, explicit `researchQuestions`, `evidenceCriteria`, `researchScope`, `researchNonGoals`, `researchConstraints`, `suppliedEvidence`, `researchRequestedOutputs`, and `researchOutputMode` (`analysis`) on `diff-state.json`. Set `trustedEvidenceRoot` to `findingsFolder`, explicitly trusting that review-local root for mirrored research evidence, and set `register2ArtifactPath` to `<findingsFolder>/walkback/<investigationId>-register-2.md`. Do not choose a research date, task slug, lane name, lane path, or budget. The walkback wrapper activates `rpi-research`, which mirrors `research/YYYY-MM-DD/<task-slug>-research.md` and `research/subagents/...` beneath the trusted root and owns its internal execution details. The wrapper then reads the returned primary research artifact and creates or updates the final Register 2 artifact at `register2ArtifactPath`, anchored to the board item. Record the route in `nextActions` with kind `investigate`.
+    * Deep, investigative "is this correct, is this safe, what are the implications" questions go to the **Code Review Walkback** subagent (Register 2). Allocate a non-colliding `investigationId` as `<boardItemId>-<NNN>` using the next unused three-digit sequence for that board item. Set `boardItem`, `question`, `investigationId`, `researchTopic`, `researchPurpose`, `researchAudienceUse`, explicit `researchQuestions`, `evidenceCriteria`, `researchScope`, `researchNonGoals`, `researchConstraints`, `suppliedEvidence`, `researchRequestedOutputs`, and `researchOutputMode` (`analysis`) on `diff-state.json`. Set `trustedEvidenceRoot` to `findingsFolder`, explicitly trusting that review-local root for mirrored research evidence, and set `register2ArtifactPath` to `<findingsFolder>/walkback/<investigationId>-register-2.md`. Do not choose a research date, task slug, or artifact path. The walkback wrapper activates `rpi-research` and then reads the returned primary research artifact and creates or updates the final Register 2 artifact at `register2ArtifactPath`, anchored to the board item. Record the route in `nextActions` with kind `investigate`.
 4. Walk the returned artifact back onto its board item per the dispatch-loop walk-back rules: update the item `status`, keep its openable links and selectable symbols current, and append any follow-on symbols or questions to `nextActions`.
 5. If a routed subagent is unavailable, note "<subagent> not available, skipping" and leave the board item bookmarked for the batch sweep.
 

.github/agents/coding-standards/subagents/code-review-walkback.agent.md

@@ -36,7 +36,7 @@ Do not invent severity levels, categories, or output fields the skill does not d
 
 1. **Read input.** Read `diff-state.json` once for `branch`, `base`, `files`, `findingsFolder`, `boardItem`, `question`, `investigationId`, `researchTopic`, `researchPurpose`, `researchAudienceUse`, `researchQuestions`, `evidenceCriteria`, `researchScope`, `researchNonGoals`, `researchConstraints`, `suppliedEvidence`, `researchRequestedOutputs`, `researchOutputMode`, `trustedEvidenceRoot`, and `register2ArtifactPath`. In the same parallel block, read the Skill Reference Contract files.
 2. **Validate the activation inputs.** Require every scoped input to be explicit. Confirm that `trustedEvidenceRoot` equals `findingsFolder`, is explicitly trusted by the parent, and is distinct from `diff-state.json`. Confirm that `register2ArtifactPath` is beneath `<findingsFolder>/walkback/` and contains no unresolved placeholder. Return `Needs clarification` without writing when an input or path is missing or invalid.
-3. **Activate research.** Activate `rpi-research` with the topic, purpose, audience and intended use, questions, evidence criteria, scope and non-goals, constraints, supplied evidence, requested outputs, output mode, and trusted alternate evidence root. Require the skill to mirror `research/YYYY-MM-DD/<task-slug>-research.md` and `research/subagents/...` beneath that root. Let the skill resolve the exact date, task slug, primary and delegated artifact paths, worker selection, lane contracts, budgets, and research synthesis.
+3. **Activate research.** Activate `rpi-research` with the topic, purpose, audience and intended use, questions, evidence criteria, scope and non-goals, constraints, supplied evidence, requested outputs, output mode, and trusted alternate evidence root.
 4. **Anchor the result.** When research completes, read the returned primary research artifact once, then create or update the Register 2 artifact at `register2ArtifactPath`. Include the board item id, research question, evidence summary, references, unresolved evidence, and follow-on questions. Preserve links and selectable symbols for later board merge. Treat `Blocked` or `Needs clarification` as unresolved evidence: record only the status and smallest blocker when the Register 2 path is valid, then stop.
 5. **Return a concise summary.** Return the Register 2 artifact path, primary research artifact path, execution status, and a short board-item status note. Do not repeat the primary artifact in the response.
 

.github/agents/experimental/pptx.agent.md

@@ -28,7 +28,7 @@
 
 When the user wants to build slides on a particular topic or add content on a specific subject, activate `rpi-research`. Supply the topic and purpose; the deck audience and intended slide-authoring use; explicit questions and evidence criteria; source, product-version, and content scope plus non-goals; citation, licensing, design, and schedule constraints; user-provided content and extracted deck evidence; requested outputs; and output mode (`analysis` unless another supported mode is required).
 
-Explicitly trust the deck working root `.copilot-tracking/ppt/{{YYYY-MM-DD}}/{{ppt-name}}/` as the alternate evidence root. Require the skill to mirror `research/YYYY-MM-DD/<task-slug>-research.md` and `research/subagents/...` beneath it. The skill resolves its exact date, task slug, primary and delegated artifact paths, worker selection, lane contracts, budgets, and research synthesis.
+Explicitly trust the deck working root `.copilot-tracking/ppt/{{YYYY-MM-DD}}/{{ppt-name}}/` as the alternate evidence root.
 
 Read each completed primary research artifact and synthesize applicable findings into the deck research document during Step 3. Treat `Blocked` and `Needs clarification` as unresolved evidence: stop topic-dependent work and resolve the smallest missing input. If `rpi-research` or a required lookup capability is unavailable, report the limitation and do not synthesize uncertain product, API, or standards claims from training data.
 
@@ -151,7 +151,7 @@
 ## Workflow Variants
 
 When the user omits the action, default to creating a new deck from scratch.
 
 ### New Slide Deck from Scratch (`create`)
 
 Phase 1: Skip Step 2 (extraction). Define the global `style.yaml` in Step 3. Phase 2 and Phase 3 proceed normally.

.github/agents/hve-core/documentation.agent.md

@@ -54,6 +54,6 @@ Do not author standards logic or assessment content in this agent. Summarize the
 ## Working Notes
 
 * Create or update a session file at `.copilot-tracking/documentation/{{YYYY-MM-DD}}-session.md` for the run.
-* Activate `rpi-research` for open-ended documentation discovery, codebase exploration, or decision-critical evidence gathering. Supply the topic and purpose; documentation audience and intended use; explicit questions or evidence criteria; scope and non-goals; repository, source, version, and validation constraints; supplied documentation, code, and session evidence; requested outputs; and the output mode appropriate to the selected documentation mode. Use the default research evidence root unless the caller explicitly supplies another trusted root. Let the skill resolve dates, task slugs, artifact paths, worker selection, lane contracts, budgets, and research synthesis.
+* Activate `rpi-research` for open-ended documentation discovery, codebase exploration, or decision-critical evidence gathering. Supply the topic and purpose; documentation audience and intended use; explicit questions or evidence criteria; scope and non-goals; repository, source, version, and validation constraints; supplied documentation, code, and session evidence; requested outputs; and the output mode appropriate to the selected documentation mode. Use the default research evidence root unless the caller explicitly supplies another trusted root.
 * After activation completes, read the returned primary research artifact and apply relevant findings to the selected documentation mode and session file. Treat `Blocked` and `Needs clarification` as unresolved evidence and stop evidence-dependent conclusions. If `rpi-research` is unavailable, report the blocked discovery instead of improvising a local research route. For authoring, use the `documentation` skill and this agent's declared edit capability.
 * Keep the workflow focused on the selected mode and the supplied context.