cfsa-antigravity 3.1.0 → 4.0.0

package/template/{.agent/workflows/bootstrap-agents-fill.md → .agents/skills/bootstrap-agents-fill/SKILL.md}

@@ -22,13 +22,13 @@ Receive template values from the calling workflow and fill the surface stack map
 **Prerequisite**: If invoked standalone, the caller must provide at least one template key-value pair. If no values are provided, there is nothing to fill — report and exit.
 
 > [!IMPORTANT]
-> This workflow fills the surface stack map and global template values. It does **NOT** provision skills from the library — that is handled exclusively by `.agent/workflows/bootstrap-agents-provision.md`. Running this workflow standalone will populate map cells but not install the corresponding skill directories.
+> This workflow fills the surface stack map and global template values. It does **NOT** provision skills from the library — that is handled exclusively by `.agents/skills/bootstrap-agents-provision/SKILL.md`. Running this workflow standalone will populate map cells but not install the corresponding skill directories.
 
 ---
 
 ## 1. Receive values
 
-Accept values in the categories defined in `.agent/skills/bootstrap-agents/SKILL.md` (Section 1):
+Accept values in the categories defined in `.agents/skills/bootstrap-agents/SKILL.md` (Section 1):
 - **Surface-keyed values** → Per-Surface Skills table
 - **Cross-cutting values** → Cross-Cutting Skills table
 - **Global values** → Global Settings table + root configs
@@ -42,7 +42,7 @@ If any values are missing, leave those cells/placeholders in place — they'll b
 
 ## 2. Fill the surface stack map
 
-Open `.agent/instructions/tech-stack.md`.
+Open `.agents/instructions/tech-stack.md`.
 
 ### 2a. Per-Surface Skills table
 
@@ -67,7 +67,7 @@ Fill `PROJECT_NAME`, `DESCRIPTION`, `TECH_STACK_SUMMARY`, `SURFACES`, `ARCHITECT
 
 ## 3. Fill instruction templates
 
-### `.agent/instructions/commands.md`
+### `.agents/instructions/commands.md`
 
 Write per-surface command sections. For each surface in the map:
 
@@ -86,13 +86,13 @@ Write per-surface command sections. For each surface in the map:
 
 If single-surface, omit the surface header — just write a flat commands table.
 
-### `.agent/instructions/workflow.md`
+### `.agents/instructions/workflow.md`
 Fill `{{VALIDATION_COMMAND}}` with the primary surface's validation command (first non-`shared` row in the map, or `shared` if only one row exists).
 
-### `.agent/instructions/patterns.md`
+### `.agents/instructions/patterns.md`
 Replace `{{FRAMEWORK_PATTERNS}}` if provided.
 
-### `.agent/instructions/structure.md`
+### `.agents/instructions/structure.md`
 Replace `{{PROJECT_STRUCTURE}}`, `{{ARCHITECTURE_TABLE}}` if provided.
 
 ---
@@ -114,7 +114,7 @@ Replace in **both** `AGENTS.md` and `GEMINI.md`:
 
 ## 5. Fill operational skill and rule templates
 
-Scan all `.agent/skills/*/SKILL.md` files for `{{PLACEHOLDER}}` values and fill any that match:
+Scan all `.agents/skills/*/SKILL.md` files for `{{PLACEHOLDER}}` values and fill any that match:
 
 - `{{VALIDATION_COMMAND}}` — in `fix-bug`, `main-workflow`, `deploy`, `refactor`
 - `{{PACKAGE_MANAGER}}` — in `refactor`, `security-audit`
@@ -126,7 +126,7 @@ Scan all `.agent/skills/*/SKILL.md` files for `{{PLACEHOLDER}}` values and fill
 - `{{DB_PORT}}` — in `setup-session`
 - `{{CREDENTIAL_TOOL}}` — in `setup-session`
 
-Also scan `.agent/rules/*.md`: `{{CONTRACT_LIBRARY}}` in `tdd-contract-first.md`.
+Also scan `.agents/rules/*.md`: `{{CONTRACT_LIBRARY}}` in `tdd-contract-first.md`.
 
 ---
 
@@ -138,6 +138,6 @@ Report:
 - Which instruction template placeholders were filled
 - Any errors encountered
 
-> **HARD GATE**: Do NOT return to the calling workflow. Do NOT stop here. You MUST now read and execute `.agent/workflows/bootstrap-agents-provision.md`. Fill without provision is an incomplete bootstrap — the skill library remains unresolved, map cells reference skills that don't exist, and downstream map guard checks will fail.
+> **HARD GATE**: Do NOT return to the calling workflow. Do NOT stop here. You MUST now read and execute `.agents/skills/bootstrap-agents-provision/SKILL.md`. Fill without provision is an incomplete bootstrap — the skill library remains unresolved, map cells reference skills that don't exist, and downstream map guard checks will fail.
 >
 > This is not conditional. This is not "if invoked standalone." This applies to EVERY invocation of fill — whether standalone or called by a parent workflow. Provision runs next. Always.

package/template/{.agent/workflows/bootstrap-agents-provision.md → .agents/skills/bootstrap-agents-provision/SKILL.md}

@@ -19,34 +19,34 @@ pipeline:
 
 Read the surface stack map, resolve each skill using the 4-tier chain, provision from the library, and report results.
 
-**Prerequisite**: The surface stack map in `.agent/instructions/tech-stack.md` must have at least one row with filled cells (from a previous `/bootstrap-agents-fill` run).
+**Prerequisite**: The surface stack map in `.agents/instructions/tech-stack.md` must have at least one row with filled cells (from a previous `/bootstrap-agents-fill` run).
 
 ---
 
 ## 6. Read skill library manifest
 
-Read `.agent/skill-library/MANIFEST.md` to load the trigger tables.
+Read `.agents/skill-library/MANIFEST.md` to load the trigger tables.
 
-If `.agent/skill-library/MANIFEST.md` does not exist (e.g., user deleted it or is using a minimal kit), use only Tier 2-4 resolution (no manifest matching).
+If `.agents/skill-library/MANIFEST.md` does not exist (e.g., user deleted it or is using a minimal kit), use only Tier 2-4 resolution (no manifest matching).
 
 ---
 
 ## 7. Provision skills — 4-Tier Resolution Chain
 
-Read the surface stack map from `.agent/instructions/tech-stack.md`. For **every skill name** referenced in any cell of both the Per-Surface Skills table and Cross-Cutting Skills table, resolve it:
+Read the surface stack map from `.agents/instructions/tech-stack.md`. For **every skill name** referenced in any cell of both the Per-Surface Skills table and Cross-Cutting Skills table, resolve it:
 
 ### Tier 1: Exact Match
 
-Check `.agent/skills/{name}/` (already installed) and `.agent/skill-library/{name}/`:
+Check `.agents/skills/{name}/` (already installed) and `.agents/skill-library/{name}/`:
 
 - **Already installed** → skip (idempotent) ✅
-- **Found in library** → copy directory to `.agent/skills/{name}/`, fill any `{{PLACEHOLDER}}`s in the copied SKILL.md ✅
+- **Found in library** → copy directory to `.agents/skills/{name}/`, fill any `{{PLACEHOLDER}}`s in the copied SKILL.md ✅
 - **Not found** → check manifest `Value Pattern` matches (glob-style, case-insensitive) → if matched, install the mapped skill → update the map cell to use the installed directory name ✅
 - **Still not found** → proceed to Tier 2
 
 ### Tier 2: Partial Match + Adequacy Check
 
-Search `.agent/skills/` and `.agent/skill-library/` for skills whose name contains the base term (e.g., for `surrealdb-embedded`, check `surrealdb`):
+Search `.agents/skills/` and `.agents/skill-library/` for skills whose name contains the base term (e.g., for `surrealdb-embedded`, check `surrealdb`):
 
 1. **Partial match found** → read its `SKILL.md`
 2. **Assess adequacy**: Does the skill cover the needed variant? Check for:
@@ -58,7 +58,7 @@ Search `.agent/skills/` and `.agent/skill-library/` for skills whose name contai
 
 ### Tier 3: External Discovery
 
-Read `.agent/skills/find-skills/SKILL.md` and invoke its methodology:
+Read `.agents/skills/find-skills/SKILL.md` and invoke its methodology:
 
 1. Search for the skill externally
 2. **Found** → install → fill map cell with resolved name ✅
@@ -79,11 +79,11 @@ Mark the map cell with `⚠️ {name} [not found]`. Add to the report:
 ## 8. Update installed skills list
 
 After provisioning, build a markdown list of all installed skills and update `{{INSTALLED_SKILLS}}` in:
-- `.agent/instructions/tech-stack.md`
+- `.agents/instructions/tech-stack.md`
 - `AGENTS.md`
 - `GEMINI.md`
 
-Read `.agent/skills/prd-templates/references/operational-templates.md` for the **Installed Skills List** template. Organize skills by:
+Read `.agents/skills/prd-templates/references/operational-templates.md` for the **Installed Skills List** template. Organize skills by:
 
 ```markdown
 ### Default Skills

package/template/{.agent/workflows/create-prd.md → .agents/skills/create-prd/SKILL.md}

@@ -19,7 +19,7 @@ Transform the ideation output into a production-grade architecture design docume
 **Input**: `.memory/wiki/specs/ideation/ideation-index.md` (must exist and be approved)
 **Output**: `.memory/wiki/specs/YYYY-MM-DD-architecture-design.md` + `.memory/wiki/specs/ENGINEERING-STANDARDS.md` + `.memory/wiki/specs/data-placement-strategy.md`
 
-> **Depth standard**: Every section must be specified to the point where a developer cannot misinterpret it. The specificity-standards rule (`.agent/rules/specificity-standards.md`) applies to every word of the output.
+> **Depth standard**: Every section must be specified to the point where a developer cannot misinterpret it. The specificity-standards rule (`.agents/rules/specificity-standards.md`) applies to every word of the output.
 
 ---
 
@@ -42,7 +42,7 @@ Pay special attention to **Project Surfaces** in `meta/constraints.md` — it de
 
 Read `## Engagement Tier` from `ideation-index.md`. If not set, ask the user and write immediately.
 
-Read `.agent/skills/prd-templates/references/engagement-tier-protocol.md` — each shard reads the tier and adapts gates.
+Read `.agents/skills/prd-templates/references/engagement-tier-protocol.md` — each shard reads the tier and adapts gates.
 
 ---
 
@@ -56,7 +56,7 @@ Read the `## Progress Summary` table in `ideation-index.md`. Check these thresho
 | Total leaf features | ≥ 50 |
 | Total surfaces | ≥ 2 (multi-product projects) |
 
-**If ANY threshold is met** → read `.agent/skills/prd-templates/references/deep-ideation-loading-protocol.md` and follow its full procedure. This produces a **Domain Digest Table** written to `.memory/wiki/specs/architecture-draft.md` as `## Ideation Digest`.
+**If ANY threshold is met** → read `.agents/skills/prd-templates/references/deep-ideation-loading-protocol.md` and follow its full procedure. This produces a **Domain Digest Table** written to `.memory/wiki/specs/architecture-draft.md` as `## Ideation Digest`.
 
 **If no threshold is met** → skip this step. The standard `ideation-index.md` read from Step 1 is sufficient.
 
@@ -68,7 +68,7 @@ Read the `## Progress Summary` table in `ideation-index.md`. Check these thresho
 
 Read each skill SKILL.md listed in the frontmatter `skills` array.
 
-Check `.agent/skills/` for stack-specific skills. Read `.agent/skills/find-skills/SKILL.md` for community skill discovery.
+Check `.agents/skills/` for stack-specific skills. Read `.agents/skills/find-skills/SKILL.md` for community skill discovery.
 
 ---
 
@@ -76,11 +76,11 @@ Check `.agent/skills/` for stack-specific skills. Read `.agent/skills/find-skill
 
 | # | Shard | What It Does |
 |---|-------|-------------|
-| 1 | [`create-prd-stack`](.agent/workflows/create-prd-stack.md) | Constraint-first discovery, tech stack decisions with bootstrap firing |
-| 1.5 | [`create-prd-design-system`](.agent/workflows/create-prd-design-system.md) | Navigation paradigm, layout grid, page archetypes, component hierarchy, motion, state design language → `.memory/wiki/specs/design-system.md` |
-| 2 | [`create-prd-architecture`](.agent/workflows/create-prd-architecture.md) | System architecture, data strategy, data placement strategy document |
-| 3 | [`create-prd-security`](.agent/workflows/create-prd-security.md) | Security model, compliance escalation, integration points |
-| 4 | [`create-prd-compile`](.agent/workflows/create-prd-compile.md) | Development methodology, phasing, compile architecture-design.md + ENGINEERING-STANDARDS.md |
+| 1 | [`create-prd-stack`](.agents/skills/create-prd-stack/SKILL.md) | Constraint-first discovery, tech stack decisions with bootstrap firing |
+| 1.5 | [`create-prd-design-system`](.agents/skills/create-prd-design-system/SKILL.md) | Navigation paradigm, layout grid, page archetypes, component hierarchy, motion, state design language → `.memory/wiki/specs/design-system.md` |
+| 2 | [`create-prd-architecture`](.agents/skills/create-prd-architecture/SKILL.md) | System architecture, data strategy, data placement strategy document |
+| 3 | [`create-prd-security`](.agents/skills/create-prd-security/SKILL.md) | Security model, compliance escalation, integration points |
+| 4 | [`create-prd-compile`](.agents/skills/create-prd-compile/SKILL.md) | Development methodology, phasing, compile architecture-design.md + ENGINEERING-STANDARDS.md |
 
 > **Progressive working artifact**: `.memory/wiki/specs/architecture-draft.md` is written incrementally by shards 1–3 and read by shard 4 to compile the final dated `architecture-design.md`.
 
@@ -88,13 +88,13 @@ Check `.agent/skills/` for stack-specific skills. Read `.agent/skills/find-skill
 
 ## Orchestration
 
-Create `.memory/wiki/specs/architecture/prd-working/` directory if it does not exist. Read `.agent/skills/prd-templates/references/workflow-checkpoint-protocol.md` — all shards use this checkpoint system.
+Create `.memory/wiki/specs/architecture/prd-working/` directory if it does not exist. Read `.agents/skills/prd-templates/references/workflow-checkpoint-protocol.md` — all shards use this checkpoint system.
 
-### Step A — Run `.agent/workflows/create-prd-stack.md`
-### Step A.5 — Run `.agent/workflows/create-prd-design-system.md`
-### Step B — Run `.agent/workflows/create-prd-architecture.md`
-### Step C — Run `.agent/workflows/create-prd-security.md`
-### Step D — Run `.agent/workflows/create-prd-compile.md`
+### Step A — Run `.agents/skills/create-prd-stack/SKILL.md`
+### Step A.5 — Run `.agents/skills/create-prd-design-system/SKILL.md`
+### Step B — Run `.agents/skills/create-prd-architecture/SKILL.md`
+### Step C — Run `.agents/skills/create-prd-security/SKILL.md`
+### Step D — Run `.agents/skills/create-prd-compile/SKILL.md`
 
 **Shard failure recovery**: If any shard (A through D) fails mid-execution:
 1. Check `.memory/wiki/specs/architecture/prd-working/workflow-state.md` for the checkpoint — it shows exact step, item, and next action
@@ -108,9 +108,9 @@ Create `.memory/wiki/specs/architecture/prd-working/` directory if it does not e
 
 ### Self-check against Architecture rubric
 
-Read `.agent/skills/pipeline-rubrics/references/architecture-rubric.md` and apply all 15 dimensions as the self-check.
+Read `.agents/skills/pipeline-rubrics/references/architecture-rubric.md` and apply all 15 dimensions as the self-check.
 
-Read `.agent/skills/prd-templates/references/architecture-completeness-checklist.md` and verify all items.
+Read `.agents/skills/prd-templates/references/architecture-completeness-checklist.md` and verify all items.
 
 For any dimension that scores ⚠️ or ❌ → resolve it NOW. Loop back to the relevant shard.
 

package/template/{.agent/workflows/create-prd-architecture.md → .agents/skills/create-prd-architecture/SKILL.md}

@@ -24,7 +24,7 @@ Design the high-level system architecture and data strategy. Create the data pla
 
 ## 0. Map guard
 
-Follow the map guard protocol (`.agent/skills/prd-templates/references/map-guard-protocol.md`). Required cells for this shard:
+Follow the map guard protocol (`.agents/skills/prd-templates/references/map-guard-protocol.md`). Required cells for this shard:
 
 | Map Location | Column/Category | Why this matters |
 |---|---|---|
@@ -34,7 +34,7 @@ Follow the map guard protocol (`.agent/skills/prd-templates/references/map-guard
 
 **HARD GATE** — If ANY required cell is empty → STOP. No timing fallbacks. No conversation-confirmed values. See map guard protocol for recovery.
 
-Read the engagement tier protocol (`.agent/skills/prd-templates/references/engagement-tier-protocol.md`) — apply the tier behavior for architecture decisions.
+Read the engagement tier protocol (`.agents/skills/prd-templates/references/engagement-tier-protocol.md`) — apply the tier behavior for architecture decisions.
 
 ---
 
@@ -45,7 +45,7 @@ Read the engagement tier protocol (`.agent/skills/prd-templates/references/engag
 1. Read `.memory/wiki/specs/ideation/ideation-index.md` — extract: Structure Map (domain list + paths), MoSCoW Summary (full feature inventory), Engagement Tier, persona list
 2. Read `.memory/wiki/specs/ideation/meta/constraints.md` — extract: Project Surfaces, compliance constraints, hard/soft constraints
 3. Read `.memory/wiki/specs/ideation/ideation-cx.md` (global cross-cuts) — extract: cross-domain data dependencies, trigger chains, shared entity ownership. Then read each domain-level `{domain}-cx.md` listed in the Structure Map
-4. If `## Ideation Digest` exists in `.memory/wiki/specs/architecture-draft.md` → use it as the structured feature inventory. Otherwise, read domain index files (`{domain}/{domain}-index.md`) directly per the deep ideation loading protocol (`.agent/skills/prd-templates/references/deep-ideation-loading-protocol.md`)
+4. If `## Ideation Digest` exists in `.memory/wiki/specs/architecture-draft.md` → use it as the structured feature inventory. Otherwise, read domain index files (`{domain}/{domain}-index.md`) directly per the deep ideation loading protocol (`.agents/skills/prd-templates/references/deep-ideation-loading-protocol.md`)
 
 **How this context feeds downstream steps:**
 - Component diagram (4.1) ← domain boundaries from domain indexes, trigger chains from CX files
@@ -57,23 +57,23 @@ Read the engagement tier protocol (`.agent/skills/prd-templates/references/engag
 
 ### Checkpoint resumption
 
-Read `.agent/skills/prd-templates/references/workflow-checkpoint-protocol.md`. Check if `.memory/wiki/specs/architecture/prd-working/workflow-state.md` exists. If it exists and `active_shard` matches this file → follow the resumption procedure. If not → initialize a fresh checkpoint.
+Read `.agents/skills/prd-templates/references/workflow-checkpoint-protocol.md`. Check if `.memory/wiki/specs/architecture/prd-working/workflow-state.md` exists. If it exists and `active_shard` matches this file → follow the resumption procedure. If not → initialize a fresh checkpoint.
 
 ---
 
 ## 4. System architecture
 
-Read `.agent/skills/api-design-principles/SKILL.md` for API surface design.
+Read `.agents/skills/api-design-principles/SKILL.md` for API surface design.
 
 Design the high-level system. Each sub-item requires full exploration, not a summary sentence:
 
 1. **Component diagram** — What services exist? How do they communicate? What protocols? What happens if one is down?
 2. **Data flow** — Request lifecycle from client to database and back. Every hop, every transformation, every auth check along the way. Draw the full sequence.
 3. **Deployment topology** — What runs where? Edge? Origin? External? Local machine? App Store? What are the latency implications? What are the cost implications?
-   Load the Hosting skill(s) from the cross-cutting section per the skill loading protocol (`.agent/skills/prd-templates/references/skill-loading-protocol.md`).
-   Read .agent/skills/technical-writer/SKILL.md and follow its methodology.
+   Load the Hosting skill(s) from the cross-cutting section per the skill loading protocol (`.agents/skills/prd-templates/references/skill-loading-protocol.md`).
+   Read .agents/skills/technical-writer/SKILL.md and follow its methodology.
 4. **API surface** — REST? GraphQL? RPC? Versioning strategy? Error format? Pagination? Rate limit headers?
-5. **Deployment strategy** — Rolling? Blue-green? Canary? Read `.agent/skills/deployment-procedures/SKILL.md` Section 6 for the strategy options and selection matrix. Ask:
+5. **Deployment strategy** — Rolling? Blue-green? Canary? Read `.agents/skills/deployment-procedures/SKILL.md` Section 6 for the strategy options and selection matrix. Ask:
    - "Which zero-downtime deployment strategy fits your risk profile? Rolling (standard), Blue-Green (easy rollback), or Canary (validate with real traffic)?"
    - "Do you want feature flags for controlled rollout of risky features? If yes, which provider (or build your own)?"
    - "What is your rollback trigger? Error rate spike above N%? Latency threshold? Manual decision?"
@@ -93,23 +93,23 @@ For each component, also define:
 - "Are there failure modes I haven't accounted for?"
 - For multi-surface: "What happens if the sync layer goes down? Can each surface degrade gracefully?"
 
-Follow the decision confirmation protocol (`.agent/skills/prd-templates/references/decision-confirmation-protocol.md`) — do not write until explicitly confirmed.
+Follow the decision confirmation protocol (`.agents/skills/prd-templates/references/decision-confirmation-protocol.md`) — do not write until explicitly confirmed.
 
-Write the completed `## System Architecture` section to `.memory/wiki/specs/architecture-draft.md` (create the file if it does not exist). Do not wait until the end — write this section as soon as it is completed and confirmed by the user. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+Write the completed `## System Architecture` section to `.memory/wiki/specs/architecture-draft.md` (create the file if it does not exist). Do not wait until the end — write this section as soon as it is completed and confirmed by the user. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
-> **Decision recording**: For each non-trivial architecture decision (technology choices, deployment topology, API style, failure handling strategy), read `.agent/skills/session-continuity/protocols/06-decision-analysis.md` and follow the **Decision Effect Analysis Protocol**. Architecture decisions have the highest downstream impact in the pipeline — record them to `.memory/wiki/decisions.md` with the Philosopher + Devil's Advocate deliberation.
+> **Decision recording**: For each non-trivial architecture decision (technology choices, deployment topology, API style, failure handling strategy), read `.agents/skills/session-continuity/protocols/06-decision-analysis.md` and follow the **Decision Effect Analysis Protocol**. Architecture decisions have the highest downstream impact in the pipeline — record them to `.memory/wiki/decisions.md` with the Philosopher + Devil's Advocate deliberation.
 
 ## 4.5. Error architecture
 
 > **Hard gate.** This step is mandatory for every project. All five decisions below must be confirmed by the user before `## 5. Data strategy` begins. Do not proceed to Data Strategy until every decision is explicitly approved.
 
-Read `.agent/skills/error-handling-patterns/SKILL.md` and follow its Error Architecture Interview methodology. All 5 decisions must receive explicit user confirmation before proceeding to Data Strategy. This step is a hard gate — do not proceed until all five decisions are confirmed.
+Read `.agents/skills/error-handling-patterns/SKILL.md` and follow its Error Architecture Interview methodology. All 5 decisions must receive explicit user confirmation before proceeding to Data Strategy. This step is a hard gate — do not proceed until all five decisions are confirmed.
 
-Write the completed decisions to `.memory/wiki/specs/architecture-draft.md` under a new top-level `## Error Architecture` section (between `## System Architecture` and `## Data Strategy`). The section must contain five sub-sections matching the five decisions above (`### Global Error Envelope`, `### Error Propagation Chain`, `### Unhandled Exception Strategy`, `### Client Fallback Contract`, `### Error Boundary Strategy`), with the locked canonical JSON example included verbatim under `### Global Error Envelope`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+Write the completed decisions to `.memory/wiki/specs/architecture-draft.md` under a new top-level `## Error Architecture` section (between `## System Architecture` and `## Data Strategy`). The section must contain five sub-sections matching the five decisions above (`### Global Error Envelope`, `### Error Propagation Chain`, `### Unhandled Exception Strategy`, `### Client Fallback Contract`, `### Error Boundary Strategy`), with the locked canonical JSON example included verbatim under `### Global Error Envelope`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ## 5. Data strategy
 
-Read .agent/skills/database-schema-design/SKILL.md and follow its schema design methodology.
+Read .agents/skills/database-schema-design/SKILL.md and follow its schema design methodology.
 
 **Digest-aware entity identification**: If `## Ideation Digest` exists in `.memory/wiki/specs/architecture-draft.md`, use its Key Entities column and Cross-Domain Dependencies table as the primary source for entity identification in sub-steps below. Cross-reference the digest's per-domain feature lists to ensure no entity is missed. If the digest does not exist, derive entities from the architecture sections written above.
 
@@ -130,19 +130,19 @@ For multi-surface projects, additionally define:
 - "Does every entity have a clear owner?"
 - "Are there query patterns I'm missing that could become hot paths?"
 
-Follow the decision confirmation protocol (`.agent/skills/prd-templates/references/decision-confirmation-protocol.md`) — do not write until explicitly confirmed.
+Follow the decision confirmation protocol (`.agents/skills/prd-templates/references/decision-confirmation-protocol.md`) — do not write until explicitly confirmed.
 
-Write the completed `## Data Strategy` section to `.memory/wiki/specs/architecture-draft.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+Write the completed `## Data Strategy` section to `.memory/wiki/specs/architecture-draft.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ### 5.5. Cross-Store Entity Consistency
 
-Read .agent/skills/database-schema-design/SKILL.md and follow its Cross-Store Entity Consistency Protocol for every entity that spans more than one store.
+Read .agents/skills/database-schema-design/SKILL.md and follow its Cross-Store Entity Consistency Protocol for every entity that spans more than one store.
 
-Write the completed cross-store consistency table to `.memory/wiki/specs/architecture-draft.md` as part of the `## Data Strategy` section. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+Write the completed cross-store consistency table to `.memory/wiki/specs/architecture-draft.md` as part of the `## Data Strategy` section. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ### Data placement strategy document
 
-Read `.agent/skills/prd-templates/references/data-placement-template.md` for the template structure. Create `.memory/wiki/specs/data-placement-strategy.md` using the template, filling each section with the data decisions confirmed above.
+Read `.agents/skills/prd-templates/references/data-placement-template.md` for the template structure. Create `.memory/wiki/specs/data-placement-strategy.md` using the template, filling each section with the data decisions confirmed above.
 
 ## Completion Gate (MANDATORY)
 

package/template/{.agent/workflows/create-prd-compile.md → .agents/skills/create-prd-compile/SKILL.md}

@@ -28,7 +28,7 @@ Verify `.memory/wiki/specs/architecture-draft.md` exists. If it does not → **S
 
 ## 0. Map guard
 
-Follow the map guard protocol (`.agent/skills/prd-templates/references/map-guard-protocol.md`). Required cells for this shard:
+Follow the map guard protocol (`.agents/skills/prd-templates/references/map-guard-protocol.md`). Required cells for this shard:
 
 | Map Location | Column/Category | Why this matters |
 |---|---|---|
@@ -38,28 +38,28 @@ Follow the map guard protocol (`.agent/skills/prd-templates/references/map-guard
 
 **HARD GATE** — If ANY required cell is empty → STOP. No timing fallbacks. No conversation-confirmed values. See map guard protocol for recovery.
 
-Read the engagement tier protocol (`.agent/skills/prd-templates/references/engagement-tier-protocol.md`) — apply the tier behavior for compile decisions.
+Read the engagement tier protocol (`.agents/skills/prd-templates/references/engagement-tier-protocol.md`) — apply the tier behavior for compile decisions.
 
 ### Checkpoint resumption
 
-Read `.agent/skills/prd-templates/references/workflow-checkpoint-protocol.md`. Check if `.memory/wiki/specs/architecture/prd-working/workflow-state.md` exists. If it exists and `active_shard` matches this file → follow the resumption procedure (skip completed sections, resume from `next_action`). If not → initialize a fresh checkpoint.
+Read `.agents/skills/prd-templates/references/workflow-checkpoint-protocol.md`. Check if `.memory/wiki/specs/architecture/prd-working/workflow-state.md` exists. If it exists and `active_shard` matches this file → follow the resumption procedure (skip completed sections, resume from `next_action`). If not → initialize a fresh checkpoint.
 
 ---
 
 ## 8. Development methodology
 
-Read .agent/skills/tdd-workflow/SKILL.md and follow its methodology.
+Read .agents/skills/tdd-workflow/SKILL.md and follow its methodology.
 
 Document the agreed approach:
 
 1. **Contract-first** — Zod schemas (or equivalent) before implementation
 2. **TDD** — Failing tests before code
-   Load the Unit Tests and E2E Tests skill(s) from the surface stack map per the skill loading protocol (`.agent/skills/prd-templates/references/skill-loading-protocol.md`).
+   Load the Unit Tests and E2E Tests skill(s) from the surface stack map per the skill loading protocol (`.agents/skills/prd-templates/references/skill-loading-protocol.md`).
 3. **Vertical slices** — All surfaces per feature
 4. **Spec layers** — IA → BE → FE pipeline
 5. **Quality gates** — What must pass before merge
 
-Write the completed `## Development Methodology` section to `.memory/wiki/specs/architecture-draft.md` immediately after user confirmation. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+Write the completed `## Development Methodology` section to `.memory/wiki/specs/architecture-draft.md` immediately after user confirmation. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ## 8.5. Ideation context reload for phasing
 
@@ -96,9 +96,9 @@ Each phase should have a rough timeline estimate and must pass the full validati
 - "Are there features in Phase 2 that actually depend on something not in Phase 1?"
 - "Is the Phase 1 scope achievable without cutting quality?"
 
-Follow the decision confirmation protocol (`.agent/skills/prd-templates/references/decision-confirmation-protocol.md`) — do not write until explicitly confirmed.
+Follow the decision confirmation protocol (`.agents/skills/prd-templates/references/decision-confirmation-protocol.md`) — do not write until explicitly confirmed.
 
-Write the completed `## Phasing Strategy` section to `.memory/wiki/specs/architecture-draft.md` immediately after user confirmation. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+Write the completed `## Phasing Strategy` section to `.memory/wiki/specs/architecture-draft.md` immediately after user confirmation. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ## 9.5. Lock project directory structure
 
@@ -108,16 +108,16 @@ Based on the locked tech stack, generate a canonical directory tree.
 2. Present the tree to the user with one-line descriptions per top-level directory. Adapt the tree to the actual stack — e.g., a CLI project won't have `components/`, a monorepo will have `apps/` and `packages/`
 3. Build an architecture separation table mapping each concern to its directory and runtime
 4. **Present to user**: Show the directory tree and architecture table. Ask: "Does this structure match your expectations?" **Do not proceed until explicit approval.**
-5. After approval, fire bootstrap with: `PROJECT_STRUCTURE`, `ARCHITECTURE_TABLE`, `CONTRACTS_DIR`, `BUILD_OUTPUT_DIR`. **HARD GATE**: Follow the bootstrap verification protocol (`.agent/skills/prd-templates/references/bootstrap-verification-protocol.md`) — verify all 4 keys.
+5. After approval, fire bootstrap with: `PROJECT_STRUCTURE`, `ARCHITECTURE_TABLE`, `CONTRACTS_DIR`, `BUILD_OUTPUT_DIR`. **HARD GATE**: Follow the bootstrap verification protocol (`.agents/skills/prd-templates/references/bootstrap-verification-protocol.md`) — verify all 4 keys.
 6. Append a `## Directory Structure` section to `.memory/wiki/specs/architecture-draft.md`
 
 > If invoked standalone, surface via `notify_user`.
 
 ## 10. Compile architecture design document
 
-Read .agent/skills/technical-writer/SKILL.md and follow its methodology.
+Read .agents/skills/technical-writer/SKILL.md and follow its methodology.
 
-Read .agent/skills/technical-writer/SKILL.md and apply its clarity and structure standards throughout document compilation.
+Read .agents/skills/technical-writer/SKILL.md and apply its clarity and structure standards throughout document compilation.
 
 Read `.memory/wiki/specs/architecture-draft.md` as the authoritative source.
 
@@ -130,13 +130,13 @@ Read `.memory/wiki/specs/architecture-draft.md` as the authoritative source.
 
 If any required section is missing → **STOP**: "architecture-draft.md is missing `[section]`. This section should have been written by a previous shard. Run the relevant shard: architecture → `/create-prd-architecture`, security → `/create-prd-security`."
 
-Read `.agent/skills/prd-templates/references/architecture-design-template.md` for the document structure. Compile it into `.memory/wiki/specs/YYYY-MM-DD-architecture-design.md` (use today's date).
+Read `.agents/skills/prd-templates/references/architecture-design-template.md` for the document structure. Compile it into `.memory/wiki/specs/YYYY-MM-DD-architecture-design.md` (use today's date).
 
 > **Depth rule**: Each section must contain the full detail gathered during steps 3-9. If a section is under 200 words, it's almost certainly too shallow. Apply the two-implementer test.
 
 ## 10.5. Performance budget interview
 
-Read `.agent/skills/performance-budgeting/SKILL.md` and follow its Interview Protocol for all applicable axes.
+Read `.agents/skills/performance-budgeting/SKILL.md` and follow its Interview Protocol for all applicable axes.
 
 Surface conditioning rules and the write-as-you-go rule are defined in the skill.
 
@@ -146,15 +146,15 @@ Write each confirmed axis to `.memory/wiki/specs/ENGINEERING-STANDARDS.md` immed
 
 ## 11. Compile Engineering Standards
 
-Read .agent/skills/technical-writer/SKILL.md and follow its methodology.
+Read .agents/skills/technical-writer/SKILL.md and follow its methodology.
 
-Read `.agent/skills/prd-templates/references/engineering-standards-template.md` for the document structure. Create `.memory/wiki/specs/ENGINEERING-STANDARDS.md` — the non-negotiable quality bar for the project. Fill in concrete values based on tech stack decisions from step 3 and methodology from step 8. **No TBDs allowed.**
+Read `.agents/skills/prd-templates/references/engineering-standards-template.md` for the document structure. Create `.memory/wiki/specs/ENGINEERING-STANDARDS.md` — the non-negotiable quality bar for the project. Fill in concrete values based on tech stack decisions from step 3 and methodology from step 8. **No TBDs allowed.**
 
 ## 12. Request review and propose next steps
 
-Read `.agent/skills/pipeline-rubrics/SKILL.md` and follow its pre-flight self-check protocol for the Architecture rubric.
+Read `.agents/skills/pipeline-rubrics/SKILL.md` and follow its pre-flight self-check protocol for the Architecture rubric.
 
-Run a pre-flight self-check before presenting. Read `.agent/skills/pipeline-rubrics/references/architecture-rubric.md` and apply each of the 15 dimensions as a self-check.
+Run a pre-flight self-check before presenting. Read `.agents/skills/pipeline-rubrics/references/architecture-rubric.md` and apply each of the 15 dimensions as a self-check.
 
 > ❌ **STOP** — If any dimension scores ⚠️ or ❌, do not call `notify_user`. Fix the gap now and re-run the self-check until all 15 dimensions are ✅.
 

package/template/{.agent/workflows/create-prd-design-system.md → .agents/skills/create-prd-design-system/SKILL.md}

@@ -19,25 +19,25 @@ pipeline:
 
 Establish the structural UI architecture — navigation paradigm, layout grid, page archetypes, global component inventory, motion language, data density philosophy, and global state design language. Produces `.memory/wiki/specs/design-system.md` which all FE specs must consume.
 
-**Prerequisite**: Tech stack decisions must be locked (`/create-prd-stack` completed). Design direction must be confirmed in `.agent/skills/brand-guidelines/SKILL.md`.
+**Prerequisite**: Tech stack decisions must be locked (`/create-prd-stack` completed). Design direction must be confirmed in `.agents/skills/brand-guidelines/SKILL.md`.
 
 ---
 
 ## 0. Prerequisite check
 
-1. Read `.agent/skills/brand-guidelines/SKILL.md`.
+1. Read `.agents/skills/brand-guidelines/SKILL.md`.
 2. Scan for any `{{PLACEHOLDER}}` values that are still unfilled. If any exist → **stop** and tell the user: _"Design direction hasn't been confirmed yet. Run `/create-prd-stack` first to establish the design direction before designing the system."_
 3. If all placeholders are filled → extract and store for this session: the confirmed `DESIGN_DIRECTION`, color palette, typography choices, motion philosophy, and anti-patterns.
 
 Read `## Engagement Tier` from `.memory/wiki/specs/ideation/ideation-index.md`.
 
-Read the engagement tier protocol (`.agent/skills/prd-templates/references/engagement-tier-protocol.md`) — apply the tier behavior for design system decisions (all 7 decisions are product decisions).
+Read the engagement tier protocol (`.agents/skills/prd-templates/references/engagement-tier-protocol.md`) — apply the tier behavior for design system decisions (all 7 decisions are product decisions).
 
 1. Read `.memory/wiki/specs/ideation/meta/constraints.md` — extract the **Project Surfaces** section. Read `.memory/wiki/specs/ideation/ideation-index.md` — extract the feature inventory from the MoSCoW Summary.
-2. Read `.agent/skills/brand-guidelines/SKILL.md` — extract the confirmed `DESIGN_DIRECTION`.
-3. Read `.agent/skills/design-direction/SKILL.md` — for direction characteristics and anti-patterns.
-4. Read `.agent/skills/technical-writer/SKILL.md` — for document writing conventions.
-5. Read `.agent/skills/prd-templates/references/design-system-decisions.md` — all decision option menus and the output template for `.memory/wiki/specs/design-system.md`.
+2. Read `.agents/skills/brand-guidelines/SKILL.md` — extract the confirmed `DESIGN_DIRECTION`.
+3. Read `.agents/skills/design-direction/SKILL.md` — for direction characteristics and anti-patterns.
+4. Read `.agents/skills/technical-writer/SKILL.md` — for document writing conventions.
+5. Read `.agents/skills/prd-templates/references/design-system-decisions.md` — all decision option menus and the output template for `.memory/wiki/specs/design-system.md`.
 6. Note which surfaces are in scope from `## Project Surfaces`.
 
 ### Ideation workflow context
@@ -53,7 +53,7 @@ Read the engagement tier protocol (`.agent/skills/prd-templates/references/engag
 
 ### Checkpoint resumption
 
-Read `.agent/skills/prd-templates/references/workflow-checkpoint-protocol.md`. Check if `.memory/wiki/specs/architecture/prd-working/workflow-state.md` exists. If it exists and `active_shard` matches this file → follow the resumption procedure (skip completed decisions, resume from `next_action`). If not → initialize a fresh checkpoint.
+Read `.agents/skills/prd-templates/references/workflow-checkpoint-protocol.md`. Check if `.memory/wiki/specs/architecture/prd-working/workflow-state.md` exists. If it exists and `active_shard` matches this file → follow the resumption procedure (skip completed decisions, resume from `next_action`). If not → initialize a fresh checkpoint.
 
 ### Per-decision Ideation Synthesis requirement
 
@@ -75,7 +75,7 @@ Present surface-appropriate options from the **Navigation Paradigm Options** sec
 
 **Wait for explicit user confirmation before proceeding** *(Interactive/Hybrid)* or auto-confirm with Deep Think *(Auto)*.
 
-On confirmation, write the `## Navigation Paradigm` section to `.memory/wiki/specs/design-system.md` immediately. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+On confirmation, write the `## Navigation Paradigm` section to `.memory/wiki/specs/design-system.md` immediately. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ---
 
@@ -90,7 +90,7 @@ Provide a **default recommendation** based on the confirmed design direction:
 
 **Wait for explicit user confirmation before proceeding.**
 
-On confirmation, write the `## Layout Grid` table to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+On confirmation, write the `## Layout Grid` table to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ---
 
@@ -100,7 +100,7 @@ Based on the feature inventory from `ideation-index.md`, propose a named archety
 
 Present the proposed archetypes to the user. Ask whether any are missing or should be renamed. **Wait for explicit user confirmation before proceeding.**
 
-On confirmation, write the `## Page Archetypes` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+On confirmation, write the `## Page Archetypes` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ---
 
@@ -112,7 +112,7 @@ Present the derived list. Ask: (1) Are any components missing? (2) Should any be
 
 **Wait for explicit user confirmation before proceeding.**
 
-On confirmation, write the `## Global Component Inventory` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`). This serves as the **Component Inventory Seed** — all FE specs must consume (not re-invent) these global components.
+On confirmation, write the `## Global Component Inventory` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`). This serves as the **Component Inventory Seed** — all FE specs must consume (not re-invent) these global components.
 
 ---
 
@@ -120,7 +120,7 @@ On confirmation, write the `## Global Component Inventory` section to `.memory/w
 
 Present the options from the **Motion Language Options** in `design-system-decisions.md`. Present a recommendation based on the confirmed design direction. **Wait for explicit user confirmation before proceeding.**
 
-On confirmation, write the `## Motion Language` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+On confirmation, write the `## Motion Language` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ---
 
@@ -128,7 +128,7 @@ On confirmation, write the `## Motion Language` section to `.memory/wiki/specs/d
 
 Present the options from the **Data Density Options** in `design-system-decisions.md`. If **Hybrid** is selected, ask the user to define per-archetype density rules. **Wait for explicit user confirmation before proceeding.**
 
-On confirmation, write the `## Data Density Philosophy` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+On confirmation, write the `## Data Density Philosophy` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ---
 
@@ -136,7 +136,7 @@ On confirmation, write the `## Data Density Philosophy` section to `.memory/wiki
 
 Two-part decision. Present the loading state, error state, and empty state options from the **Global State Design Language Options** in `design-system-decisions.md`. Present recommendations based on the confirmed design direction. **Wait for explicit user confirmation before proceeding.**
 
-On confirmation, write the `## Global State Design Language` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`).
+On confirmation, write the `## Global State Design Language` section to `.memory/wiki/specs/design-system.md`. Follow the write verification protocol (`.agents/skills/prd-templates/references/write-verification-protocol.md`).
 
 ---