opencodekit 0.15.0 → 0.15.2

package/dist/template/.opencode/command/create.md

@@ -60,7 +60,9 @@ bd create "[title]" -t epic -p 1
 
 ## Create Spec
 
-Write `.beads/artifacts/<bead-id>/spec.md`:
+Write `.beads/artifacts/<bead-id>/spec.md`.
+
+Treat `spec.md` as a **short task card** (one screen): goal + success criteria + constraints. Put the detailed plan and task breakdown in `prd.md`.
 
 ```markdown
 # [Title]
@@ -84,9 +86,16 @@ Write `.beads/artifacts/<bead-id>/spec.md`:
 **Must:** [required]
 **Never:** [forbidden]
 
+## PRD (Optional)
+
+If this task has a PRD, keep details there:
+
+- `.beads/artifacts/<bead-id>/prd.md`
+- `.beads/artifacts/<bead-id>/prd.json` (generated)
+
 ## Notes
 
-[context if needed]
+[only brief context here; details belong in prd.md]
 ```
 
 ## If Epic: Create Subtasks
@@ -104,6 +113,30 @@ Visualize:
 
 !`bd dep tree bd-[epic]`
 
+## Optional: Create a PRD (Recommended for features)
+
+If the work is more than a small one-off change, create a PRD alongside the spec.
+
+- Template: `.opencode/memory/_templates/prd.md`
+- Output: `.beads/artifacts/<bead-id>/prd.md`
+
+```typescript
+skill({ name: "prd" });
+```
+
+Write the PRD so it includes a `## Tasks` section (each `### ... [category]` with `**Verification:**` bullets).
+
+After PRD is written, convert it to executable tasks:
+
+```typescript
+skill({ name: "prd-task" });
+```
+
+This generates:
+
+- `.beads/artifacts/<bead-id>/prd.json`
+- `.beads/artifacts/<bead-id>/progress.txt`
+
 ## Sync
 
 ```bash
@@ -119,7 +152,9 @@ Type: [task/bug/feature/epic]
 Priority: [0-4]
 Spec: .beads/artifacts/bd-[id]/spec.md
 
-Next: /implement bd-[id]
+Next:
+- `/start bd-[id]` (recommended)
+- or `/implement bd-[id]` (direct implementation)
 ```
 
 If epic with subtasks:

package/dist/template/.opencode/command/design-audit.md

@@ -474,7 +474,7 @@ Save outputs to:
 
 | Need                   | Skill                 |
 | ---------------------- | --------------------- |
-| Aesthetic improvements | `frontend-aesthetics` |
+| Aesthetic improvements | `frontend-design` |
 | Implement from mockup  | `mockup-to-code`      |
 | Accessibility audit    | `accessibility-audit` |
 | Visual analysis        | `visual-analysis`     |

package/dist/template/.opencode/command/design.md

@@ -55,7 +55,7 @@ read({ filePath: "src/styles/globals.css" });
 
 ## Phase 2: Aesthetic Direction (DECISION GATE)
 
-skill({ name: "frontend-aesthetics" })
+skill({ name: "frontend-design" })
 
 **BEFORE any design work, you MUST state:**
 

package/dist/template/.opencode/command/finish.md

@@ -76,6 +76,14 @@ Read the spec and check each criterion:
 
 For each success criterion listed, run its verification. All must pass. If something's missing, go back and implement it.
 
+## If PRD Tasks Exist
+
+If `.beads/artifacts/$ARGUMENTS/prd.json` exists:
+
+- Ensure every task has `passes: true`
+- If tasks remain incomplete, do NOT close the bead yet
+- Continue with: `/complete-next-task $ARGUMENTS`
+
 ## Review Changes (Ask Before Commit)
 
 Show what would be committed:

package/dist/template/.opencode/command/frontend-design.md

@@ -0,0 +1,21 @@
+---
+description: Create distinctive, production-grade frontend interfaces
+argument-hint: "[component/page description]"
+agent: build
+---
+
+# Frontend Design: $ARGUMENTS
+
+Create UI components, pages, or applications with React, Tailwind CSS v4, shadcn/ui, and Motion.
+
+## Load Skill
+
+```typescript
+skill({ name: "frontend-design" });
+```
+
+Then follow the skill instructions to create the interface.
+
+<user-request>
+$ARGUMENTS
+</user-request>

package/dist/template/.opencode/command/index-knowledge.md

@@ -0,0 +1,25 @@
+---
+description: Generate hierarchical AGENTS.md knowledge base
+argument-hint: "[optional focus or notes]"
+agent: plan
+---
+
+# Index Knowledge: $ARGUMENTS
+
+Generate or refresh hierarchical `AGENTS.md` files for this codebase.
+
+## Load Skill
+
+```typescript
+skill({ name: "index-knowledge" });
+```
+
+Then follow the skill workflow to:
+
+- Analyze the repo structure
+- Identify subsystem boundaries
+- Generate/refresh `AGENTS.md` files (root + nested where appropriate)
+
+<user-request>
+$ARGUMENTS
+</user-request>

package/dist/template/.opencode/command/init.md

@@ -140,6 +140,12 @@ Detected subsystems that may benefit from nested AGENTS.md:
 Create nested AGENTS.md files? (y/n)
 ```
 
+### Optional Follow-Up: Index Knowledge
+
+If the repo is large or keeps changing (monorepos especially), generate/refresh hierarchical `AGENTS.md` using:
+
+- `/index-knowledge`
+
 ## Phase 5: Populate Memory Files
 
 ### .opencode/memory/user.md

package/dist/template/.opencode/command/opensrc.md

@@ -0,0 +1,58 @@
+---
+description: Clone a repo and enhance with AGENTS.md knowledge base
+---
+
+Clone a repository using opensrc and generate hierarchical AGENTS.md documentation.
+
+## Workflow
+
+### Step 1: Load opensrc skill
+
+```
+skill({ name: 'opensrc' })
+```
+
+### Step 2: Clone the repository
+
+```bash
+npx opensrc <repo>
+```
+
+Where `<repo>` is extracted from the user request (supports `owner/repo`, `github:owner/repo`, full URL, etc.)
+
+### Step 3: Navigate to cloned repo
+
+After clone completes, cd into the repo:
+
+```bash
+cd opensrc/repos/github.com/<owner>/<repo>/
+```
+
+Parse owner/repo from the input or from `opensrc/sources.json` after clone.
+
+### Step 4: Load index-knowledge skill
+
+```
+skill({ name: 'index-knowledge' })
+```
+
+Execute in **update mode** (default) - modify existing AGENTS.md + create new where warranted.
+
+### Step 5: Report completion
+
+```
+=== opensrc Complete ===
+
+Repository: <owner>/<repo>
+Location: opensrc/repos/github.com/<owner>/<repo>/
+
+AGENTS.md files generated:
+  ✓ ./AGENTS.md (root)
+  ✓ ./src/... (if applicable)
+
+The repository is now enhanced with agent context.
+```
+
+<user-request>
+$ARGUMENTS
+</user-request>

package/dist/template/.opencode/command/skill-create.md

@@ -19,13 +19,13 @@ Skills are process instructions that:
 
 ## Prerequisites
 
-Load the skill-writing skill first:
+Load the skill-creator skill first:
 
 ```typescript
-skill({ name: "writing-skills" });
+skill({ name: "skill-creator" });
 ```
 
-This provides the TDD framework for skill creation.
+This provides the framework for skill creation.
 
 ## Phase 1: Define the Problem
 

package/dist/template/.opencode/command/skill-optimize.md

@@ -10,10 +10,10 @@ Improve an existing skill to be more effective, concise, and resistant to agent
 
 ## Prerequisites
 
-Load the skill-writing methodology:
+Load the skill-creator skill:
 
 ```typescript
-skill({ name: "writing-skills" });
+skill({ name: "skill-creator" });
 ```
 
 ## Phase 1: Locate and Load Current Skill

package/dist/template/.opencode/command/start.md

@@ -206,6 +206,9 @@ Task({
 Look for:
 
 - `spec.md` - Requirements and constraints
+- `prd.md` - PRD (optional, recommended for features)
+- `prd.json` - PRD tasks (generated from prd.md)
+- `progress.txt` - PRD execution progress (append-only)
 - `research.md` - Previous research
 - `plan.md` - Implementation plan
 - `handoffs/` - Previous session handoffs
@@ -250,6 +253,11 @@ memory -
 
 If memory search fails (Ollama not running), continue without it.
 
+## PRD Tasks (If Present)
+
+- If `.beads/artifacts/$ARGUMENTS/prd.json` exists: next is `/complete-next-task $ARGUMENTS`.
+- If `.beads/artifacts/$ARGUMENTS/prd.md` exists but `prd.json` does not: generate tasks with `prd-task` (see `/create` for the full PRD workflow).
+
 ## Determine Next Step
 
 Based on task type and what exists:
@@ -264,12 +272,13 @@ Based on task type and what exists:
 
 ### For Tasks/Subtasks (leaf work)
 
-| Artifacts Found       | Next Command            |
-| --------------------- | ----------------------- |
-| Nothing               | `/research $ARGUMENTS`  |
-| Only spec.md          | `/plan $ARGUMENTS`      |
-| spec.md + research.md | `/plan $ARGUMENTS`      |
-| plan.md exists        | `/implement $ARGUMENTS` |
+| Artifacts Found       | Next Command                     |
+| --------------------- | -------------------------------- |
+| Nothing               | `/research $ARGUMENTS`           |
+| Only spec.md          | `/plan $ARGUMENTS`               |
+| spec.md + research.md | `/plan $ARGUMENTS`               |
+| plan.md exists        | `/implement $ARGUMENTS`          |
+| prd.json exists       | `/complete-next-task $ARGUMENTS` |
 
 ## Output
 

package/dist/template/.opencode/command/ui-review.md

@@ -17,7 +17,7 @@ skill({ name: "beads" }); // Session protocol
 ```
 
 ```typescript
-skill({ name: "frontend-aesthetics" });
+skill({ name: "frontend-design" });
 skill({ name: "visual-analysis" });
 skill({ name: "accessibility-audit" });
 ```

package/dist/template/.opencode/memory/_templates/prd.md

@@ -1,26 +1,24 @@
-# Task PRD Template
+# Beads PRD Template
 
-**Task ID:** [auto-generated]
+**Bead:** bd-[id]
 **Created:** [date]
-**Status:** To Do
+**Status:** Draft
 
 ## Goal
 
-What exactly are we building and why does it exist in the product?
+What exactly are we building and why does it exist?
 
 ## Scope
 
-### In-Scope:
+### In-Scope
 
 - [List what's allowed]
 
-### Out-of-Scope:
+### Out-of-Scope
 
 - [List what's explicitly off-limits]
 
-## User Flow
-
-The literal step-by-step of what the user sees/does:
+## User Flow (if user-facing)
 
 1. [Step 1]
 2. [Step 2]
@@ -28,16 +26,54 @@ The literal step-by-step of what the user sees/does:
 
 ## Success Criteria
 
-The exact conditions under which I consider this done:
-
 - [ ] [Specific, measurable criteria 1]
+  - Verify: `[command or manual check]`
 - [ ] [Specific, measurable criteria 2]
-- [ ] [Specific, measurable criteria 3]
+  - Verify: `[command or manual check]`
+
+## Technical Context
+
+### Existing Patterns
+
+- Pattern 1: `src/path/to/example.ts` - Why relevant
 
-## Dependencies
+### Key Files
 
-- [List any prerequisites or blocking tasks]
+- `src/relevant/file.ts` - Why relevant
+
+## Risks
+
+- [Risk 1 + mitigation]
 
 ## Notes
 
 [Additional context or constraints]
+
+---
+
+## Tasks
+
+Write tasks in a machine-convertible format for `prd-task`.
+
+Rules:
+
+- Each task is a `### <Title> [category]` heading.
+- Provide one sentence describing the end state.
+- Include `**Verification:**` with bullet steps proving it works.
+
+### <Task Title> [category]
+
+<One sentence describing the end state>
+
+**Verification:**
+
+- [Command or check]
+- [Command or check]
+
+### <Task Title> [category]
+
+<One sentence describing the end state>
+
+**Verification:**
+
+- [Command or check]