@papi-ai/server 0.5.0 → 0.5.2

package/package.json

@@ -1,13 +1,13 @@
 {
   "name": "@papi-ai/server",
-  "version": "0.5.0",
+  "version": "0.5.2",
   "description": "PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects",
   "license": "Elastic-2.0",
   "type": "module",
   "main": "./dist/index.js",
   "exports": {
     ".": "./dist/index.js",
-    "./prompts": "./src/prompts.ts"
+    "./prompts": "./dist/prompts.js"
   },
   "bin": {
     "papi-server": "./dist/index.js"
@@ -19,6 +19,7 @@
   ],
   "scripts": {
     "build": "tsup",
+    "build:prompts": "tsup src/prompts.ts --format esm",
     "start": "node dist/index.js",
     "test": "vitest run",
     "test:watch": "vitest",

package/skills/check-mcp.md

@@ -0,0 +1,46 @@
+---
+name: check-mcp
+description: >
+  Verify the PAPI MCP server is running and healthy.
+  Use when the user says "check mcp", "is papi running", "mcp status",
+  or at the start of any session that needs PAPI tools.
+  Also use proactively if PAPI MCP tools are expected but not appearing.
+invocable: true
+---
+
+# Check MCP Server Health
+
+Run these steps in order and report the result clearly.
+
+## Step 1: Read config
+
+Read `.mcp.json` from the project root. Extract the server command, args, and env vars.
+
+If `.mcp.json` doesn't exist, stop and report: "No MCP server configured. Create .mcp.json to connect PAPI."
+
+## Step 2: Check connection
+
+Look at the available tools list. If PAPI MCP tools (like `orient`, `plan`, `build_list`, `build_execute`) are present, the server is connected.
+
+If not, tell the user:
+
+"PAPI MCP server is configured but not connected. Try one of these:
+1. Restart Claude Code (close and reopen)
+2. In VS Code: Cmd+Shift+P → 'Developer: Reload Window'
+3. Check that npx can run: `npx @papi-ai/server --help`"
+
+## Step 3: Quick health check
+
+If tools are available, run `orient` to verify the server can reach the database and return project state.
+
+If orient fails, check:
+- Is `PAPI_DATA_API_KEY` set in `.mcp.json` env?
+- Is the API key valid? (Try regenerating from the dashboard onboarding page)
+
+## Step 4: Report
+
+Summarise with one of:
+- **Healthy**: Server configured, tools available, database connected
+- **Configured but disconnected**: .mcp.json exists, tools not showing — needs restart
+- **Connection error**: Tools available but database unreachable — check API key
+- **Not configured**: No .mcp.json found

package/skills/{sprint-status.md → cycle-status.md}

@@ -1,31 +1,31 @@
 ---
-name: sprint-status
+name: cycle-status
 description: >
-  Show current sprint health, board state, and recommended next action.
-  Use when the user says /sprint-status, "what's the status", "where are we",
-  "sprint health", or at the start of a session to orient.
+  Show current cycle health, board state, and recommended next action.
+  Use when the user says /cycle-status, "what's the status", "where are we",
+  "cycle health", or at the start of a session to orient.
 invocable: true
 ---
 
-# /sprint-status — Sprint Health Check
+# /cycle-status — Cycle Health Check
 
 Run the PAPI health and build list tools to give the user a complete picture of where things stand.
 
 ## Steps
 
-1. **Run `health`** — the PAPI MCP tool that returns sprint number, board state, strategy review cadence, Active Decisions summary, velocity, and estimation accuracy.
+1. **Run `health`** — the PAPI MCP tool that returns cycle number, board state, strategy review cadence, Active Decisions summary, velocity, and estimation accuracy.
 
 2. **Run `build_list`** — shows tasks with BUILD HANDOFFs ready for execution, prioritised by status (In Progress first, then Backlog).
 
 3. **Summarise clearly:**
-   - "You're on Sprint N. X tasks to build, Y builds pending review."
-   - Or: "Sprint N is complete — ready for the next plan."
+   - "You're on Cycle N. X tasks to build, Y builds pending review."
+   - Or: "Cycle N is complete — ready for the next plan."
    - Flag any issues: stale In Progress tasks, strategy review due, orphaned branches.
 
 4. **Suggest the next action:**
    - If tasks are In Review: "Run `review_submit` to accept/reject pending reviews."
    - If tasks are in Backlog: "Pick a task to build — use `/next-task` to start."
-   - If all tasks are Done: "All tasks complete. Run `plan` to create the next sprint."
+   - If all tasks are Done: "All tasks complete. Run `plan` to create the next cycle."
    - If strategy review is due: mention it before suggesting plan.
 
 ## Output format

package/skills/papi-audit.md

@@ -0,0 +1,52 @@
+---
+name: papi-audit
+description: >
+  Audit the latest changes in this branch for bugs and compliance with the project's conventions.
+  Use when the user says "audit", "review changes", "check my code", "check my branch",
+  or after completing a build task before submitting for review.
+invocable: true
+---
+
+# PAPI Audit — Bug & Doc Drift Check
+
+Audit all changes on the current branch for bugs, convention violations, and documentation drift.
+
+## Steps
+
+### 1. Identify changed files
+
+Run `git diff origin/main --name-only` to find all files modified on this branch. If no changes are found, report "No changes to audit" and stop.
+
+### 2. Read and review each changed file
+
+For each changed file, read it and review for:
+
+**Bug check:**
+- Logic errors, off-by-one mistakes, incorrect conditions
+- Unhandled edge cases (null, undefined, empty inputs)
+- Race conditions or state management issues
+- Functions that could throw but aren't wrapped in try/catch where needed
+- Incorrect type narrowing or unsafe casts
+
+**Code style (from CLAUDE.md):**
+- Check all conventions defined in CLAUDE.md and flag any violations
+- Pay special attention to naming, typing, error handling, and import patterns
+
+### 3. Documentation check
+
+For each changed source file, check if any documentation in `docs/` describes behaviour, architecture, or file interactions that the change modified. Specifically:
+- If a doc needs updating, report it as a finding with severity "Doc drift" and specify which section is stale.
+
+### 4. Report findings
+
+For each issue found:
+- **File**: path and line number
+- **Severity**: Bug / Convention violation / Doc drift / Nitpick
+- **Issue**: What's wrong
+- **Fix**: How to fix it
+
+If no issues are found, state that the changes are clean.
+
+### 5. Pre-existing issues
+
+Note pre-existing issues separately — flag them but don't fix them unless they interact with the new changes.