@crewpilot/agent 1.0.0 → 3.0.0

package/prompts/skills/engineer-feature-builder/SKILL.md

@@ -193,12 +193,12 @@ If any check fails, fix it before proceeding.
 - `codebase` — Understand existing structure, find reusable code
 - `terminal` — Install dependencies, run tests, run linters
 - `findTestFiles` — Locate existing test patterns
-- `catalyst_metrics_coverage` — Verify coverage after implementation
+- `crewpilot_metrics_coverage` — Verify coverage after implementation
 
 ## Output Format
 
 ```
-## [Catalyst → Feature Builder]
+## [CrewPilot → Feature Builder]
 
 ### Feature: {name}
 **Acceptance criteria**: {list}
@@ -238,7 +238,7 @@ After completing work, append **one** contextual hint to the response based on w
 | Bug was fixed | 💡 *I can run a systematic root cause analysis to find the real cause, not just the symptom — say "debug this" next time.* |
 | Tests were not written (no test framework or user declined) | 💡 *I can enforce TDD — write failing tests first, then implement — say "test first" next time.* |
 | Complex feature completed | 💡 *I can run code quality, security scan, and deploy readiness checks — say "review this" or "ready to deploy?".* |
-| First interaction in session | 💡 *I'm Catalyst — I can plan, build, test, review, and ship code end-to-end. Say "autopilot" for the full pipeline, or just tell me what to build.* |
+| First interaction in session | 💡 *I'm CrewPilot — I can plan, build, test, review, and ship code end-to-end. Say "autopilot" for the full pipeline, or just tell me what to build.* |
 
 **Rules:**
 - One hint per response, max. Never stack multiple hints.

package/prompts/skills/engineer-root-cause-analysis/SKILL.md

@@ -99,13 +99,13 @@ If the root cause is still unknown after max_attempts, escalate to human instead
 
 - `codebase` — Read failing code, trace call chains
 - `terminal` — Run code, execute tests, check logs
-- `catalyst_git_log` — Check recent changes
-- `catalyst_git_diff` — Compare working vs. broken state
+- `crewpilot_git_log` — Check recent changes
+- `crewpilot_git_diff` — Compare working vs. broken state
 
 ## Output Format
 
 ```
-## [Catalyst → Root Cause Analysis]
+## [CrewPilot → Root Cause Analysis]
 
 ### Symptom
 {error/behavior description}

package/prompts/skills/engineer-test-first/SKILL.md

@@ -106,12 +106,12 @@ Tests MUST fail before any implementation begins. No exceptions.
 - `codebase` — Find existing test patterns, test config
 - `findTestFiles` — Locate related test files
 - `terminal` — Run tests, run coverage
-- `catalyst_metrics_coverage` — Get coverage report
+- `crewpilot_metrics_coverage` — Get coverage report
 
 ## Output Format
 
 ```
-## [Catalyst → Test First]
+## [CrewPilot → Test First]
 
 ### Test Strategy
 - Type: {unit/integration/e2e}

package/prompts/skills/insights-knowledge-base/SKILL.md

@@ -56,7 +56,7 @@ digraph knowledge_base {
 When a significant decision is made during any skill:
 1. Extract: decision, rationale, alternatives rejected, date, related files
 2. Tag with categories: `architecture`, `technology`, `process`, `convention`
-3. Store via `catalyst_knowledge_store`
+3. Store via `crewpilot_knowledge_store`
 
 Entry format:
 ```json
@@ -82,11 +82,32 @@ When `pattern-detection` identifies a codebase convention:
 2. Tag with: `pattern`, `convention`, `style`
 3. Reference canonical implementation files
 
+#### Store a Meeting Reference
+When a meeting produces decisions or requirements that influence code:
+1. Extract: meeting subject, date, attendees, key decisions, action items, linked documents
+2. Tag with: `meeting`, `decision`, `requirements`, and relevant feature/module tags
+3. Link to the board items created from the meeting (if any)
+4. Store via `crewpilot_knowledge_store`
+
+Entry format:
+```json
+{
+  "type": "meeting-reference",
+  "title": "{meeting subject} — {date}",
+  "content": "Decisions: {list}. Requirements: {list}. Action items: {list}.",
+  "tags": ["meeting", "{feature}", "{module}"],
+  "related_files": ["{board item URLs or issue numbers}"],
+  "timestamp": "{ISO date}"
+}
+```
+
+This creates a link between decisions and their source meetings — enabling other skills to trace why a requirement exists and who stated it. The `autopilot-meeting` skill should automatically store meeting references after creating board items.
+
 ### Retrieve Operations
 
 #### Direct Query
 User asks "what did we decide about X":
-1. Search knowledge base via `catalyst_knowledge_search`
+1. Search knowledge base via `crewpilot_knowledge_search`
 2. Return matching entries with context
 3. If multiple matches, rank by relevance and recency
 
@@ -99,7 +120,7 @@ Skills query the knowledge base before starting:
 
 #### Timeline View
 User asks "what happened this week/sprint":
-1. Retrieve entries within the time range via `catalyst_knowledge_timeline`
+1. Retrieve entries within the time range via `crewpilot_knowledge_timeline`
 2. Group by type (decisions, lessons, patterns)
 3. Present as a chronological narrative
 
@@ -119,17 +140,17 @@ Generate a summary document:
 
 ## Tools Required
 
-- `catalyst_knowledge_store` — Write entries to the knowledge base
-- `catalyst_knowledge_search` — Full-text search across entries
-- `catalyst_knowledge_timeline` — Time-range queries
-- `catalyst_knowledge_patterns` — Pattern frequency analysis
-- `catalyst_knowledge_export` — Generate summary documents
+- `crewpilot_knowledge_store` — Write entries to the knowledge base
+- `crewpilot_knowledge_search` — Full-text search across entries
+- `crewpilot_knowledge_timeline` — Time-range queries
+- `crewpilot_knowledge_patterns` — Pattern frequency analysis
+- `crewpilot_knowledge_export` — Generate summary documents
 
 ## Output Format
 
 ### For Storage
 ```
-## [Catalyst → Knowledge Base: Stored]
+## [CrewPilot → Knowledge Base: Stored]
 
 ✓ Stored: {type} — "{title}"
 Tags: {tags}
@@ -138,7 +159,7 @@ Related: {files}
 
 ### For Retrieval
 ```
-## [Catalyst → Knowledge Base: Retrieved]
+## [CrewPilot → Knowledge Base: Retrieved]
 
 ### Results for "{query}"
 Found {N} entries:
@@ -154,7 +175,7 @@ Found {N} entries:
 
 ### For Timeline
 ```
-## [Catalyst → Knowledge Base: Timeline]
+## [CrewPilot → Knowledge Base: Timeline]
 
 ### {date range}
 

package/prompts/skills/insights-pattern-detection/SKILL.md

@@ -83,7 +83,7 @@ For each anti-pattern or inconsistency:
 3. Rate urgency: address now vs. track vs. accept
 
 ### Phase 5 — Trend Analysis
-If `catalyst_knowledge_search` has historical data:
+If `crewpilot_knowledge_search` has historical data:
 1. Compare current patterns vs. previous scans
 2. Identify patterns that are spreading (good or bad)
 3. Flag entropy increase — growing inconsistency over time
@@ -92,14 +92,14 @@ If `catalyst_knowledge_search` has historical data:
 
 - `codebase` — Full project scan
 - `terminal` — Run static analysis tools
-- `catalyst_metrics_complexity` — Complexity metrics per module
-- `catalyst_knowledge_search` — Historical pattern data
-- `catalyst_knowledge_store` — Record findings for future comparison
+- `crewpilot_metrics_complexity` — Complexity metrics per module
+- `crewpilot_knowledge_search` — Historical pattern data
+- `crewpilot_knowledge_store` — Record findings for future comparison
 
 ## Output Format
 
 ```
-## [Catalyst → Pattern Detection]
+## [CrewPilot → Pattern Detection]
 
 ### Architecture
 {detected patterns and organization style}

package/prompts/skills/strategize-architecture-planner/SKILL.md

@@ -99,12 +99,12 @@ If `require_adr` is true in config, generate:
 
 - `codebase` — Analyze existing project structure and dependencies
 - `terminal` — Run dependency analysis commands (package.json, imports, etc.)
-- `catalyst_knowledge_search` — Retrieve prior architecture decisions
+- `crewpilot_knowledge_search` — Retrieve prior architecture decisions
 
 ## Output Format
 
 ```
-## [Catalyst → Architecture Planner]
+## [CrewPilot → Architecture Planner]
 
 ### Scope
 {boundaries, actors, quality attributes}

package/prompts/skills/strategize-solution-design/SKILL.md

@@ -79,12 +79,12 @@ Present the recommendation and wait for explicit approval or selection.
 
 - `codebase` — Scan existing stack for constraints
 - `fetch` — Pull external docs/benchmarks when comparing technologies
-- `catalyst_knowledge_search` — Check if similar decisions were made before
+- `crewpilot_knowledge_search` — Check if similar decisions were made before
 
 ## Output Format
 
 ```
-## [Catalyst → Solution Design]
+## [CrewPilot → Solution Design]
 
 ### Problem
 {one-sentence problem statement}

package/scripts/postinstall.js

@@ -1,7 +1,7 @@
 /**
  * postinstall.js — Runs after `npm install @crewpilot/agent`
  * 
- * Creates .github/ files in the user's project so @Catalyst agent
+ * Creates .github/ files in the user's project so @CrewPilot agent
  * appears in Copilot Chat dropdown automatically.
  * 
  * Uses INIT_CWD (set by npm to the directory where `npm install` was run).
@@ -94,14 +94,14 @@ function syncSkills() {
 try {
   fs.mkdirSync(githubDir, { recursive: true });
 
-  syncFile('agent.md', path.join('agents', 'catalyst.md'));
+  syncFile('agent.md', path.join('agents', 'crewpilot.md'));
   syncFile('copilot-instructions.md', 'copilot-instructions.md');
-  syncFile('catalyst.config.json', 'catalyst.config.json');
+  syncFile('crewpilot.config.json', 'crewpilot.config.json');
   syncSkills();
 
   if (created > 0) {
     console.log(`\n  ⚡ CrewPilot: Created ${created} file(s) in .github/ (${skipped} already existed)`);
-    console.log('  ⚡ Open Copilot Chat and select @Catalyst from the agent dropdown\n');
+    console.log('  ⚡ Open Copilot Chat and select @CrewPilot from the agent dropdown\n');
   }
 } catch {
   // Silently fail — postinstall should never break npm install