@softspark/ai-toolkit 3.5.1 → 4.0.0

package/llms-full.txt

@@ -92,7 +92,6 @@
 - **dart-rules**: Dart/Flutter coding rules: style, patterns, security, testing. Triggers: .dart, pubspec.yaml, Flutter, Riverpod, Bloc, widget, StatelessWidget, StatefulWidget.
 - **database-patterns**: DB schema design and query tuning: normalization, indexing, N+1, transactions, EXPLAIN. Triggers: schema, index, slow query, N+1, PostgreSQL, MySQL, EXPLAIN, deadlock, query plan.
 - **debug**: Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
-- **debugging-tactics**: RCA debugging: investigation, hypothesis, validation, fix. No fix without RCA. Triggers: bug, error, exception, stack trace, intermittent, flaky, crash, regression, broken after.
 - **deploy**: Deploys with pre-flight checks and health verification. Triggers: deploy, deployment, ship, release, push to prod.
 - **design-an-interface**: Generates and compares parallel interface designs (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice.
 - **design-engineering**: UI craftsmanship: animation rules, easing, micro-interactions, state polish. Triggers: animation, transition, ease-out, motion, micro-interaction, hover, loading state, UI polish.
@@ -111,7 +110,6 @@
 - **grill-me**: Stress-tests a plan via Socratic questioning down each decision branch. Triggers: stress-test, grill me, validate assumptions, challenge plan, socratic review.
 - **health**: Service/infra health via liveness/readiness checks, resource usage, quick diagnostics. Triggers: health check, services up, system status, infra health, degraded service.
 - **hipaa-validate**: HIPAA validator: PHI exposure, audit logging, encryption, access control, BAA refs. Triggers: HIPAA, PHI, healthcare compliance, audit log, BAA.
-- **hive-mind**: Multi-agent swarm: consensus voting, aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, agent voting.
 - **hook-creator**: Create new Claude Code lifecycle hook (PreToolUse/PostToolUse/Stop/SessionStart) with bash + hooks.json. Triggers: create hook, lifecycle hook, PreToolUse, PostToolUse, hook event.
 - **index**: Reindexes KB for semantic search via vector store (Qdrant). Triggers: reindex KB, rebuild index, vector reindex, refresh embeddings.
 - **instinct-review**: Reviews/promotes/removes instincts from `.claude/instincts/*.md`. Triggers: instinct review, curate instincts, manage instincts, promote instinct.
@@ -138,7 +136,6 @@
 - **persona**: Switches engineering persona at runtime. Triggers: persona, switch role, backend-lead, frontend-lead, devops-eng, junior-dev.
 - **php-rules**: PHP coding rules: style, patterns, security, testing. Triggers: .php, composer.json, Laravel, Symfony, PHPUnit, PSR-12, Composer.
 - **plan**: Breaks features/goals into phased plans with task lists, agent assignments, dependencies. Triggers: plan feature, implementation roadmap, break down task, project phases.
-- **plan-writing**: Implementation plans + pre-mortems: phases, success criteria, risks, rollback. Triggers: implementation plan, pre-mortem, phased plan, task breakdown.
 - **plugin-creator**: Creates opt-in plugin packs with manifests + module scaffolding for Claude/Codex. Triggers: new plugin, plugin pack, plugin scaffold.
 - **pr**: Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
 - **prd-to-issues**: Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.
@@ -158,7 +155,6 @@
 - **ruby-rules**: Ruby coding rules: style, patterns, security, testing. Triggers: .rb, Gemfile, .gemspec, Rails, ActiveRecord, Sidekiq, RSpec, Sorbet, rubocop.
 - **rust-patterns**: Rust: ownership, lifetimes, async (Tokio), Result/anyhow/thiserror, traits, unsafe. Triggers: Rust, borrow checker, lifetime, Tokio, cargo, trait, impl, Result, unsafe, clippy.
 - **rust-rules**: Rust coding rules: style, patterns, security, testing. Triggers: .rs, Cargo.toml, Cargo.lock, Tokio, Axum, Serde, clippy, cargo test.
-- **search**: Searches the KB with semantic + hybrid modes. Triggers: search KB, semantic search, hybrid search, knowledge base query.
 - **security-patterns**: App security: OWASP, authN/authZ, input validation, secrets, TLS, CSRF/XSS/SQLi, JWT, CSP. Triggers: security, OWASP, auth, JWT, CSRF, XSS, SQL injection, secrets, TLS, CSP, CORS.
 - **seo-validate**: SEO validator: meta/OG, Schema.org, hreflang, Core Web Vitals, crawlability. Triggers: SEO, meta tags, Schema.org, hreflang, LCP, INP, CLS, Core Web Vitals, sitemap, crawlability.
 - **skill-audit**: Scans skills/agents for security risks: dangerous patterns, secrets, excessive perms. Triggers: skill audit, security scan, agent audit, dangerous pattern.
@@ -168,7 +164,6 @@
 - **swift-patterns**: Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.
 - **swift-rules**: Swift coding rules: style, patterns, security, testing. Triggers: .swift, Package.swift, .xcodeproj, SwiftUI, Combine, async/await, XCTest.
 - **tdd**: TDD with red-green-refactor loop and vertical slices. Triggers: TDD, test-first, red-green-refactor, test driving development.
-- **teams**: Launches multi-agent teams for review, debugging, feature dev, security audits, migrations. Triggers: multi-agent workflow, agent teams, team review, parallel agent collaboration.
 - **test**: Runs project test suite with coverage, auto-detects framework (pytest, vitest, jest, flutter, go, cargo, phpunit). Triggers: run tests, test suite, coverage report.
 - **testing-patterns**: Testing strategy: pyramid, AAA, mocks/fakes/stubs, flaky tests, coverage. Triggers: test, fixture, mock, stub, e2e, TDD, Playwright, Cypress, flaky, coverage, property-based.
 - **triage-issue**: Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
@@ -5453,7 +5448,7 @@ python3 scripts/audit_skills.py --ci
 **Verify audit_skills.py:**
 - [ ] `HIGH: 0` (MUST be zero — CI fails otherwise)
 - [ ] `WARN: 0`
-- [ ] `INFO: N` (acceptable — broad-access skills: orchestrate, swarm, teams)
+- [ ] `INFO: N` (acceptable — broad-access skills: orchestrate, swarm, workflow)
 
 ---
 
@@ -7007,7 +7002,6 @@ The main adapted group is multi-agent orchestration:
 - `/orchestrate`
 - `/workflow`
 - `/swarm`
-- `/teams`
 - `/subagent-development`
 
 The adapter also covers skills that previously depended only on Claude's
@@ -10650,7 +10644,7 @@ User-authored opencode files and user-authored `opencode.json` keys are never de
 ## Behavioral Limits
 
 - opencode does not expose the full Claude hook event surface; only the events in the mapping table above are bridged. Claude-only events (`TaskCompleted`, `TeammateIdle`, `SubagentStart`, `SubagentStop`, `PreCompact`) are silently skipped.
-- Multi-agent orchestration skills (`/orchestrate`, `/workflow`, `/swarm`, `/teams`, `/subagent-development`) run through the Codex adaptation layer — they use opencode subagents and explicit file ownership instead of Claude's `Agent`/`TaskCreate` primitives.
+- Multi-agent orchestration skills (`/orchestrate`, `/workflow`, `/swarm`, `/subagent-development`) run through the Codex adaptation layer — they use opencode subagents and explicit file ownership instead of Claude's `Agent`/`TaskCreate` primitives.
 
 ## Verification
 
@@ -10997,7 +10991,7 @@ All functionality is unified under skills. Task and hybrid skills are user-invoc
 | **2 — Multi-agent workflow** | `/workflow <type>` | Cross-cutting task with known pattern |
 | **3 — Custom parallelism** | `/orchestrate`, `/swarm` | No predefined workflow matches |
 
-## Task Skills (32)
+## Task Skills (30)
 
 Task skills execute a specific action. Invoked via slash commands. `disable-model-invocation: true`.
 
@@ -11050,13 +11044,11 @@ Hybrid skills combine slash-command invocation with domain knowledge that agents
 | **analyze** | `/analyze` | medium | Analyze code quality, complexity, and patterns |
 | **cve-scan** | `/cve-scan` | medium | Scan project dependencies for known CVEs using native audit tools (npm, pip, composer, cargo, go, ruby, dart) |
 | **docs** | `/docs` | high | Generate/update docs: README, API docs, architecture notes, changelogs (Tier 1 — single agent) |
-| **search** | `/search` | medium | Search knowledge base (MCP tools with local fallback) |
 | **explain** | `/explain` | medium | Explain architecture of a file/module using Mermaid diagrams |
 | **orchestrate** | `/orchestrate` | max | Custom multi-agent parallelism — Tier 3, native in Claude, Codex-adapted to `spawn_agent` workflows |
 | **swarm** | `/swarm` | max | Massive parallelism: map-reduce, consensus, relay — Tier 3 |
 | **workflow** | `/workflow` | max | 15 predefined multi-agent workflow types — Tier 2, Codex-adapted to native subagent orchestration |
 | **instinct-review** | `/instinct-review` | low | Review, curate, and manage learned instincts from past sessions |
-| **teams** | `/teams` | max | Launch pre-configured Agent Teams compositions for common workflows |
 | **write-a-prd** | `/write-a-prd` | high | Create PRD through interactive interview, codebase exploration, and module design |
 | **prd-to-plan** | `/prd-to-plan` | high | Convert PRD into phased implementation plan using tracer-bullet vertical slices |
 | **tdd** | `/tdd` | high | Test-driven development with red-green-refactor loop and vertical slices |
@@ -11137,24 +11129,16 @@ Hybrid skills combine slash-command invocation with domain knowledge that agents
 | **content-moderation-patterns** | `skills/content-moderation-patterns/` | Two-stage moderation: pre-filter + LLM classifier; categories; thresholds |
 | **model-routing-patterns** | `skills/model-routing-patterns/` | Haiku/Sonnet/Opus routing; escalation; sub-agent delegation; fallback |
 
-## Knowledge Skills - Process (7)
+## Knowledge Skills - Process (5)
 
 | Skill | Directory | Domain |
 |-------|-----------|--------|
-| **plan-writing** | `skills/plan-writing/` | Implementation plans, success criteria, pre-mortem |
-| **debugging-tactics** | `skills/debugging-tactics/` | Iron Law 4-phase debugging: root cause → pattern → hypothesis → fix |
 | **git-mastery** | `skills/git-mastery/` | Git workflows, branching, conflict resolution |
 | **architecture-decision** | `skills/architecture-decision/` | Architecture notes, trade-off analysis, alternatives |
 | **performance-profiling** | `skills/performance-profiling/` | Profiling, bottleneck analysis, optimization |
 | **research-mastery** | `skills/research-mastery/` | Multi-source research, synthesis, fact-checking |
 | **verification-before-completion** | `skills/verification-before-completion/` | Iron Law: evidence-before-claims, no completion without fresh verification |
 
-## Knowledge Skills - Orchestration (1)
-
-| Skill | Directory | Domain |
-|-------|-----------|--------|
-| **hive-mind** | `skills/hive-mind/` | Multi-agent aggregation, consensus, swarm patterns |
-
 ## Quality Guardrails
 
 ### Anti-Rationalization Tables
@@ -11246,7 +11230,6 @@ Common adapted skills:
 - `/orchestrate`
 - `/workflow`
 - `/swarm`
-- `/teams`
 - `/subagent-development`
 - `/tdd`
 

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.5.1",
+  "version": "4.0.0",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",
@@ -9,7 +9,7 @@
       "tags": ["core", "agents"]
     },
     "skills": {
-      "description": "112 skills (32 task + 31 hybrid + 49 knowledge)",
+      "description": "107 skills (30 task + 31 hybrid + 46 knowledge)",
       "path": "app/skills",
       "target": ".claude/skills",
       "type": "symlink",
@@ -90,7 +90,7 @@
       "default": true
     },
     "skills": {
-      "description": "112 skills (task, hybrid, knowledge)",
+      "description": "107 skills (task, hybrid, knowledge)",
       "default": true
     },
     "rules-common": {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "3.5.1",
-  "description": "AI coding toolkit: 112 skills, 44 agents, 12-editor write-through (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo, Aider, Augment, Antigravity, Codex, opencode), machine-enforced safety constitution, SARIF audit, signed npm provenance.",
+  "version": "4.0.0",
+  "description": "AI coding toolkit: 107 skills, 44 agents, 12-editor write-through (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo, Aider, Augment, Antigravity, Codex, opencode), machine-enforced safety constitution, SARIF audit, signed npm provenance.",
   "keywords": [
     "claude",
     "claude-code",

package/scripts/codex_skill_adapter.py

@@ -98,7 +98,7 @@ def build_codex_skill_text(skill_file: Path) -> str:
 
     if adapted:
         frontmatter = _adapt_frontmatter(frontmatter)
-        body = _adapt_body(skill_file.parent.name, body)
+        body = _adapt_body(body)
 
     rendered_frontmatter = _render_frontmatter(frontmatter)
     return f"---\n{rendered_frontmatter}\n---\n{body.rstrip()}\n"
@@ -221,7 +221,7 @@ def _adapt_allowed_tools(value: str) -> list[str]:
     return tools
 
 
-def _adapt_body(skill_name: str, body: str) -> str:
+def _adapt_body(body: str) -> str:
     body = body.replace(
         "## MANDATORY: You MUST use the Agent tool",
         "## MANDATORY: Use Codex subagents for delegation",
@@ -258,11 +258,6 @@ def _adapt_body(skill_name: str, body: str) -> str:
     if "$ARGUMENTS" in body:
         body = body.replace("$ARGUMENTS", f"$ARGUMENTS\n{_CODEX_NOTE.rstrip()}", 1)
 
-    if skill_name == "teams":
-        body = body.replace(
-            "Launches a pre-configured Agent Teams composition for your task.",
-            "Launches a pre-configured Codex subagent composition for your task.",
-        )
     return body
 
 

package/app/skills/debugging-tactics/SKILL.md

@@ -1,136 +0,0 @@
----
-name: debugging-tactics
-description: "RCA debugging: investigation, hypothesis, validation, fix. No fix without RCA. Triggers: bug, error, exception, stack trace, intermittent, flaky, crash, regression, broken after."
-effort: medium
-user-invocable: false
-allowed-tools: Grep, Read
----
-
-# Debugging Tactics Skill
-
-## The Iron Law
-
-```
-NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
-```
-
-If you haven't completed Phase 1 (Root Cause Investigation), you cannot propose fixes.
-
-Random fixes waste time and create new bugs. Quick patches mask underlying issues.
-
-**Violating the letter of this process is violating the spirit of debugging.**
-
-## The Four Phases
-
-You MUST complete each phase before proceeding to the next.
-
-### Phase 1: Root Cause Investigation
-
-**BEFORE attempting ANY fix:**
-
-1. **Read Error Messages Carefully**
-   - Don't skip past errors or warnings — they often contain the answer
-   - Read stack traces completely
-   - Note line numbers, file paths, error codes
-
-2. **Reproduce Consistently**
-   - Can you trigger it reliably?
-   - What are the exact steps?
-   - If not reproducible, gather more data — don't guess
-
-3. **Check Recent Changes**
-   - `git diff`, recent commits, new dependencies
-   - Config changes, environmental differences
-
-4. **Gather Evidence in Multi-Component Systems**
-   For each component boundary: log what enters, log what exits, verify state at each layer.
-   Run once to gather evidence showing WHERE it breaks, THEN investigate that specific component.
-
-5. **Trace Data Flow**
-   Where does the bad value originate? Trace backward through call stack to the source. Fix at source, not at symptom.
-
-### Phase 2: Pattern Analysis
-
-1. **Find Working Examples** — locate similar working code in same codebase
-2. **Compare Against References** — read reference implementations COMPLETELY, not skimming
-3. **Identify Differences** — list every difference, however small
-4. **Understand Dependencies** — what other components, settings, config does this need?
-
-### Phase 3: Hypothesis and Testing
-
-1. **Form Single Hypothesis** — "I think X is the root cause because Y" (be specific)
-2. **Test Minimally** — smallest possible change, one variable at a time
-3. **Verify Before Continuing** — did it work? If not, form NEW hypothesis. Don't add more fixes on top.
-
-### Phase 4: Implementation
-
-1. **Create Failing Test Case** — MUST have before fixing (use TDD skill)
-2. **Implement Single Fix** — address root cause, ONE change at a time, no "while I'm here" improvements
-3. **Verify Fix** — test passes? No regressions? Issue resolved?
-4. **If Fix Doesn't Work** — count your attempts:
-   - If < 3: Return to Phase 1, re-analyze with new information
-   - **If >= 3: STOP and question the architecture** (see below)
-
-### Architecture Escalation (3+ Failed Fixes)
-
-**Pattern indicating architectural problem:**
-- Each fix reveals new shared state/coupling in different places
-- Fixes require "massive refactoring" to implement
-- Each fix creates new symptoms elsewhere
-
-**STOP and question fundamentals:**
-- Is this pattern fundamentally sound?
-- Should we refactor architecture vs. continue fixing symptoms?
-- Discuss with user before attempting more fixes
-
-This is NOT a failed hypothesis — this is a wrong architecture.
-
-## Red Flags — STOP and Follow Process
-
-| Excuse | Reality |
-|--------|---------|
-| "Quick fix for now, investigate later" | Systematic is faster than thrashing |
-| "Just try changing X and see" | One variable at a time, with hypothesis |
-| "I'll skip the test, I'll manually verify" | Untested fixes don't stick |
-| "It's probably X, let me fix that" | Seeing symptoms is not understanding root cause |
-| "One more fix attempt" (after 2+) | 3+ failures = architectural problem. STOP. |
-| "Here are the main problems: [list]" | You're proposing fixes without investigation |
-
-## Legacy Reference
-
-## Language-Specific Tactics
-
-### Python
-- **Debugger**: `import pdb; pdb.set_trace()` (or `ipdb`)
-- **Trace**: `traceback.print_stack()`
-- **Memory**: `tracemalloc` for leaks.
-```python
-import tracemalloc
-tracemalloc.start()
-# ... code ...
-snapshot = tracemalloc.take_snapshot()
-top_stats = snapshot.statistics('lineno')
-```
-
-### Node.js / TypeScript
-- **Debugger**: `node --inspect-brk app.js` -> Open `chrome://inspect`.
-- **Memory**: `heapdump` or built-in inspector.
-- **Async Traces**: Ensure `Error.stackTraceLimit = Infinity`.
-
-### PHP (Laravel/Symfony)
-- **Debugger**: Xdebug (`xdebug_break()`).
-- **Logs**: `Log::info('State:', $data);`.
-- **Query Log**: `DB::enableQueryLog(); ... dd(DB::getQueryLog());`.
-
-### Flutter / Dart
-- **Debugger**: `debugger()` statement.
-- **Inspector**: Flutter DevTools (Widget Inspector).
-- **Network**: Network tab in DevTools for API calls.
-
-## "5 Whys" Root Cause Analysis
-Ask "Why?" 5 times to find the real issue:
-- "The app crashed." -> Why? -> "Null pointer exception."
-- -> Why? -> "User object was null."
-- -> Why? -> "API returned 404."
-- -> Why? -> "User ID was invalid."
-- -> Why? -> "Frontend validation allowed negative IDs." (ROOT CAUSE)

package/app/skills/hive-mind/SKILL.md

@@ -1,57 +0,0 @@
----
-name: hive-mind
-description: "Multi-agent swarm: consensus voting, aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, agent voting."
-effort: medium
-user-invocable: false
-allowed-tools: Read
----
-
-# Hive Mind Skill
-
-You are part of a Swarm. You are not alone.
-
-## 🔴 Swarm Protocols
-
-### 1. Consensus (The Vote)
-When agents disagree:
-1. Each agent generates a solution + confidence score.
-2. **Weighted Voting**: Higher confidence = Higher weight.
-3. **Majority Rule**: >50% wins.
-
-### 2. Aggregation (The Merge)
-When multiple agents produce outputs:
-1. **Format Standardization**: Ensure all JSON/Markdown matches.
-2. **De-duplication**: Remove identical findings.
-3. **Synthesis**: Combine unique insights into one report.
-
-### 3. File Ownership (Agent Teams Mode)
-
-**With Agent Teams enabled**: File conflicts are prevented by **file ownership assignment** at spawn time. Each teammate gets distinct files/directories. No locking needed.
-
-- Lead assigns ownership when creating the team
-- Teammates respect boundaries in their prompts
-- Quality hooks verify completeness on `TaskCompleted`
-
-**Without Agent Teams** (fallback):
-1. Before editing a file: Check if another agent is editing.
-2. Use `touch .lock.{filename}`.
-3. Remove lock after edit.
-
-### 4. Communication (Agent Teams Mode)
-
-- **message**: Send to ONE specific teammate (targeted, low cost)
-- **broadcast**: Send to ALL teammates (use sparingly — costs N×)
-- **Shared task list**: `~/.claude/tasks/{team-name}/` — all agents can see/claim
-
-## Example Workflow (Map-Reduce)
-
-### With Agent Teams
-1. **Map**: Lead spawns 5 teammates, each scanning 20 files
-2. **Parallel**: All teammates execute simultaneously in tmux panes
-3. **Reduce**: Lead waits, collects results, applies Aggregation protocol
-4. **Report**: `final_report.md` synthesized from all findings
-
-### Without Agent Teams (Fallback)
-1. **Map**: "Scan 100 files for leaks." → 10 Agents × 10 Files.
-2. **Reduce**: Agents output `leaks_{i}.json`.
-3. **Hive Mind**: Merge all `leaks_*.json` → `final_report.json`.

package/app/skills/plan-writing/SKILL.md

@@ -1,228 +0,0 @@
----
-name: plan-writing
-description: "Implementation plans + pre-mortems: phases, success criteria, risks, rollback. Triggers: implementation plan, pre-mortem, phased plan, task breakdown."
-effort: medium
-user-invocable: false
-allowed-tools: Read
----
-
-# Plan Writing Skill
-
-## Plan Structure
-
-### Basic Plan Template
-
-```markdown
-# [Project Name] - Implementation Plan
-
-## Overview
-- **Type**: [Project type]
-- **Stack**: [Tech choices]
-- **Complexity**: [Low/Medium/High]
-- **Estimated Effort**: [Days/Weeks]
-
-## Goals
-1. [Primary goal]
-2. [Secondary goal]
-
-## Requirements
-
-### Functional
-| ID | Requirement | Priority |
-|----|-------------|----------|
-| FR1 | [Requirement] | Must |
-| FR2 | [Requirement] | Should |
-
-### Non-Functional
-| ID | Requirement | Metric |
-|----|-------------|--------|
-| NFR1 | Performance | < 2s load |
-| NFR2 | Security | OWASP compliant |
-
-## Task Breakdown
-
-### Phase 1: Foundation
-- [ ] Task 1.1
-- [ ] Task 1.2
-
-### Phase 2: Core
-- [ ] Task 2.1
-- [ ] Task 2.2
-
-### Phase 3: Polish
-- [ ] Task 3.1
-- [ ] Task 3.2
-
-## Dependencies
-
-```mermaid
-graph TD
-    A[Database Schema] --> B[API Endpoints]
-    B --> C[UI Components]
-    C --> D[Tests]
-    D --> E[Deployment]
-```
-
-## Agent Assignment
-
-| Task | Agent | Dependencies |
-|------|-------|--------------|
-| Schema | database-architect | None |
-| API | backend-specialist | Schema |
-| UI | frontend-specialist | API |
-| Tests | test-engineer | UI |
-
-## Success Criteria
-- [ ] All tests passing
-- [ ] Performance targets met
-- [ ] Security review complete
-
-## Risks
-| Risk | Probability | Impact | Mitigation |
-|------|-------------|--------|------------|
-| [Risk] | High/Med/Low | High/Med/Low | [Plan] |
-```
-
----
-
-## Task Breakdown Principles
-
-### SMART Tasks
-- **S**pecific: Clear deliverable
-- **M**easurable: Done/not done
-- **A**ssignable: One owner
-- **R**ealistic: Achievable
-- **T**ime-bound: Estimated duration
-
-### Good vs Bad Tasks
-
-| ❌ Bad | ✅ Good |
-|--------|--------|
-| "Implement authentication" | "Create login API endpoint with JWT" |
-| "Build UI" | "Create user dashboard component" |
-| "Fix bugs" | "Fix login redirect on mobile" |
-| "Optimize" | "Reduce API response time to <200ms" |
-
----
-
-## Dependency Management
-
-### Dependency Types
-
-| Type | Example |
-|------|---------|
-| **Hard** | API must exist before UI can call it |
-| **Soft** | Tests can start when 50% features done |
-| **External** | Waiting for third-party API access |
-
-### Identifying Dependencies
-
-```
-For each task, ask:
-1. What must exist before this can start?
-2. What does this task produce?
-3. Who/what consumes that output?
-```
-
----
-
-## Estimation Patterns
-
-### T-Shirt Sizing
-
-| Size | Effort | Example |
-|------|--------|---------|
-| XS | <2 hours | Fix typo, add field |
-| S | 2-4 hours | Simple component, basic API |
-| M | 1-2 days | Feature with tests |
-| L | 3-5 days | Complex feature |
-| XL | 1-2 weeks | Major subsystem |
-
-### Cone of Uncertainty
-
-| Phase | Accuracy |
-|-------|----------|
-| Initial idea | 4x variance |
-| After discovery | 2x variance |
-| After design | 1.5x variance |
-| After development | 1.1x variance |
-
----
-
-## Phase Templates
-
-### MVP Launch
-
-```
-Phase 1: Core (Week 1-2)
-- Database schema
-- Authentication
-- Core feature 1
-
-Phase 2: Essential (Week 3-4)
-- Core feature 2
-- Basic UI
-- Critical integrations
-
-Phase 3: Launch (Week 5)
-- Testing
-- Deployment
-- Documentation
-```
-
-### Feature Addition
-
-```
-Phase 1: Preparation
-- Research existing code
-- Define acceptance criteria
-- Design solution
-
-Phase 2: Implementation
-- Backend changes
-- Frontend changes
-- Integration
-
-Phase 3: Validation
-- Testing
-- Code review
-- Deploy to staging
-```
-
----
-
-## Review Checklist
-
-Before finalizing plan:
-- [ ] All requirements captured
-- [ ] Tasks are SMART
-- [ ] Dependencies identified
-- [ ] Agents assigned
-- [ ] Risks documented
-- [ ] Success criteria defined
-
-## Rules
-
-- **MUST** include a Success Criteria section with measurable, verifiable conditions — subjective criteria are not criteria
-- **MUST** include a Rollback Plan for any work that touches production data or shared infrastructure
-- **MUST** write a Pre-Mortem when estimated effort exceeds 1 day — "what could go wrong" surfaces real risks cheaply
-- **NEVER** estimate in hours for work longer than a week. Use T-shirt sizes (S/M/L/XL) or tracer-bullet slices — precise long-horizon estimates are false confidence
-- **CRITICAL**: every risk has an owner AND a mitigation. A risk register with named risks but no mitigations is decorative.
-- **MANDATORY**: explicit scope boundaries — "not in this plan" is as important as "in this plan"
-
-## Gotchas
-
-- SMART criteria look complete but often omit the "relevant" dimension — a task can be Specific, Measurable, Achievable, Time-bound and still irrelevant to the outcome. Check relevance explicitly.
-- Pre-mortems feel pessimistic and get shortened under deadline pressure. Make the pre-mortem a first-class section with at least 5 named failure modes — a 2-bullet pre-mortem is theater.
-- Risk registers bloat when stakeholders add low-probability items to be safe. Cap the register at 10 risks ranked by (probability × impact); everything below line 10 is noise.
-- Plans authored by the person who will execute them are biased toward feasibility (they want to do it). Plans authored by someone who won't execute are biased toward ambition (they don't pay the cost). Mix both perspectives.
-- "Success criteria: deploy to production" is the weakest criterion — it measures effort, not outcome. Replace with user-facing or metric-based criteria ("20% reduction in p95 latency sustained for 7 days").
-
-## When NOT to Use
-
-- For **actually generating** a plan with phases and task breakdown — use `/plan`
-- For requirements capture before planning — use `/write-a-prd`
-- For turning a plan into filed issues — use `/prd-to-issues`
-- For stress-testing a plan's assumptions — use `/grill-me`
-- For executing plans with agents — use `/orchestrate` or `/workflow`
-- For a single-step fix that does not warrant a document — skip the plan entirely

package/app/skills/search/SKILL.md

@@ -1,64 +0,0 @@
----
-name: search
-description: "Searches the KB with semantic + hybrid modes. Triggers: search KB, semantic search, hybrid search, knowledge base query."
-user-invocable: true
-effort: medium
-argument-hint: "[query]"
-allowed-tools: Read, Grep, Glob
----
-
-# Knowledge Base Search
-
-$ARGUMENTS
-
-## Search Methods
-
-### Method 1: MCP Tools (requires rag-mcp MCP server)
-
-If the `rag-mcp` MCP server is configured, use these tools:
-
-| Tool | Best For | Speed |
-|------|----------|-------|
-| `smart_query` | Default (90% of queries), auto-routing | 2-4s |
-| `hybrid_search_kb` | Raw vector + text search | <1s |
-| `get_document` | Full document content | <1s |
-| `crag_search` | Vague queries (Corrective RAG) | 1-3s |
-| `multi_hop_search` | Complex multi-step reasoning | 20-30s |
-
-```python
-# Primary search
-smart_query("your search query", limit=10)
-
-# Full document retrieval
-get_document(path="kb/reference/architecture.md")
-```
-
-### Method 2: Local File Search (fallback, always available)
-
-If MCP tools are unavailable, use built-in tools:
-
-```
-# Search file contents
-Grep: pattern="your query" path="kb/"
-
-# Search file names
-Glob: pattern="kb/**/*.md"
-
-# Read specific document
-Read: "kb/reference/architecture.md"
-```
-
-## Search Tips
-
-1. **Be specific** - "nginx rate limiting" > "rate limiting"
-2. **Try MCP first**, fall back to Grep/Glob if unavailable
-3. **Use multi-hop** for "compare X with Y" questions (MCP only)
-4. **Always cite sources**: `[PATH: kb/reference/doc.md]`
-
-## Examples
-
-```
-/search rate limiting configuration
-/search how to deploy to production
-/search database migration patterns
-```