skill-library-mcp 1.0.0

package/skills/pipedrive-automation/SKILL.md

@@ -0,0 +1,224 @@
+---
+name: pipedrive-automation
+description: "Automate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube MCP (Composio). Always search tools first for current schemas."
+requires:
+  mcp: [rube]
+---
+
+# Pipedrive Automation via Rube MCP
+
+Automate Pipedrive CRM workflows including deal management, contact and organization operations, activity scheduling, notes, and pipeline/stage queries through Composio's Pipedrive toolkit.
+
+## Prerequisites
+
+- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
+- Active Pipedrive connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `pipedrive`
+- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
+
+## Setup
+
+**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
+
+
+1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
+2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `pipedrive`
+3. If connection is not ACTIVE, follow the returned auth link to complete Pipedrive OAuth
+4. Confirm connection status shows ACTIVE before running any workflows
+
+## Core Workflows
+
+### 1. Create and Manage Deals
+
+**When to use**: User wants to create a new deal, update an existing deal, or review deal details in the sales pipeline.
+
+**Tool sequence**:
+1. `PIPEDRIVE_SEARCH_ORGANIZATIONS` - Find existing org to link to the deal [Optional]
+2. `PIPEDRIVE_ADD_AN_ORGANIZATION` - Create organization if none found [Optional]
+3. `PIPEDRIVE_SEARCH_PERSONS` - Find existing contact to link [Optional]
+4. `PIPEDRIVE_ADD_A_PERSON` - Create contact if none found [Optional]
+5. `PIPEDRIVE_GET_ALL_PIPELINES` - Resolve pipeline ID [Prerequisite]
+6. `PIPEDRIVE_GET_ALL_STAGES` - Resolve stage ID within the pipeline [Prerequisite]
+7. `PIPEDRIVE_ADD_A_DEAL` - Create the deal with title, value, org_id, person_id, stage_id [Required]
+8. `PIPEDRIVE_UPDATE_A_DEAL` - Modify deal properties after creation [Optional]
+9. `PIPEDRIVE_ADD_A_PRODUCT_TO_A_DEAL` - Attach line items/products [Optional]
+
+**Key parameters**:
+- `title`: Deal title (required for creation)
+- `value`: Monetary value of the deal
+- `currency`: 3-letter ISO currency code (e.g., "USD")
+- `pipeline_id` / `stage_id`: Numeric IDs for pipeline placement
+- `org_id` / `person_id`: Link to organization and contact
+- `status`: "open", "won", or "lost"
+- `expected_close_date`: Format YYYY-MM-DD
+
+**Pitfalls**:
+- `title` is the only required field for `PIPEDRIVE_ADD_A_DEAL`; all others are optional
+- Custom fields appear as long hash keys in responses; use dealFields endpoint to map them
+- `PIPEDRIVE_UPDATE_A_DEAL` requires the numeric `id` of the deal
+- Setting `status` to "lost" requires also providing `lost_reason`
+
+### 2. Manage Contacts (Persons and Organizations)
+
+**When to use**: User wants to create, update, search, or list contacts and companies in Pipedrive.
+
+**Tool sequence**:
+1. `PIPEDRIVE_SEARCH_PERSONS` - Search for existing person by name, email, or phone [Prerequisite]
+2. `PIPEDRIVE_ADD_A_PERSON` - Create new contact if not found [Required]
+3. `PIPEDRIVE_UPDATE_A_PERSON` - Modify existing contact details [Optional]
+4. `PIPEDRIVE_GET_DETAILS_OF_A_PERSON` - Retrieve full contact record [Optional]
+5. `PIPEDRIVE_SEARCH_ORGANIZATIONS` - Search for existing organization [Prerequisite]
+6. `PIPEDRIVE_ADD_AN_ORGANIZATION` - Create new organization if not found [Required]
+7. `PIPEDRIVE_UPDATE_AN_ORGANIZATION` - Modify organization properties [Optional]
+8. `PIPEDRIVE_GET_DETAILS_OF_AN_ORGANIZATION` - Retrieve full org record [Optional]
+
+**Key parameters**:
+- `name`: Required for both person and organization creation
+- `email`: Array of objects with `value`, `label`, `primary` fields for persons
+- `phone`: Array of objects with `value`, `label`, `primary` fields for persons
+- `org_id`: Link a person to an organization
+- `visible_to`: 1 = owner only, 3 = entire company
+- `term`: Search term for SEARCH_PERSONS / SEARCH_ORGANIZATIONS (minimum 2 characters)
+
+**Pitfalls**:
+- `PIPEDRIVE_ADD_AN_ORGANIZATION` may auto-merge with an existing org; check `response.additional_data.didMerge`
+- Email and phone fields are arrays of objects, not plain strings: `[{"value": "test@example.com", "label": "work", "primary": true}]`
+- `PIPEDRIVE_SEARCH_PERSONS` wildcards like `*` or `@` are NOT supported; use `PIPEDRIVE_GET_ALL_PERSONS` to list all
+- Deletion via `PIPEDRIVE_DELETE_A_PERSON` or `PIPEDRIVE_DELETE_AN_ORGANIZATION` is soft-delete with 30-day retention, then permanent
+
+### 3. Schedule and Track Activities
+
+**When to use**: User wants to create calls, meetings, tasks, or other activities linked to deals, contacts, or organizations.
+
+**Tool sequence**:
+1. `PIPEDRIVE_SEARCH_PERSONS` or `PIPEDRIVE_GET_DETAILS_OF_A_DEAL` - Resolve linked entity IDs [Prerequisite]
+2. `PIPEDRIVE_ADD_AN_ACTIVITY` - Create the activity with subject, type, due date [Required]
+3. `PIPEDRIVE_UPDATE_AN_ACTIVITY` - Modify activity details or mark as done [Optional]
+4. `PIPEDRIVE_GET_DETAILS_OF_AN_ACTIVITY` - Retrieve activity record [Optional]
+5. `PIPEDRIVE_GET_ALL_ACTIVITIES_ASSIGNED_TO_A_PARTICULAR_USER` - List user's activities [Optional]
+
+**Key parameters**:
+- `subject`: Activity title (required)
+- `type`: Activity type key string, e.g., "call", "meeting", "task", "email" (required)
+- `due_date`: Format YYYY-MM-DD
+- `due_time`: Format HH:MM
+- `duration`: Format HH:MM (e.g., "00:30" for 30 minutes)
+- `deal_id` / `person_id` / `org_id`: Link to related entities
+- `done`: 0 = not done, 1 = done
+
+**Pitfalls**:
+- Both `subject` and `type` are required for `PIPEDRIVE_ADD_AN_ACTIVITY`
+- `type` must match an existing ActivityTypes key_string in the account
+- `done` is an integer (0 or 1), not a boolean
+- Response includes `more_activities_scheduled_in_context` in additional_data
+
+### 4. Add and Manage Notes
+
+**When to use**: User wants to attach notes to deals, persons, organizations, leads, or projects.
+
+**Tool sequence**:
+1. `PIPEDRIVE_SEARCH_PERSONS` or `PIPEDRIVE_GET_DETAILS_OF_A_DEAL` - Resolve entity ID [Prerequisite]
+2. `PIPEDRIVE_ADD_A_NOTE` - Create note with HTML content linked to an entity [Required]
+3. `PIPEDRIVE_UPDATE_A_NOTE` - Modify note content [Optional]
+4. `PIPEDRIVE_GET_ALL_NOTES` - List notes filtered by entity [Optional]
+5. `PIPEDRIVE_GET_ALL_COMMENTS_FOR_A_NOTE` - Retrieve comments on a note [Optional]
+
+**Key parameters**:
+- `content`: Note body in HTML format (required)
+- `deal_id` / `person_id` / `org_id` / `lead_id` / `project_id`: At least one entity link required
+- `pinned_to_deal_flag` / `pinned_to_person_flag`: Filter pinned notes when listing
+
+**Pitfalls**:
+- `content` is required and supports HTML; plain text works but is sanitized server-side
+- At least one of `deal_id`, `person_id`, `org_id`, `lead_id`, or `project_id` must be provided
+- `PIPEDRIVE_GET_ALL_NOTES` returns notes across all entities by default; filter with entity ID params
+
+### 5. Query Pipelines and Stages
+
+**When to use**: User wants to view sales pipelines, stages, or deals within a pipeline/stage.
+
+**Tool sequence**:
+1. `PIPEDRIVE_GET_ALL_PIPELINES` - List all pipelines and their IDs [Required]
+2. `PIPEDRIVE_GET_ONE_PIPELINE` - Get details and deal summary for a specific pipeline [Optional]
+3. `PIPEDRIVE_GET_ALL_STAGES` - List all stages, optionally filtered by pipeline [Required]
+4. `PIPEDRIVE_GET_ONE_STAGE` - Get details for a specific stage [Optional]
+5. `PIPEDRIVE_GET_DEALS_IN_A_PIPELINE` - List all deals across stages in a pipeline [Optional]
+6. `PIPEDRIVE_GET_DEALS_IN_A_STAGE` - List deals in a specific stage [Optional]
+
+**Key parameters**:
+- `id`: Pipeline or stage ID (required for single-item endpoints)
+- `pipeline_id`: Filter stages by pipeline
+- `totals_convert_currency`: 3-letter currency code or "default_currency" for converted totals
+- `get_summary`: Set to 1 for deal summary in pipeline responses
+
+**Pitfalls**:
+- `PIPEDRIVE_GET_ALL_PIPELINES` takes no parameters; returns all pipelines
+- `PIPEDRIVE_GET_ALL_STAGES` returns stages for ALL pipelines unless `pipeline_id` is specified
+- Deal counts in pipeline summaries use `per_stages_converted` only when `totals_convert_currency` is set
+
+## Common Patterns
+
+### ID Resolution
+Always resolve display names to numeric IDs before operations:
+- **Organization name -> org_id**: `PIPEDRIVE_SEARCH_ORGANIZATIONS` with `term` param
+- **Person name -> person_id**: `PIPEDRIVE_SEARCH_PERSONS` with `term` param
+- **Pipeline name -> pipeline_id**: `PIPEDRIVE_GET_ALL_PIPELINES` then match by name
+- **Stage name -> stage_id**: `PIPEDRIVE_GET_ALL_STAGES` with `pipeline_id` then match by name
+
+### Pagination
+Most list endpoints use offset-based pagination:
+- Use `start` (offset) and `limit` (page size) parameters
+- Check `additional_data.pagination.more_items_in_collection` to know if more pages exist
+- Use `additional_data.pagination.next_start` as the `start` value for the next page
+- Default limit is ~500 for some endpoints; set explicitly for predictable paging
+
+## Known Pitfalls
+
+### ID Formats
+- All entity IDs (deal, person, org, activity, pipeline, stage) are numeric integers
+- Lead IDs are UUID strings, not integers
+- Custom field keys are long alphanumeric hashes (e.g., "a1b2c3d4e5f6...")
+
+### Rate Limits
+- Pipedrive enforces per-company API rate limits; bulk operations should be paced
+- `PIPEDRIVE_GET_ALL_PERSONS` and `PIPEDRIVE_GET_ALL_ORGANIZATIONS` can return large datasets; always paginate
+
+### Parameter Quirks
+- Email and phone on persons are arrays of objects, not plain strings
+- `visible_to` is numeric: 1 = owner only, 3 = entire company, 5 = specific groups
+- `done` on activities is integer 0/1, not boolean true/false
+- Organization creation may auto-merge duplicates silently; check `didMerge` in response
+- `PIPEDRIVE_SEARCH_PERSONS` requires minimum 2 characters and does not support wildcards
+
+### Response Structure
+- Custom fields appear as hash keys in responses; map them via the respective Fields endpoints
+- Responses often nest data under `response.data.data` in wrapped executions
+- Search results are under `response.data.items`, not top-level
+
+## Quick Reference
+
+| Task | Tool Slug | Key Params |
+|------|-----------|------------|
+| Create deal | `PIPEDRIVE_ADD_A_DEAL` | `title`, `value`, `org_id`, `stage_id` |
+| Update deal | `PIPEDRIVE_UPDATE_A_DEAL` | `id`, `status`, `value`, `stage_id` |
+| Get deal details | `PIPEDRIVE_GET_DETAILS_OF_A_DEAL` | `id` |
+| Search persons | `PIPEDRIVE_SEARCH_PERSONS` | `term`, `fields` |
+| Add person | `PIPEDRIVE_ADD_A_PERSON` | `name`, `email`, `phone`, `org_id` |
+| Update person | `PIPEDRIVE_UPDATE_A_PERSON` | `id`, `name`, `email` |
+| Get person details | `PIPEDRIVE_GET_DETAILS_OF_A_PERSON` | `id` |
+| List all persons | `PIPEDRIVE_GET_ALL_PERSONS` | `start`, `limit`, `filter_id` |
+| Search organizations | `PIPEDRIVE_SEARCH_ORGANIZATIONS` | `term`, `fields` |
+| Add organization | `PIPEDRIVE_ADD_AN_ORGANIZATION` | `name`, `visible_to` |
+| Update organization | `PIPEDRIVE_UPDATE_AN_ORGANIZATION` | `id`, `name`, `address` |
+| Get org details | `PIPEDRIVE_GET_DETAILS_OF_AN_ORGANIZATION` | `id` |
+| Add activity | `PIPEDRIVE_ADD_AN_ACTIVITY` | `subject`, `type`, `due_date`, `deal_id` |
+| Update activity | `PIPEDRIVE_UPDATE_AN_ACTIVITY` | `id`, `done`, `due_date` |
+| Get activity details | `PIPEDRIVE_GET_DETAILS_OF_AN_ACTIVITY` | `id` |
+| List user activities | `PIPEDRIVE_GET_ALL_ACTIVITIES_ASSIGNED_TO_A_PARTICULAR_USER` | `user_id`, `start`, `limit` |
+| Add note | `PIPEDRIVE_ADD_A_NOTE` | `content`, `deal_id` or `person_id` |
+| List notes | `PIPEDRIVE_GET_ALL_NOTES` | `deal_id`, `person_id`, `start`, `limit` |
+| List pipelines | `PIPEDRIVE_GET_ALL_PIPELINES` | (none) |
+| Get pipeline details | `PIPEDRIVE_GET_ONE_PIPELINE` | `id` |
+| List stages | `PIPEDRIVE_GET_ALL_STAGES` | `pipeline_id` |
+| Deals in pipeline | `PIPEDRIVE_GET_DEALS_IN_A_PIPELINE` | `id`, `stage_id` |
+| Deals in stage | `PIPEDRIVE_GET_DEALS_IN_A_STAGE` | `id`, `start`, `limit` |
+| Add product to deal | `PIPEDRIVE_ADD_A_PRODUCT_TO_A_DEAL` | `id`, `product_id`, `item_price` |

package/skills/plaid-fintech/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: plaid-fintech
+description: "Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech compliance best practices. Use when: plaid, bank account linking, bank connection, ach, account aggregation."
+source: vibeship-spawner-skills (Apache 2.0)
+---
+
+# Plaid Fintech
+
+## Patterns
+
+### Link Token Creation and Exchange
+
+Create a link_token for Plaid Link, exchange public_token for access_token.
+Link tokens are short-lived, one-time use. Access tokens don't expire but
+may need updating when users change passwords.
+
+
+### Transactions Sync
+
+Use /transactions/sync for incremental transaction updates. More efficient
+than /transactions/get. Handle webhooks for real-time updates instead of
+polling.
+
+
+### Item Error Handling and Update Mode
+
+Handle ITEM_LOGIN_REQUIRED errors by putting users through Link update mode.
+Listen for PENDING_DISCONNECT webhook to proactively prompt users.
+
+
+## Anti-Patterns
+
+### ❌ Storing Access Tokens in Plain Text
+
+### ❌ Polling Instead of Webhooks
+
+### ❌ Ignoring Item Errors
+
+## ⚠️ Sharp Edges
+
+| Issue | Severity | Solution |
+|-------|----------|----------|
+| Issue | critical | See docs |
+| Issue | high | See docs |
+| Issue | high | See docs |
+| Issue | high | See docs |
+| Issue | medium | See docs |
+| Issue | medium | See docs |
+| Issue | medium | See docs |
+| Issue | medium | See docs |

package/skills/plan-writing/SKILL.md

@@ -0,0 +1,152 @@
+---
+name: plan-writing
+description: Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
+allowed-tools: Read, Glob, Grep
+---
+
+# Plan Writing
+
+> Source: obra/superpowers
+
+## Overview
+This skill provides a framework for breaking down work into clear, actionable tasks with verification criteria.
+
+## Task Breakdown Principles
+
+### 1. Small, Focused Tasks
+- Each task should take 2-5 minutes
+- One clear outcome per task
+- Independently verifiable
+
+### 2. Clear Verification
+- How do you know it's done?
+- What can you check/test?
+- What's the expected output?
+
+### 3. Logical Ordering
+- Dependencies identified
+- Parallel work where possible
+- Critical path highlighted
+- **Phase X: Verification is always LAST**
+
+### 4. Dynamic Naming in Project Root
+- Plan files are saved as `{task-slug}.md` in the PROJECT ROOT
+- Name derived from task (e.g., "add auth" → `auth-feature.md`)
+- **NEVER** inside `.claude/`, `docs/`, or temp folders
+
+## Planning Principles (NOT Templates!)
+
+> 🔴 **NO fixed templates. Each plan is UNIQUE to the task.**
+
+### Principle 1: Keep It SHORT
+
+| ❌ Wrong | ✅ Right |
+|----------|----------|
+| 50 tasks with sub-sub-tasks | 5-10 clear tasks max |
+| Every micro-step listed | Only actionable items |
+| Verbose descriptions | One-line per task |
+
+> **Rule:** If plan is longer than 1 page, it's too long. Simplify.
+
+---
+
+### Principle 2: Be SPECIFIC, Not Generic
+
+| ❌ Wrong | ✅ Right |
+|----------|----------|
+| "Set up project" | "Run `npx create-next-app`" |
+| "Add authentication" | "Install next-auth, create `/api/auth/[...nextauth].ts`" |
+| "Style the UI" | "Add Tailwind classes to `Header.tsx`" |
+
+> **Rule:** Each task should have a clear, verifiable outcome.
+
+---
+
+### Principle 3: Dynamic Content Based on Project Type
+
+**For NEW PROJECT:**
+- What tech stack? (decide first)
+- What's the MVP? (minimal features)
+- What's the file structure?
+
+**For FEATURE ADDITION:**
+- Which files are affected?
+- What dependencies needed?
+- How to verify it works?
+
+**For BUG FIX:**
+- What's the root cause?
+- What file/line to change?
+- How to test the fix?
+
+---
+
+### Principle 4: Scripts Are Project-Specific
+
+> 🔴 **DO NOT copy-paste script commands. Choose based on project type.**
+
+| Project Type | Relevant Scripts |
+|--------------|------------------|
+| Frontend/React | `ux_audit.py`, `accessibility_checker.py` |
+| Backend/API | `api_validator.py`, `security_scan.py` |
+| Mobile | `mobile_audit.py` |
+| Database | `schema_validator.py` |
+| Full-stack | Mix of above based on what you touched |
+
+**Wrong:** Adding all scripts to every plan
+**Right:** Only scripts relevant to THIS task
+
+---
+
+### Principle 5: Verification is Simple
+
+| ❌ Wrong | ✅ Right |
+|----------|----------|
+| "Verify the component works correctly" | "Run `npm run dev`, click button, see toast" |
+| "Test the API" | "curl localhost:3000/api/users returns 200" |
+| "Check styles" | "Open browser, verify dark mode toggle works" |
+
+---
+
+## Plan Structure (Flexible, Not Fixed!)
+
+```
+# [Task Name]
+
+## Goal
+One sentence: What are we building/fixing?
+
+## Tasks
+- [ ] Task 1: [Specific action] → Verify: [How to check]
+- [ ] Task 2: [Specific action] → Verify: [How to check]
+- [ ] Task 3: [Specific action] → Verify: [How to check]
+
+## Done When
+- [ ] [Main success criteria]
+```
+
+> **That's it.** No phases, no sub-sections unless truly needed.
+> Keep it minimal. Add complexity only when required.
+
+## Notes
+[Any important considerations]
+```
+
+---
+
+## Best Practices (Quick Reference)
+
+1. **Start with goal** - What are we building/fixing?
+2. **Max 10 tasks** - If more, break into multiple plans
+3. **Each task verifiable** - Clear "done" criteria
+4. **Project-specific** - No copy-paste templates
+5. **Update as you go** - Mark `[x]` when complete
+
+---
+
+## When to Use
+
+- New project from scratch
+- Adding a feature
+- Fixing a bug (if complex)
+- Refactoring multiple files

package/skills/planning-with-files/SKILL.md

@@ -0,0 +1,211 @@
+---
+name: planning-with-files
+version: "2.1.2"
+description: Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
+user-invocable: true
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - WebFetch
+  - WebSearch
+hooks:
+  SessionStart:
+    - hooks:
+        - type: command
+          command: "echo '[planning-with-files] Ready. Auto-activates for complex tasks, or invoke manually with /planning-with-files'"
+  PreToolUse:
+    - matcher: "Write|Edit|Bash"
+      hooks:
+        - type: command
+          command: "cat task_plan.md 2>/dev/null | head -30 || true"
+  PostToolUse:
+    - matcher: "Write|Edit"
+      hooks:
+        - type: command
+          command: "echo '[planning-with-files] File updated. If this completes a phase, update task_plan.md status.'"
+  Stop:
+    - hooks:
+        - type: command
+          command: "${CLAUDE_PLUGIN_ROOT}/scripts/check-complete.sh"
+---
+
+# Planning with Files
+
+Work like Manus: Use persistent markdown files as your "working memory on disk."
+
+## Important: Where Files Go
+
+When using this skill:
+
+- **Templates** are stored in the skill directory at `${CLAUDE_PLUGIN_ROOT}/templates/`
+- **Your planning files** (`task_plan.md`, `findings.md`, `progress.md`) should be created in **your project directory** — the folder where you're working
+
+| Location | What Goes There |
+|----------|-----------------|
+| Skill directory (`${CLAUDE_PLUGIN_ROOT}/`) | Templates, scripts, reference docs |
+| Your project directory | `task_plan.md`, `findings.md`, `progress.md` |
+
+This ensures your planning files live alongside your code, not buried in the skill installation folder.
+
+## Quick Start
+
+Before ANY complex task:
+
+1. **Create `task_plan.md`** in your project — Use [templates/task_plan.md](templates/task_plan.md) as reference
+2. **Create `findings.md`** in your project — Use [templates/findings.md](templates/findings.md) as reference
+3. **Create `progress.md`** in your project — Use [templates/progress.md](templates/progress.md) as reference
+4. **Re-read plan before decisions** — Refreshes goals in attention window
+5. **Update after each phase** — Mark complete, log errors
+
+> **Note:** All three planning files should be created in your current working directory (your project root), not in the skill's installation folder.
+
+## The Core Pattern
+
+```
+Context Window = RAM (volatile, limited)
+Filesystem = Disk (persistent, unlimited)
+
+→ Anything important gets written to disk.
+```
+
+## File Purposes
+
+| File | Purpose | When to Update |
+|------|---------|----------------|
+| `task_plan.md` | Phases, progress, decisions | After each phase |
+| `findings.md` | Research, discoveries | After ANY discovery |
+| `progress.md` | Session log, test results | Throughout session |
+
+## Critical Rules
+
+### 1. Create Plan First
+Never start a complex task without `task_plan.md`. Non-negotiable.
+
+### 2. The 2-Action Rule
+> "After every 2 view/browser/search operations, IMMEDIATELY save key findings to text files."
+
+This prevents visual/multimodal information from being lost.
+
+### 3. Read Before Decide
+Before major decisions, read the plan file. This keeps goals in your attention window.
+
+### 4. Update After Act
+After completing any phase:
+- Mark phase status: `in_progress` → `complete`
+- Log any errors encountered
+- Note files created/modified
+
+### 5. Log ALL Errors
+Every error goes in the plan file. This builds knowledge and prevents repetition.
+
+```markdown
+## Errors Encountered
+| Error | Attempt | Resolution |
+|-------|---------|------------|
+| FileNotFoundError | 1 | Created default config |
+| API timeout | 2 | Added retry logic |
+```
+
+### 6. Never Repeat Failures
+```
+if action_failed:
+    next_action != same_action
+```
+Track what you tried. Mutate the approach.
+
+## The 3-Strike Error Protocol
+
+```
+ATTEMPT 1: Diagnose & Fix
+  → Read error carefully
+  → Identify root cause
+  → Apply targeted fix
+
+ATTEMPT 2: Alternative Approach
+  → Same error? Try different method
+  → Different tool? Different library?
+  → NEVER repeat exact same failing action
+
+ATTEMPT 3: Broader Rethink
+  → Question assumptions
+  → Search for solutions
+  → Consider updating the plan
+
+AFTER 3 FAILURES: Escalate to User
+  → Explain what you tried
+  → Share the specific error
+  → Ask for guidance
+```
+
+## Read vs Write Decision Matrix
+
+| Situation | Action | Reason |
+|-----------|--------|--------|
+| Just wrote a file | DON'T read | Content still in context |
+| Viewed image/PDF | Write findings NOW | Multimodal → text before lost |
+| Browser returned data | Write to file | Screenshots don't persist |
+| Starting new phase | Read plan/findings | Re-orient if context stale |
+| Error occurred | Read relevant file | Need current state to fix |
+| Resuming after gap | Read all planning files | Recover state |
+
+## The 5-Question Reboot Test
+
+If you can answer these, your context management is solid:
+
+| Question | Answer Source |
+|----------|---------------|
+| Where am I? | Current phase in task_plan.md |
+| Where am I going? | Remaining phases |
+| What's the goal? | Goal statement in plan |
+| What have I learned? | findings.md |
+| What have I done? | progress.md |
+
+## When to Use This Pattern
+
+**Use for:**
+- Multi-step tasks (3+ steps)
+- Research tasks
+- Building/creating projects
+- Tasks spanning many tool calls
+- Anything requiring organization
+
+**Skip for:**
+- Simple questions
+- Single-file edits
+- Quick lookups
+
+## Templates
+
+Copy these templates to start:
+
+- [templates/task_plan.md](templates/task_plan.md) — Phase tracking
+- [templates/findings.md](templates/findings.md) — Research storage
+- [templates/progress.md](templates/progress.md) — Session logging
+
+## Scripts
+
+Helper scripts for automation:
+
+- `scripts/init-session.sh` — Initialize all planning files
+- `scripts/check-complete.sh` — Verify all phases complete
+
+## Advanced Topics
+
+- **Manus Principles:** See [reference.md](reference.md)
+- **Real Examples:** See [examples.md](examples.md)
+
+## Anti-Patterns
+
+| Don't | Do Instead |
+|-------|------------|
+| Use TodoWrite for persistence | Create task_plan.md file |
+| State goals once and forget | Re-read plan before decisions |
+| Hide errors and retry silently | Log errors to plan file |
+| Stuff everything in context | Store large content in files |
+| Start executing immediately | Create plan file FIRST |
+| Repeat failed actions | Track attempts, mutate approach |
+| Create files in skill directory | Create files in your project |