@mohammadhprp/system-prompt 0.12.1 → 0.12.3

package/framework/skills/learning-opportunities/examples.md

@@ -1,34 +0,0 @@
-# Learning Opportunities Examples
-
-## Offer an exercise after creating a module
-
-User just created auth middleware: "Done, that's the middleware working."
-
-Good agent behavior:
-
-- Offer one short, optional exercise: "Would you like a quick learning exercise on middleware patterns? About 10-15 minutes."
-- If the user agrees, use a predict-then-observe exercise: ask what happens when a request hits the middleware with an expired token.
-- Stop generating immediately after the question and wait for the user's answer.
-- If the prediction is wrong, be direct about what's incorrect, then explore the gap.
-
-## Teach it back after a refactor
-
-User: "We just replaced the cache layer. I want to make sure I actually understand it."
-
-Good agent behavior:
-
-- Ask the user to explain the caching layer as if to a new developer joining the project.
-- Stop after posing the question and wait for the response.
-- Confirm the specific parts they nailed, then name one concrete gap to refine.
-- Keep the exercise exploratory rather than test-like.
-
-## Decline when the user is in a hurry
-
-User: "Just ship it, this needs to go out now."
-
-Good agent behavior:
-
-- Recognize urgency and skip the exercise offer entirely.
-- Avoid repeating the offer when the user has already declined once this session.
-- Cap the session at two completed exercises and stop offering.
-- Keep any offer to a single sentence without insisting.

package/framework/skills/learning-opportunities/references/PRINCIPLES.md

@@ -1,42 +0,0 @@
-# Learning Principles
-
-Consult this file when adapting techniques or making judgment calls about learning approaches. These principles explain WHY the techniques in the main skill work.
-
-## Generation Effect
-
-Users encode information better when they produce it rather than passively consume it. Active retrieval strengthens memory traces in ways that passive review does not. This is why we ask for predictions and explanations before revealing answers.
-
-## Pre-testing
-
-Attempting to answer before learning new information produces stronger memory — even when the attempt is wrong. A failed attempt makes the correct answer more memorable by contrast. Wrong predictions are valuable data, not failures.
-
-## Spacing Effect
-
-Distributing learning over time beats cramming. This is why we use retrieval check-ins at session starts and limit exercises to 2 per session rather than drilling continuously.
-
-## Desirable Difficulties
-
-Conditions that make learning harder in the short term often produce better long-term retention. Exercises should require effort without being frustrating. Struggle during learning is a sign it's working, not failing.
-
-## Fluency Illusion
-
-When AI-generated code is clean and readable, users overestimate how well they understand it. The fluency of the output masks gaps in mental models. This is the primary risk this skill counteracts.
-
-## Dynamic Testing
-
-Errors during learning, when followed by clear corrective feedback, enhance retention compared to error-free learning. This is why we are direct about wrong answers rather than softening them.
-
-## Transfer and Interleaving
-
-Knowledge transfers better when connected to underlying principles and varied contexts. Asking "where else would this apply?" builds flexible knowledge rather than context-bound recall.
-
-## Sources
-
-- Bjork, R. A., Dunlosky, J., & Kornell, N. (2013). Self-regulated learning: Beliefs, techniques, and illusions.
-- Dunlosky, J., et al. (2013). Improving students' learning with effective learning techniques.
-- Giebl, S., et al. (2021). Answer first or Google first?
-- Hicks, C. M., Lee, C. S., & Foster-Marks, K. (2025). The New Developer: AI Skill Threat, Identity Change & Developer Thriving.
-- Roediger III, H. L., & Karpicke, J. D. (2006). The power of testing memory.
-- Soderstrom, N. C., & Bjork, R. A. (2015). Learning versus performance: An integrative review.
-- Tankelevitch, L., et al. (2024). The metacognitive demands and opportunities of generative AI.
-- Hicks, C. (2025). Cognitive helmets for the AI bicycle. Fight for the Human.

package/framework/skills/notion-mcp/SKILL.md

@@ -1,57 +0,0 @@
----
-name: notion-mcp
-description: Use this skill when working with the Notion MCP server tools for pages, databases, comments, search, users, and related Notion workflows.
----
-
-# notion-mcp
-
-Notion MCP server providing 14 tools for interacting with your Notion workspace via the Notion API.
-
-## Tools
-
-| Category         | Tools                                                                                                                                      | Default |
-|------------------|--------------------------------------------------------------------------------------------------------------------------------------------|---------|
-| Pages (6 tools)  | `fetch`, `create-pages`, `update-page`, `duplicate-page`, `move-pages`, `search`                                                          | yes     |
-| Databases (4)    | `create-database`, `update-data-source`, `create-view`, `update-view`                                                                      | yes     |
-| Comments (2)     | `create-comment`, `get-comments`                                                                                                           | yes     |
-| Users & Teams (2)| `get-users`, `get-teams`                                                                                                                   | yes     |
-
-All tools are available by default — there are no opt-in toolsets for this server.
-
-## Key Workflows
-
-### Page Lifecycle (see references/pages.md)
-
-`fetch` → `create-pages` → `update-page` / `duplicate-page` / `move-pages` → `search`
-
-### Database Schema (see references/databases.md)
-
-`fetch` → `create-database` → `update-data-source` → `create-view` → `update-view`
-
-### Comment Threads (see references/comments.md)
-
-`fetch` (with `include_discussions`) → `create-comment` → `get-comments`
-
-### Search & Discovery
-
-`search` → `fetch` → `get-users` / `get-teams`
-
-## Parameter Hints
-
-- **page_id / database_id**: UUID (with or without dashes) or full Notion URL. Extract from Notion page URLs or from `<page>` / `<database>` tags in fetch output.
-- **data_source_id**: Found in `<data-source url="collection://...">` tags in fetch output. Used for `create-pages`, `update-data-source`, `create-view`.
-- **Markdown content**: Notion-flavored Markdown. Supports inline formatting (bold, italic, code, links), inline math (`$Equation$`), and mention tags (`<mention-date>`, `<mention-user>`, `<mention-page>`, `<mention-database>`). Do not use `@today`, `@name`, `[[page]]` UI shortcuts.
-- **Properties**: JSON map of property names to SQLite values. Date/place properties use expanded key format (e.g., `date:Due:start`, `place:Office:latitude`).
-- **SQL DDL**: Used for `create-database` and `update-data-source` statements. Column names double-quoted, options single-quoted.
-
-## Irreversible Tools
-
-`move-pages` — permanently relocates pages. Cannot be undone programmatically. Use with caution.
-
-## Advanced
-
-- **Enhanced Markdown spec**: Read `notion://docs/enhanced-markdown-spec` through your MCP client's resource reader before writing page content.
-- **View DSL spec**: Read `notion://docs/view-dsl-spec` through your MCP client's resource reader before configuring views.
-- **Templates**: `create-pages` and `update-page` support applying page templates (template IDs shown in `<templates>` section of fetch output).
-- **Multi-source databases**: Some databases have multiple data sources. Use `fetch` to identify the correct `data_source_id`.
-- **Verification**: `update-page` with `update_verification` command supports verifying pages as reviewed (Business/Enterprise plan required).

package/framework/skills/notion-mcp/examples.md

@@ -1,31 +0,0 @@
-# Notion MCP Examples
-
-## Example 1: Create Project Documentation
-
-A new feature needs documentation in the team's Notion workspace. Good agent behavior:
-
-- Use `notion-get-teams` to verify which team space the project docs live in.
-- Use `notion-search` to find the existing project folder page.
-- Use `notion-fetch` on the folder page to understand its structure and available templates.
-- Use `notion-create-pages` with the parent, title, properties, and content matching the folder's page template.
-- Use `notion-create-comment` to notify the team about the new documentation.
-
-## Example 2: Track Bug Reports
-
-A production bug needs to be filed in the team's bug tracking database. Good agent behavior:
-
-- Use `notion-search` to find the bug tracking database.
-- Use `notion-fetch` on the database to see its schema, properties, and available templates.
-- Use `notion-create-pages` with the database parent, filling in title, severity, status, assignee, and reproduction steps.
-- Use `notion-get-users` to look up the correct assignee's user ID.
-- Use `notion-create-comment` on the new bug page to add environment details.
-
-## Example 3: Query Tasks and Update Status
-
-Review all in-progress tasks and update their status. Good agent behavior:
-
-- Use `notion-fetch` on the tasks database to see its views and schema.
-- Use `notion-query-database-view` on the "In Progress" view to filter active tasks.
-- Use `notion-fetch` on each task page URL to review full details.
-- Use `notion-update-page` to transition completed tasks to "Done" with a summary of what was completed.
-- Use `notion-create-comment` on blocked tasks to document the blocker.

package/framework/skills/notion-mcp/references/comments.md

@@ -1,112 +0,0 @@
-# Comments & Discussions
-
-## Overview
-
-Notion supports page-level comments, content-targeted comments on specific blocks, and discussion threads with replies. Use `fetch` with `include_discussions: true` first to see where discussions are anchored, then `get-comments` for full threads.
-
-## Create Comment
-
-### Page-level comment
-
-```
-create-comment
-  page_id: "abc123..."
-  markdown: "Comment with **important** context and a [link](https://example.com)."
-```
-
-### Comment on specific content
-
-Target content by providing a unique start/end snippet:
-
-```
-create-comment
-  page_id: "abc123..."
-  markdown: "This section needs updating."
-  selection_with_ellipsis: "# Meeting No...es heading"
-```
-
-The snippet format: first ~10 characters, `...`, last ~10 characters. Must uniquely identify the content.
-
-### Reply to discussion thread
-
-```
-create-comment
-  page_id: "abc123..."
-  discussion_id: "discussion://pageId/blockId/discussionId"
-  markdown: "Fixed this in the latest update."
-```
-
-Get `discussion_id` from `fetch` (with `include_discussions`) or `get-comments` output.
-
-### Using rich_text instead of markdown
-
-For features that markdown cannot express (mentions, custom emoji, colors):
-
-```
-create-comment
-  page_id: "abc123..."
-  rich_text:
-    - text:
-        content: "Assigned to "
-    - mention:
-        type: "user"
-        user:
-          id: "user-uuid"
-    - text:
-        content: " for review"
-```
-
-### Comment formatting
-
-- **Markdown**: inline formatting only (bold, italic, strikethrough, underline, code, links)
-- **Inline math**: `$Equation$`
-- **Mention tags**: `<mention-date start="2024-12-25"/>`, `<mention-page id="..."/>`, `<mention-user id="..."/>`, `<mention-database id="..."/>`
-- ❌ No block-level markdown (headings, lists, tables, blockquotes) — these render as plain text
-- ❌ No UI shortcuts like `@today`, `@name`, `[[page]]`
-
-## Read Comments
-
-```
-get-comments
-  page_id: "abc123..."
-```
-
-Returns all discussions on the page with full thread content.
-
-### Include child block comments
-
-```
-get-comments
-  page_id: "abc123..."
-  include_all_blocks: true
-```
-
-### Include resolved discussions
-
-```
-get-comments
-  page_id: "abc123..."
-  include_resolved: true
-```
-
-### Get specific discussion by ID
-
-```
-get-comments
-  page_id: "abc123..."
-  discussion_id: "discussion://pageId/blockId/discussionId"
-```
-
-## Workflow
-
-1. `fetch` with `include_discussions: true` — see discussion anchors and `<page-discussions>` summary
-2. `get-comments` with `discussion_id` — read full thread
-3. `create-comment` with `discussion_id` — reply
-4. `create-comment` with `selection_with_ellipsis` — start a new thread on specific content
-5. `create-comment` with just `page_id` — add a general page-level comment
-
-## Limitations
-
-- **No edit/update** — comments cannot be modified after creation
-- **No delete** — comments cannot be removed via this server
-- **No resolution** — cannot mark discussions as resolved via this server

package/framework/skills/notion-mcp/references/databases.md

@@ -1,193 +0,0 @@
-# Database Management
-
-## Overview
-
-Notion databases consist of views on top of data sources. A data source (collection) holds the actual schema and pages. A database can have multiple data sources (linked databases). Use `fetch` first to get the database structure and data source IDs from `<data-source>` tags.
-
-```
-fetch
-  id: "database-uuid-here"
-```
-
-## Create Database
-
-Uses SQL DDL syntax to define the schema:
-
-```
-create-database
-  title: "Tasks"
-  parent:
-    page_id: "abc123..."           # where to place the database
-  schema: |
-    CREATE TABLE (
-      "Task Name" TITLE,
-      "Status" SELECT('To Do':red, 'In Progress':yellow, 'Done':green),
-      "Priority" NUMBER FORMAT 'dollar',
-      "Due Date" DATE,
-      "Assignee" PEOPLE,
-      "Tags" MULTI_SELECT('eng':blue, 'design':pink),
-      "URL" URL,
-      "Email" EMAIL,
-      "Complete" CHECKBOX,
-      "Task ID" UNIQUE_ID PREFIX 'TASK'
-    )
-  description: "Team task tracker"
-```
-
-### Column types
-
-| Type | SQL Syntax |
-|------|------------|
-| Title | `TITLE` |
-| Rich text | `RICH_TEXT` |
-| Date | `DATE` |
-| People | `PEOPLE` |
-| Checkbox | `CHECKBOX` |
-| URL | `URL` |
-| Email | `EMAIL` |
-| Phone | `PHONE_NUMBER` |
-| Status | `STATUS` |
-| Files | `FILES` |
-| Number | `NUMBER [FORMAT 'dollar']` |
-| Select | `SELECT('opt1':red, 'opt2':blue)` |
-| Multi-select | `MULTI_SELECT('opt1':green, 'opt2':pink)` |
-| Formula | `FORMULA('prop("A") + prop("B")')` |
-| Relation | `RELATION('data_source_id')` or `RELATION('ds_id', DUAL)` |
-| Rollup | `ROLLUP('relation_prop', 'target_prop', 'function')` |
-| Unique ID | `UNIQUE_ID [PREFIX 'X']` |
-| Created time | `CREATED_TIME` |
-| Last edited | `LAST_EDITED_TIME` |
-
-Column colors: `default`, `gray`, `brown`, `orange`, `yellow`, `green`, `blue`, `purple`, ` pink`, `red`
-
-Add descriptions: `"Status" STATUS COMMENT 'Current task status'`
-
-### Self-referencing relation (two-step)
-
-1. Create the database without the relation
-2. Use `update-data-source` with the returned `data_source_id` to add the relation:
-
-```
-update-data-source
-  data_source_id: "abc123..."
-  statements: |
-    ADD COLUMN "Parent" RELATION('abc123...', DUAL 'Children' 'children');
-    ADD COLUMN "Children" RELATION('abc123...', DUAL 'Parent' 'parent')
-```
-
-## Update Data Source
-
-Modify a data source's schema, title, or description.
-
-```
-update-data-source
-  data_source_id: "f336d0bc-..."
-  title: "Project Tracker 2025"
-
-  statements: |
-    ADD COLUMN "Priority" SELECT('High':red, 'Medium':yellow, 'Low':green);
-    ADD COLUMN "Due Date" DATE;
-    RENAME COLUMN "Status" TO "Progress";
-    ALTER COLUMN "Priority" SET SELECT('P0':red, 'P1':orange, 'P2':green);
-    DROP COLUMN "Old Column"
-```
-
-### Statements
-
-- `ADD COLUMN "Name" <type>` — add a property
-- `DROP COLUMN "Name"` — remove a property (only if unused in views)
-- `RENAME COLUMN "Old" TO "New"` — rename a property
-- `ALTER COLUMN "Name" SET <type>` — change type/options
-- `ALTER COLUMN "Name" SET COMMENT 'new description'` — update description
-
-Cannot delete or create title properties. Max one `UNIQUE_ID` property.
-
-## Views
-
-### Create View
-
-```
-create-view
-  data_source_id: "abc123..."
-  name: "Sprint Board"
-  type: "board"                 # table, board, list, calendar, timeline, gallery, form, chart, map, dashboard
-  configure: |
-    GROUP BY "Status";
-    SORT BY "Due Date" ASC;
-    FILTER "Priority" != "Low"
-```
-
-Or add a view to an existing database:
-
-```
-create-view
-  database_id: "abc123..."
-  data_source_id: "abc123..."
-  name: "All Tasks"
-  type: "table"
-```
-
-Or create a linked database view on a page:
-
-```
-create-view
-  parent_page_id: "ghi789..."
-  data_source_id: "abc123..."
-  name: "Company tasks"
-  type: "table"
-  configure: |
-    FILTER "Company" = "Acme"
-```
-
-### View types and required directives
-
-| View type | Required |
-|-----------|----------|
-| table | — |
-| board | `GROUP BY "Property"` |
-| list | — |
-| calendar | `CALENDAR BY "DateProperty"` |
-| timeline | `TIMELINE BY "Start" TO "End"` |
-| gallery | — |
-| form | — |
-| chart | `CHART column\|bar\|line\|donut\|number` |
-| map | `MAP BY "LocationProperty"` |
-| dashboard | — |
-
-### View DSL directives
-
-```
-FILTER "Status" = "In Progress"           # filter rows
-SORT BY "Due Date" ASC                     # sort rows
-GROUP BY "Status"                          # group/board columns
-CALENDAR BY "Date"                         # calendar date property
-TIMELINE BY "Start" TO "End"               # timeline date range
-MAP BY "Location"                          # map location property
-CHART bar AGGREGATE count                  # chart type + aggregation
-SHOW "Name", "Status", "Due Date"          # visible properties
-HIDE "Internal Note"                        # hidden properties
-COVER "Image"                              # cover image property
-WRAP CELLS true                             # wrap cell content
-FREEZE COLUMNS 2                            # freeze first N columns
-FORM CLOSE | OPEN                           # form submissions
-FORM ANONYMOUS true | false                 # anonymous submissions
-FORM PERMISSIONS none | reader | editor    # form submission permissions
-```
-
-### Update View
-
-```
-update-view
-  view_id: "abc123..."          # view:// URI, Notion URL with ?v=, or bare UUID
-  name: "Q1 Sprint Board"
-  configure: |
-    CLEAR FILTER;
-    CLEAR SORT;
-    GROUP BY "Priority"
-```
-
-### Clear directives
-
-- `CLEAR FILTER` — remove all filters
-- `CLEAR SORT` — remove all sorts
-- `CLEAR GROUP BY` — remove grouping