@antaif3ng/til-work 0.1.2 → 0.2.0

package/skills/playwright-mcp/SKILL.md

@@ -0,0 +1,90 @@
+---
+name: playwright-mcp
+description: "Browser automation via Playwright MCP server. Use when the user needs to navigate websites, click elements, fill forms, extract data, take screenshots, or perform browser automation workflows."
+---
+
+# Playwright MCP Skill
+
+Browser automation powered by Playwright MCP server.
+
+## Prerequisites
+
+Install the Playwright MCP server:
+
+```bash
+npm install -g @playwright/mcp
+npx playwright install chromium
+```
+
+## MCP Configuration
+
+Add to your `~/.til/config.json`:
+
+```json
+{
+  "mcpServers": {
+    "playwright": {
+      "command": "npx",
+      "args": ["@playwright/mcp", "--headless"]
+    }
+  }
+}
+```
+
+For headed mode (visible browser):
+```json
+{
+  "mcpServers": {
+    "playwright": {
+      "command": "npx",
+      "args": ["@playwright/mcp"]
+    }
+  }
+}
+```
+
+## MCP Tools Reference
+
+| Tool | Description |
+|------|-------------|
+| `browser_navigate` | Navigate to URL |
+| `browser_click` | Click element by CSS selector or coordinates |
+| `browser_type` | Type text into input field |
+| `browser_select_option` | Select dropdown option |
+| `browser_get_text` | Get text content of element or page |
+| `browser_evaluate` | Execute JavaScript in page context |
+| `browser_snapshot` | Get accessible page snapshot (recommended before interactions) |
+| `browser_close` | Close browser context |
+| `browser_choose_file` | Upload file to input |
+| `browser_press` | Press keyboard key (Enter, Tab, etc.) |
+
+## Workflow
+
+1. **Navigate** to the target URL
+2. **Snapshot** to understand the page structure
+3. **Interact** with elements (click, type, select)
+4. **Extract** data or take screenshots as needed
+5. **Close** when done
+
+## Configuration Options
+
+| Flag | Description |
+|------|-------------|
+| `--allowed-hosts` | Restrict navigation to specific hosts |
+| `--blocked-origins` | Block specific origins |
+| `--browser` | Browser engine (chromium, firefox, webkit) |
+| `--headless` | Run without visible browser window |
+| `--viewport-size` | Set viewport dimensions (e.g. "1280x720") |
+| `--timeout-action` | Action timeout in ms |
+| `--timeout-navigation` | Navigation timeout in ms |
+| `--output-dir` | Directory for screenshots and traces |
+| `--save-trace` | Save Playwright trace file |
+| `--save-video` | Record browser session video |
+
+## Tips
+
+- Always use `browser_snapshot` before interacting with elements
+- Use CSS selectors for reliable element targeting
+- Set appropriate timeouts for slow-loading pages
+- Use `--headless` in CI/automation environments
+- Use `browser_evaluate` for complex page manipulation

package/skills/self-improving-agent/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: self-improvement
+description: "Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects you, (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) You realize your knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task."
+---
+
+# Self-Improving Agent
+
+Captures learnings, errors, and corrections into structured files for continuous improvement across sessions.
+
+## Trigger Conditions
+
+Activate this skill when:
+1. A command or operation fails unexpectedly
+2. User corrects you ("No, that's wrong...", "Actually...")
+3. User requests a capability that doesn't exist
+4. An external API or tool fails
+5. You realize your knowledge is outdated or incorrect
+6. A better approach is discovered for a recurring task
+
+## Storage Structure
+
+All learnings are stored in the project's `.til/` directory:
+
+```
+.til/
+├── MEMORY.md          # Persistent memory (existing system)
+└── learnings/
+    ├── LEARNINGS.md   # Corrections, knowledge gaps, best practices
+    ├── ERRORS.md      # Command failures, API errors, exceptions
+    └── FEATURE_REQUESTS.md  # User needs, missing capabilities
+```
+
+## Entry Format
+
+Each entry follows this format:
+
+```markdown
+### [ID] Short Title
+- **Date**: YYYY-MM-DD
+- **Context**: What was happening
+- **Issue**: What went wrong / what was learned
+- **Resolution**: How it was fixed / the correct approach
+- **Tags**: #category #subcategory
+```
+
+**ID format**: `TYPE-YYYYMMDD-XXX`
+- `LRN-20250115-001` for learnings
+- `ERR-20250115-001` for errors
+- `FRQ-20250115-001` for feature requests
+
+## How to Record
+
+### On Error
+1. Capture the exact error message
+2. Document what was attempted
+3. Record the fix or workaround
+4. Add to `ERRORS.md`
+
+### On Correction
+1. Note what you said that was wrong
+2. Record the correct information from the user
+3. Update your understanding
+4. Add to `LEARNINGS.md`
+
+### On Feature Request
+1. Document what the user wanted
+2. Note current limitations
+3. Suggest possible implementations
+4. Add to `FEATURE_REQUESTS.md`
+
+## Before Major Tasks
+
+Before starting a complex task, review existing learnings:
+```bash
+# Check for relevant past learnings
+cat .til/learnings/LEARNINGS.md
+cat .til/learnings/ERRORS.md
+```
+
+This helps avoid repeating past mistakes and apply discovered best practices.
+
+## Promoting Learnings
+
+When a learning is important enough, promote it to persistent memory:
+- Write to `~/.til/MEMORY.md` (global, cross-project) using the write tool
+- Write to `.til/MEMORY.md` (project-specific) using the write tool
+
+This ensures the learning persists across sessions via the existing memory system.

package/skills/skill-creator/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: skill-creator
+description: "Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations."
+---
+
+# Skill Creator
+
+Guide for creating effective agent skills.
+
+## Skill Structure
+
+A skill is a directory containing a `SKILL.md` file:
+
+```
+my-skill/
+├── SKILL.md          # Required: frontmatter + instructions
+├── scripts/          # Optional: helper scripts
+├── references/       # Optional: reference docs
+└── assets/           # Optional: templates, configs
+```
+
+## SKILL.md Format
+
+```markdown
+---
+name: my-skill
+description: "One-line description. Include WHEN to use this skill."
+---
+
+# Skill Title
+
+Instructions for the agent...
+```
+
+### Frontmatter Rules
+
+- `name`: kebab-case, max 64 characters
+- `description`: **Critical** — this is the primary trigger. Must include:
+  - What the skill does
+  - When to activate it (trigger phrases)
+  - Keep under 160 characters for the summary
+
+## Core Principles
+
+### 1. Concise over verbose
+Context window is a shared resource. Every token in a skill competes with the user's conversation.
+
+### 2. Progressive disclosure
+- **Level 1**: Frontmatter (always loaded) — triggers activation
+- **Level 2**: SKILL.md body (loaded on demand via read tool) — detailed instructions
+- **Level 3**: Bundled resources (loaded as needed) — scripts, references
+
+### 3. Appropriate freedom
+Don't over-constrain. Give the agent guidelines, not rigid scripts.
+
+## Creating a Skill — Step by Step
+
+### Step 1: Define the purpose
+What specific task does this skill help with? Be concrete.
+
+### Step 2: Write the description
+This is the most important part. The description determines when the agent loads the skill.
+
+Bad: "Helps with code"
+Good: "Generate comprehensive test suites for TypeScript projects. Use when the user asks to write tests, add test coverage, or set up a testing framework."
+
+### Step 3: Write instructions
+Structure as:
+1. **When to use** — trigger conditions
+2. **How to do it** — step-by-step workflow
+3. **Tools/commands** — specific commands or tools to use
+4. **Examples** — concrete examples
+5. **Pitfalls** — common mistakes to avoid
+
+### Step 4: Test the skill
+Place in `~/.til/skills/my-skill/SKILL.md` and verify:
+- Does it trigger on the right queries?
+- Are the instructions clear enough?
+- Does it produce good results?
+
+## Installation Paths
+
+- **Global**: `~/.til/skills/<skill-name>/SKILL.md`
+- **Project**: `.til/skills/<skill-name>/SKILL.md`
+- **CLI**: `til --skill /path/to/skill-dir`
+
+## Tips
+
+- Keep SKILL.md under 200 lines — longer skills should use bundled references
+- Use markdown headers for structure — the agent processes these well
+- Include example commands that the agent can run directly
+- Reference tool names that exist in the agent's toolkit (bash, read, write, edit, etc.)
+- Test with real user queries, not just ideal inputs

package/skills/summarize/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: summarize
+description: "Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube). Use when the user asks to summarize a webpage, document, PDF, or video."
+---
+
+# Summarize
+
+Fast CLI to summarize URLs, local files, and YouTube links.
+
+## Quick start
+
+```bash
+summarize "https://example.com" --model google/gemini-3-flash-preview
+summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview
+summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto
+```
+
+## Model + keys
+
+Set the API key for your chosen provider:
+- OpenAI: `OPENAI_API_KEY`
+- Anthropic: `ANTHROPIC_API_KEY`
+- xAI: `XAI_API_KEY`
+- Google: `GEMINI_API_KEY` (aliases: `GOOGLE_GENERATIVE_AI_API_KEY`, `GOOGLE_API_KEY`)
+
+Default model is `google/gemini-3-flash-preview` if none is set.
+
+## Useful flags
+
+- `--length short|medium|long|xl|xxl`
+- `--max-output-tokens <n>`
+- `--extract-only` (URLs only)
+- `--json` (machine readable)
+- `--firecrawl auto|off|always` (fallback extraction)
+- `--youtube auto` (Apify fallback if `APIFY_API_TOKEN` set)
+
+## Config
+
+Optional config file: `~/.summarize/config.json`
+
+```json
+{ "model": "openai/gpt-5.2" }
+```
+
+Optional services:
+- `FIRECRAWL_API_KEY` for blocked sites
+- `APIFY_API_TOKEN` for YouTube fallback
+
+## Prerequisites
+
+Install the summarize CLI:
+```bash
+brew install steipete/tap/summarize
+```
+Or check https://summarize.sh/ for other installation methods.