add-lesson

Add a new lesson learned to shared rules and sync to context files.

16 stars

Best use case

add-lesson is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Add a new lesson learned to shared rules and sync to context files.

Teams using add-lesson should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/add-lesson/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/cli-automation/add-lesson/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/add-lesson/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How add-lesson Compares

Feature / Agentadd-lessonStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Add a new lesson learned to shared rules and sync to context files.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Add Lesson Skill

Add a new lesson learned to the shared rules.

## Overview

When you discover a bug, mistake, or useful pattern, use this skill to document it so all agents learn from it.

## Usage

```
/add-lesson
```

## Prerequisites

- Access to `shared-rules/` and permission to run `scripts/sync-rules.py`.

## Lesson Template

```markdown
### YYYY-MM-DD - Brief Title

- **Issue**: What went wrong or was discovered
- **Root Cause**: Why it happened
- **Fix**: How it was fixed
- **Prevention**: Rule or check to prevent recurrence
- **Applies To**: all | claude | cursor | gemini
- **Files Changed**: List of affected files
```

## Process

1. **Gather information**:
   - What was the issue?
   - What caused it?
   - How was it fixed?
   - How can we prevent it?

2. **Add to lessons file**:
   - Open `shared-rules/lessons-learned.md`
   - Add new entry at TOP of "Recent Lessons" section
   - Use the template format

3. **Run sync**:
   ```bash
   python scripts/sync-rules.py
   ```

4. **Verify propagation**:
   - Check CLAUDE.md updated
   - Check timestamp

## Example

```markdown
### 2026-01-22 - Task Tool Token Efficiency

- **Issue**: Spawning Claude workers via subprocess was expensive (~13k tokens overhead)
- **Root Cause**: Full context duplication to each subprocess
- **Fix**: Use native Task tool with context filtering
- **Prevention**: Always prefer Task tool over subprocess for Claude workers
- **Applies To**: claude
- **Files Changed**:
  - `.claude/skills/implement-task/SKILL.md`
  - `CLAUDE.md`
```

## Categories

Lessons should be categorized by:
- `all` - Applies to all agents
- `claude` - Claude-specific
- `cursor` - Cursor-specific
- `gemini` - Gemini-specific

## Archiving

After 30 days or when list gets long:
- Move old lessons to "Archived Lessons" section
- Keep for historical reference

## Outputs

- Updated `shared-rules/` content and synced context files (e.g. `CLAUDE.md`).

## Error Handling

- If sync fails, do not proceed; resolve and rerun `scripts/sync-rules.py`.
- If lesson template is incomplete, request the missing fields before adding.

## Related Skills

- `/sync-rules` - Sync shared rules into context files

Related Skills

learned-lesson

16
from diegosouzapw/awesome-omni-skill

Captura e armazena licoes tecnicas de bug fixes ou decisoes arquiteturais

bgo

10
from diegosouzapw/awesome-omni-skill

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Coding & Development

openweather-api-automation

16
from diegosouzapw/awesome-omni-skill

Automate Openweather API tasks via Rube MCP (Composio). Always search tools first for current schemas.

opentangl

16
from diegosouzapw/awesome-omni-skill

Not a code generator — an entire dev team. You write the vision, it ships the code. Autonomous builds, PRs, reviews, and merges across multiple repos. Point it at any JS/TS project and a product vision. It plans features, writes code, verifies builds, creates PRs, reviews diffs, and merges — autonomously. Manages multiple repos as one product. Use when you want to ship code without writing it. AI code generation, autonomous development, workflow automation, multi-repo orchestration, TypeScript, JavaScript, GitHub, OpenAI, Anthropic, Claude, GPT, LLM, devtools, CI/CD, pull requests, code review.

openhue

16
from diegosouzapw/awesome-omni-skill

Philips Hue smart lights control

opencode

16
from diegosouzapw/awesome-omni-skill

OpenCode - Open source AI coding agent for terminal, desktop, and IDE with multi-provider LLM support, custom agents, MCP integration, and granular permissions

opencode-plugin-builder

16
from diegosouzapw/awesome-omni-skill

This skill should be used when creating, modifying, or debugging OpenCode plugins. It provides the complete plugin architecture, available hooks, event types, SDK client methods, and best practices learned from real-world plugin development.

openclaw-sentry-pro

16
from diegosouzapw/awesome-omni-skill

Full secret scanning suite: detect leaked API keys, tokens, and credentials, then automatically redact, quarantine exposed files, and enforce .gitignore policies. Everything in openclaw-sentry (free) plus automated countermeasures.

opence-skill-creator

16
from diegosouzapw/awesome-omni-skill

Learn how to create effective project skills following opence conventions.

openapi-to-application-java-spring-boot-openapi-to-application-c

16
from diegosouzapw/awesome-omni-skill

Generate a complete, production-ready application from an OpenAPI specification Use when: the task directly matches openapi to application code responsibilities within plugin openapi-to-application-java-spring-boot. Do not use when: a more specific framework or task-focused skill is clearly a better match.

openapi-to-application-code

16
from diegosouzapw/awesome-omni-skill

Generate a complete, production-ready application from an OpenAPI specification. Use when creating controllers, services, models, and configurations from an OpenAPI/Swagger spec.

openapi-spec-generation

16
from diegosouzapw/awesome-omni-skill

Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.