cfn-knowledge-base
MUST BE USED after every CFN Loop execution to capture successful patterns. Query before repeating any task type to retrieve prior learnings and avoid re-solving solved problems. Organizational learning from CFN Loop execution - workflow codification and playbooks.
Best use case
cfn-knowledge-base is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
MUST BE USED after every CFN Loop execution to capture successful patterns. Query before repeating any task type to retrieve prior learnings and avoid re-solving solved problems. Organizational learning from CFN Loop execution - workflow codification and playbooks.
Teams using cfn-knowledge-base 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cfn-knowledge-base/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cfn-knowledge-base Compares
| Feature / Agent | cfn-knowledge-base | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
MUST BE USED after every CFN Loop execution to capture successful patterns. Query before repeating any task type to retrieve prior learnings and avoid re-solving solved problems. Organizational learning from CFN Loop execution - workflow codification and playbooks.
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
# Knowledge Base Skill (Mega-Skill)
**Version:** 1.0.0
**Purpose:** Organizational learning from CFN Loop execution
**Status:** Production
**Consolidates:** workflow-codification, cfn-playbook
**Confidence:** 7.0/10 (dual learning systems)
---
## Overview
This mega-skill provides organizational learning:
- **Workflow** - Track edge cases, failures, cost metrics, ROI
- **Playbook** - Store successful patterns, agent configs, iteration strategies
---
## Directory Structure
```
knowledge-base/
├── SKILL.md # This file
├── execute.sh # Main entry point
├── cli/
│ └── knowledge-base.sh # Unified CLI interface
├── lib/
│ ├── workflow/ # From workflow-codification
│ └── playbook/ # From cfn-playbook
└── data/ # Database files (created on init)
├── workflows.db
├── playbooks.db
└── learnings.db
```
---
## Learning System
- **Successes** → Playbook (what worked)
- **Failures** → Workflow codification (what to avoid)
- Combined: Complete organizational memory
---
## Migration Paths
| Old Path | New Path |
|----------|----------|
| workflow-codification/ | knowledge-base/lib/workflow/ |
| cfn-playbook/ | knowledge-base/lib/playbook/ |
---
## Usage
### Main Entry Point
```bash
# Initialize databases
./execute.sh init
# Query for patterns
./execute.sh query 'authentication'
# Store new learning
./execute.sh store playbook '{"task_type": "auth", "pattern": "..."}'
# Show help
./execute.sh help
```
### Advanced CLI Usage
```bash
# Direct CLI access
./cli/knowledge-base.sh --help
# Query workflow patterns
./cli/knowledge-base.sh query-workflow --pattern 'auth'
# Query playbook entries
./cli/knowledge-base.sh query-playbook --task-type bugfix
# Store learning with metadata
./cli/knowledge-base.sh store-learning \
--type workflow \
--category edge-case \
--data '...' \
--confidence 0.85
```
## Version History
### 1.1.0 (2025-12-08)
- Fixed bootstrap utilities path to use shared location
- Created unified CLI interface
- Added main execute.sh entry point
- Integrated workflow and playbook functionality
### 1.0.0 (2025-12-02)
- Consolidated workflow + playbook into unified knowledge base
---
## Learnings Integration
A lightweight per-project learnings system complements the knowledge base. While the knowledge base stores structured workflow and playbook data in SQLite, the learnings system uses append-only JSONL files for fast, low-friction logging of patterns, pitfalls, and preferences discovered during agent work.
See [LEARNINGS.md](./LEARNINGS.md) for the full specification, including storage format, subcommands (`/learn`), auto-logging hooks, and pruning rules.Related Skills
supabase-schema-sync
Introspects Supabase DB after migrations and updates project db-query skill with current schema. Run after any migration to keep agent context accurate.
commit
Stage, commit, and push changes using a background github-commit-agent. Accepts optional args for message override or push control.
cfn-vote-implement
MUST BE USED after cfn-dry-review or cfn-alpha-launch:manifest produces a manifest. Also the verification phase of /cfn-loop-task. Do not manually implement code review suggestions - always route through this skill. 3-agent specialized voting. Unanimous (3/3) auto-implemented with TDD. 2/3 routed to product-owner agent. 1/3 surfaced to user via AskUserQuestion (batched 4 per call, at end).
cfn-utilities
Reusable bash utility functions for CFN Loop - logging, error handling, retry, file operations. Use when you need structured logging, atomic file operations, retry logic with exponential backoff, or standardized error handling in bash scripts.
CFN Test Runner Skill
**Version:** 1.0.0
cfn-test-framework
Test execution, running, and webapp testing for CFN
cfn-task-planning
Classify tasks, initialize structured configs with scope boundaries, decompose complex tasks
Specialist Injection Skill
## Purpose
!/bin/bash
# cfn-task-intelligence.sh
Task Complexity Estimator
**Version:** 1.0.0
task-classifier
Analyzes task descriptions and classifies them into categories for agent selection
cfn-task-intelligence
Classify tasks (type/domain), estimate complexity/iterations, recommend specialists from feedback themes