Records important technical designs, bug fixes, and architecture decisions in a structured KB.
Install
mkdir -p .claude/skills/kb && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17314" && unzip -o skill.zip -d .claude/skills/kb && rm skill.zipInstalls to .claude/skills/kb
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Capture important architectural decisions, bug patterns, feature designs, or other critical findings into the project knowledge base. Use proactively when significant technical decisions are made, non-obvious bugs are resolved, new subsystems are designed, or important product features are discussed.Key capabilities
- →Capture architectural decisions into the knowledge base
- →Document non-obvious bug root causes
- →Record new subsystem designs and data formats
- →Capture significant refactor changes
- →Document product strategy and feature scope discussions
- →Store performance investigation findings
How it works
The skill captures important technical information by creating a new markdown file in a categorized directory within `lambda/scripts/memory/` and updating the `INDEX.md` with a one-liner entry.
Inputs & outputs
When to use kb
- →Capturing architectural decisions
- →Documenting bug root causes
- →Designing future features
About this skill
Knowledge Base Capture
Capture this into the knowledge base: $ARGUMENTS
Knowledge Base Location
All files live in lambda/scripts/memory/. The index is at lambda/scripts/memory/INDEX.md.
Step 1: Read the current index
Read lambda/scripts/memory/INDEX.md to understand what's already captured and avoid duplicates.
Step 2: Choose a category
| Category | Directory | When to use |
|---|---|---|
| Architecture | architecture/ | System design, infrastructure, sync protocols, data formats, tech stack choices |
| Decisions | decisions/ | "We chose X over Y because Z" — explicit tradeoff analysis |
| Features | features/ | Product feature descriptions, UX designs, user-facing behavior |
| Bugs | bugs/ | Non-obvious bug root causes, debugging patterns worth remembering |
| Future Plans | futureplans/ | Planned work not yet started — roadmap items, RFCs for future features |
| SEO | seo/ | SEO research, keyword analysis, backlink data, Core Web Vitals |
If none fit, create a new category directory and add a section to INDEX.md.
Step 3: Create the entry file
Filename: lowercase-kebab-case, descriptive. Example: watch-echo-loop-bug.md
Entry format:
---
date: YYYY-MM-DD
tags: [relevant, tags]
---
# Title
Concise description of the finding/decision/pattern.
Keep it 5-20 lines. Link to relevant source files where useful.
Focus on the WHY and the non-obvious parts — assume the reader is a developer familiar with the codebase.
Step 4: Update INDEX.md
Add a one-liner entry under the appropriate category heading:
- [filename.md](category/filename.md) — concise one-liner (max 80 chars)
Keep entries sorted by relevance within each category (most important first), not by date.
When to auto-invoke this skill
Capture knowledge when ANY of these happen during a conversation:
- An architectural decision is made (chose X over Y)
- A non-obvious bug root cause is discovered
- A new subsystem or data format is designed
- A significant refactor changes how something works
- The user discusses product strategy or feature scope
- Performance investigation reveals important findings
- A workaround for an external limitation is implemented
Do NOT capture:
- Routine code changes (rename variable, fix typo)
- Information already in the knowledge base
- Temporary debugging steps
- Anything the user explicitly says is experimental/throwaway
When not to use it
- →When documenting routine code changes like variable renames or typos
- →When the information is already present in the knowledge base
- →When recording temporary debugging steps
Limitations
- →The knowledge base files are located in `lambda/scripts/memory/`
- →Entries must be 5-20 lines and focus on the WHY and non-obvious parts
- →The skill does not capture routine code changes or temporary debugging steps
How it compares
This skill provides a structured and indexed way to store critical project knowledge, ensuring that important decisions and findings are easily retrievable, unlike informal notes or undocumented discussions.
Compared to similar skills
kb side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| kb (this skill) | 0 | 4mo | No flags | Beginner |
| ejs-session-init | 0 | 4mo | Review | Beginner |
| meeting-minutes | 41 | 5mo | No flags | Beginner |
| notion-knowledge-capture | 10 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
ejs-session-init
McFuzzySquirrel
>
meeting-minutes
github
Generate concise, actionable meeting minutes for internal meetings. Includes metadata, attendees, agenda, decisions, action items (owner + due date), and follow-up steps.
notion-knowledge-capture
makenotion
Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.
super-save
supermemoryai
Save important project knowledge to memory. Use when user wants to preserve architectural decisions, significant bug fixes, design patterns, or important implementation details for team reference.
knowledge-base
incidentfox
Search runbooks, documentation, and knowledge base articles from Confluence. Use when looking for incident response procedures, service documentation, post-mortems, or troubleshooting guides.
decision-logger
alirezarezvani
Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.