Agent skill

add-note

Use this skill whenever important information is learned during a task or when the user explicitly asks to store something. Use when users ask to remember. Triggers on "remember this", "update memory", "share" or any persistent storage request.

Stars 0
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/timbuchinger/loadout/tree/main/skills/add-note

SKILL.md

Be proactive, but intentional:

  • Store CLI commands, API endpoints, error resolutions, operational gotchas, patterns, and internal processes
  • Prefer small, focused, reusable notes
  • If the information would save time if recalled later, it likely belongs here

What this skill does

Stores a structured knowledge note in Qdrant for retrieval by AI coding agents.

This skill uses the Qdrant MCP server via the qdrant-add-note tool.


Collection

All notes are stored in the following collection: notes-hybrid


Storage guardrails (IMPORTANT)

These rules must be followed exactly:

  • Do not store test notes unless they contain a concrete, reusable learning
  • Context is required unless the text is completely self-explanatory
  • Only use the fields supported by the qdrant-add-note tool
  • All required fields must be provided

If any rule is violated, do not store the note.


Minimum acceptable note

A note must meet at least this standard:

Required parameters:

  • text: concrete command, endpoint, or learning
  • context: when or why this is useful
  • type: one of cli, api, learning, snippet, or pattern
  • created_at: ISO-8601 timestamp

If you cannot fill in all required fields meaningfully, do not store the note.


Fields and how to use them

text (required)

The primary knowledge content.

  • One command, endpoint, rule, or learning
  • Must be understandable without chat history

Good examples:

  • kubectl rollout restart deployment my-app -n prod
  • Avoid using async forEach in Node.js; it does not await promises

Bad examples:

  • testing the note system
  • this worked

context (required unless self-explanatory)

Explains when, why, or how the text is useful. Include:

  • Conditions
  • Warnings
  • Operational context

If you cannot explain the usefulness, do not store the note.


type (required)

Choose exactly one:

  • cli
  • api
  • learning
  • snippet
  • pattern

tool (optional but recommended)

The tool, system, or service involved.

Examples:

  • kubectl
  • aws
  • terraform
  • internal-api
  • github-actions

tags (optional)

Array of short, lowercase keywords describing concepts or domains.

Examples:

  • ["kubernetes", "deployments"]
  • ["auth", "debugging"]
  • ["terraform", "aws"]

language (optional)

Use for code or CLI-related notes.

Examples:

  • bash
  • python
  • yaml
  • json

source (optional)

Where this knowledge applies.

Examples:

  • personal-notes
  • repo:infra
  • service:billing
  • team:platform

created_at (required)

ISO-8601 timestamp. Use the current date/time if not explicitly provided.


Tool usage

Use the qdrant-add-note MCP tool with the following parameters:

Required:

  • text (string)
  • context (string)
  • type (string: cli | api | learning | snippet | pattern)
  • created_at (string: ISO-8601 timestamp)

Optional:

  • tool (string)
  • tags (array of strings)
  • language (string)
  • source (string)

The tool handles vector generation and storage automatically.


Pre-store quality checklist

Before storing, confirm:

  • Would another agent benefit from this in 30 days?
  • Is the note understandable without chat history?
  • Does context clearly explain when or why it applies?
  • Is this more than a test or confirmation?

If any answer is no, do not store the note.


Agent reminder

When in doubt:

Check existing notes first. Store only what improves future decisions.

Expand your agent's capabilities with these related and highly-rated skills.

timbuchinger/loadout

brainstorming

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

0 0
Explore
timbuchinger/loadout

user-story

Creates well-structured user stories for software development and project management. Use when the user asks to write, create, or format a user story, or needs to document requirements, features, or tasks in user story format.

0 0
Explore
timbuchinger/loadout

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

0 0
Explore
timbuchinger/loadout

kubernetes-troubleshoot

Troubleshoot and manage Kubernetes clusters, including resource inspection, debugging, pod logs, events, and cluster operations. Use when the user needs to diagnose issues, inspect workloads, analyze pod failures, or perform Kubernetes cluster operations.

0 0
Explore
timbuchinger/loadout

writing-plans

Use when design is complete and you need detailed implementation tasks - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming minimal codebase familiarity

0 0
Explore
timbuchinger/loadout

1password

Manage personal secrets and passwords using 1Password CLI (op). Use when the user asks to query, retrieve, create, or manage secrets in 1Password, 1p, or op. This is for personal secrets only - not for cloud provider secret managers like Azure Key Vault, AWS Secrets Manager, or GCP Secret Manager.

0 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results