Agent skill

Document Learnings

by pando85 in pando85/kaniop

Guidelines for documenting reusable patterns discovered during work.

AGPL-3.0Auto-check passedDevOps & Cloud

Install Document Learnings

skills CLI
$ npx skills add pando85/kaniop --skill document-learnings -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pando85/kaniop document-learnings --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pando85/kaniop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/document-learnings .claude/skills/document-learnings && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
document-learnings
GitHub stars
130
Token cost
~501 tokens
SKILL.md length
187 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Guidelines for documenting reusable patterns discovered during work.

  • Completing tasks that reveal non-obvious workflows
  • SKILL.md covers Purpose, When to Document, When NOT to Document and Where to Put Documentation, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Project conventions

What it does

Document Learnings is an agent skill from pando85/kaniop. Guidelines for documenting reusable patterns discovered during work. Use when completing tasks that reveal non-obvious workflows or project conventions.

Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. It works with Kubernetes. The repository describes itself as: Kubernetes operator for managing Kanidm. The licence is AGPL-3.0.

When your agent uses it

  • Completing tasks that reveal non-obvious workflows
  • Project conventions

Example prompts

  • “Use the document-learnings skill to guideline for documenting reusable patterns discovered during work”
  • “/document-learnings”

What it can do on your machine

Read from SKILL.md and the folder at commit 768ac0b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Document Learnings loads about 501 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 187 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~501

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pando85/kaniop at commit 768ac0b, republished under its AGPL-3.0 licence (© pando85). 187 words, ~501 tokens.

Download SKILL.mdSave it as .claude/skills/document-learnings/SKILL.md (or your agent's skills folder).
name
document-learnings
description
Guidelines for documenting reusable patterns discovered during work. Use when completing tasks that reveal non-obvious workflows or project conventions.

Purpose

Capture reusable knowledge so future sessions avoid repeated debugging and rediscovery.

When to Document

  • After discovering a required workflow with multiple mandatory steps
  • After fixing a non-obvious bug or uncovering a subtle constraint
  • After establishing a new pattern or convention
  • After the user corrects the model's approach — this reveals the user's preferred way of working
  • When the user asks to document learnings

When NOT to Document

  • Obvious or standard practices
  • One-off debugging that won't recur
  • Information already well-covered in existing docs

Where to Put Documentation

ScopeLocation
Public user documentationDocumentation/src/
Architecture decisionsdocs/adr/NNNN-*.md and docs/adr/README.md
Durable intent, specification, and planintent/<work-item>/{intent,spec,plan}.md
Project-specific agent workflows.opencode/skills/<name>/SKILL.md
Short reference needed every invocationAGENTS.md
Reproducible agent regressionevals/cases/<name>/

Skill File Format

---
name: skill-name
description: Short description. Use when ...
---

## Purpose
What this skill covers.

## Instructions
### 1. Step One
Specific, actionable steps with code examples.

## Common Pitfalls
| Pitfall | Fix |
|---------|-----|
| ... | ... |

Tips

  • Keep skill descriptions actionable
  • Include code examples and common pitfalls tables
  • Commit skills to the repo so the whole team benefits
  • Pay special attention when the user corrects or refines the model's output — that feedback encodes the user's standards and preferences for this project
  • Document the "why" behind conventions, not just the "what" — e.g., why a checklist exists, what goes wrong if a step is skipped

© pando85, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .opencode/skills/document-learnings of pando85/kaniop.

Open the folder on GitHubat commit 768ac0b

Compare with similar skills

Document Learnings next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Document Learnings compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Document Learnings this skillpando85/kaniop130—~501Automated safety check: PassAGPL-3.0
KubeSphere Multi-Tenant Managementkubesphere/kubesphere17k1 repos~3.1kAutomated safety check: PassCustom licence
Azure Diagnosticsmicrosoft/azure-skills1.5k1 repos~1.6kAutomated safety check: PassMIT
Kubeshark Installerkubeshark/kubeshark12k—~3.6kAutomated safety check: NotesApache-2.0
Sim Helmsimstudioai/sim30k—~2.2kAutomated safety check: PassApache-2.0
Helm Chart ScaffoldingCybereason-Public/owLSM28013 repos~381Automated safety check: PassGPL-2.0

Similar skills

  • Creates and queries KubeSphere users, workspaces and projects and assigns built-in roles, defaulting to least privilege and never deleting anything.

    17k GitHub starsUsed in 1 repo~3.1k tokens
    DevOps & CloudAuto-check passed
  • Azure Diagnostics

    microsoft/azure-skills

    Official

    Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage.

    1.5k GitHub starsUsed in 1 repo~1.6k tokens
    DevOps & CloudAuto-check passed
  • Kubeshark Installer

    kubeshark/kubeshark

    Installs and configures Kubeshark on a Kubernetes cluster, choosing between the quick CLI path and a Helm install with custom values.

    12k GitHub stars~3.6k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Sim Helm

    simstudioai/sim

    Install, upgrade, and operate the Sim Helm chart on Kubernetes.

    30k GitHub stars~2.2k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Helm Chart Scaffolding

    Cybereason-Public/owLSM

    Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications.

    280 GitHub starsUsed in 13 repos~381 tokens
    DevOps & CloudAuto-check passed
  • Syntax reference for KFL2, the CEL-based display filter language used to search Kubernetes network traffic captured by Kubeshark, loaded before any filter is written.

    12k GitHub stars~3.6k tokensUpdated today
    DevOps & CloudAuto-check passed

More from pando85/kaniop

  • Helm Chart

    pando85/kaniop

    Guidelines for modifying the Helm chart. An agent skill from pando85/kaniop.

    130 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Kaniop Development

    pando85/kaniop

    Kaniop architecture, Rust controller conventions, commands, testing, and repository workflows.

    130 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Release

    pando85/kaniop

    Prepare and publish a new release. An agent skill from pando85/kaniop.

    130 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Grafana Dashboard

    pando85/kaniop

    Improve and validate the Kaniop Grafana dashboard against repository metrics and the grigri live cluster.

    130 GitHub stars~987 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Document Learnings

What does Document Learnings do?

Guidelines for documenting reusable patterns discovered during work. Document Learnings is an agent skill from pando85/kaniop. Guidelines for documenting reusable patterns discovered during work.

When should I use Document Learnings?

Document Learnings fits situations like: completing tasks that reveal non-obvious workflows; project conventions.

How do I install Document Learnings in Claude Code?

Run `npx skills add pando85/kaniop --skill document-learnings -a claude-code`. Or copy the skill folder (.opencode/skills/document-learnings in pando85/kaniop) into .claude/skills/document-learnings in your project. Claude Code loads it when a task matches its description.

How do I install Document Learnings in Codex?

Run `npx skills add pando85/kaniop --skill document-learnings -a codex`. Or copy the skill folder (.opencode/skills/document-learnings in pando85/kaniop) into .agents/skills/document-learnings in your project. Codex loads it when a task matches its description.

Can I use Document Learnings in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pando85/kaniop --skill document-learnings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/document-learnings, .gemini/skills/document-learnings, .github/skills/document-learnings and .opencode/skills/document-learnings in your project.

What does Document Learnings need to run?

SKILL.md names no scripts, command-line tools or credentials: Document Learnings is instructions for the agent only.

Does Document Learnings access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Document Learnings safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Document Learnings use?

Document Learnings is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Document Learnings use?

About 501 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Document Learnings?

Skills that share tags, products or a category with Document Learnings: KubeSphere Multi-Tenant Management (kubesphere/kubesphere, 17k stars), Azure Diagnostics (microsoft/azure-skills, 1.5k stars), Kubeshark Installer (kubeshark/kubeshark, 12k stars) and Sim Helm (simstudioai/sim, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Document Learnings?

pando85 (a GitHub user) maintains it in pando85/kaniop, which has 130 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

Source: pando85/kaniop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.