kb-article

A guide for turning a solved support problem or common question into a knowledge base article.

In plain words
What is it for?
Use it to draft how-to guides, troubleshooting articles, frequently asked questions, known-issue notices, and reference articles from tickets or other source material.
Why use it?
It helps document solutions so customers and support teams can find answers without resolving the same issue repeatedly.

Skill for Claude CodeCodex

Part of the customer-support plugin — 5 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/anthropics/knowledge-work-plugins/kb-article
Any agent
npx skills add anthropics/knowledge-work-plugins --skill kb-article
Clone the repo
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins

Made for: Claude Code, Codex.

Or install customer-support, the plugin that ships this one along with the rest of its 5 skills.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.02725
Opus 5 $0.00026 $0.01362
Sonnet 5 $0.00011 $0.00545
Haiku 4.5 $0.00005 $0.00272

Measured 3d ago against content hash cfc300f5ecc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kb-article scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

customer-support/skills/kb-article/SKILL.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kb-article

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Draft a publish-ready knowledge base article from a resolved support issue, common question, or documented workaround. Structures the content for searchability and self-service.

Usage

/kb-article <resolved issue, ticket reference, or topic description>

Examples:

  • /kb-article How to configure SSO with Okta — resolved this for 3 customers last month
  • /kb-article Ticket #4521 — customer couldn't export data over 10k rows
  • /kb-article Common question: how to set up webhook notifications
  • /kb-article Known issue: dashboard charts not loading on Safari 16

Workflow

1. Understand the Source Material

Parse the input to identify:

  • What was the problem? The original issue, question, or error
  • What was the solution? The resolution, workaround, or answer
  • Who does this affect? User type, plan level, or configuration
  • How common is this? One-off or recurring issue
  • What article type fits best? How-to, troubleshooting, FAQ, known issue, or reference (see article types below)

If a ticket reference is provided, look up the full context:

  • ~~support platform: Pull the ticket thread, resolution, and any internal notes
  • ~~knowledge base: Check if a similar article already exists (update vs. create new)
  • ~~project tracker: Check if there's a related bug or feature request

2. Draft the Article

Using the article structure, formatting standards, and searchability best practices below:

  • Follow the template for the chosen article type (how-to, troubleshooting, FAQ, known issue, or reference)
  • Apply the searchability best practices: customer-language title, plain-language opening sentence, exact error messages, common synonyms
  • Keep it scannable: headers, numbered steps, short paragraphs

3. Generate the Article

Present the draft with metadata:

## KB Article Draft

**Title:** [Article title]
**Type:** [How-to / Troubleshooting / FAQ / Known Issue / Reference]
**Category:** [Product area or topic]
**Tags:** [Searchable tags]
**Audience:** [All users / Admins / Developers / Specific plan]

---

[Full article content — using the appropriate template below]

---

### Publishing Notes
- **Source:** [Ticket #, customer conversation, or internal discussion]
- **Existing articles to update:** [If this overlaps with existing content]
- **Review needed from:** [SME or team if technical accuracy needs verification]
- **Suggested review date:** [When to revisit for accuracy]

Read the full file on GitHub · 352 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 352 lines · 53 tokens per session scan A cfc300f5ecc5

Subscribe to this mod's changes

kb-article is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 2,725 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens