agentleFS
c-monganc-mongan/support-triage-agent-template/skills/kb-article/SKILL.md

kb-article

Skill0 starsChanged 36 days agoMITView on GitHub

Turn a resolved or well-understood triage report into a draft knowledge-base article (how-to, troubleshooting, known issue or FAQ). Use after triage when the same question is likely to come up again.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No customer-specific details are needed to understand it.

    line 14
  2. Distinctive:

    Do not write one for Suspected root causes, single-customer misconfigurations, or anything involving security details that are not yet …

    line 16

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

KB Article

Support teams answer the same question many times. When a triage report shows a documented limit, a workaround or a known issue, draft an article so the next customer can self-serve. The draft is for a human to review and publish; this skill never publishes anything.

When to write one

  • The root cause is Confirmed by data, or Likely with a working workaround.
  • The answer is not already covered by an existing docs page (if it is, suggest a docs link or a docs fix instead).
  • No customer-specific details are needed to understand it.

Do not write one for Suspected root causes, single-customer misconfigurations, or anything involving security details that are not yet public.

Pick a type

TypeUse whenLead with
How-toThe customer wanted to do something supportedThe goal, then numbered steps
TroubleshootingA symptom has a few known causesThe symptom in the customer's words, then causes in order of likelihood
Known issueA bug is acknowledged and trackedAffected versions, workaround, fixed-in version (only if released)
FAQ / limitBehavior is by designThe limit stated plainly, then the alternatives

Shape

# <Symptom or task, in the words a customer would search for>

**Applies to:** <product area, versions, plans>
**Last reviewed:** <YYYY-MM-DD>

## Summary
<Two sentences: what happens and what to do.>

## Cause
<Plain English. No internal ticket IDs, tool names or private links.>

## Resolution
1. <step>
2. <step>

## Workaround (if no fix yet)
<steps>

## Related
- <public docs links only>

Rules

  • Same guardrails as customer replies: no internal links, no raw queries, no customer data, no promised dates, no unverified feature claims.
  • Title it with the words a customer would search, for example "CSV export stops at 10,000 rows", not "BEACON-097".
  • Save drafts under reports/ as YYYYMMDD-HHmmss-<ticket-id>-kb-draft.md. Never write to a docs repo or help center.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.