ever-works/orgs/employee-faq
Claude Code and agent skill by ever-works/orgs
- community
Checking that the SKILL.md file is still in the repository.
Use when building or maintaining the self-serve answers employees reach for — turns the questions people actually ask into clear, sourced FAQ entries that deflect repeat questions and stay consistent with policy.
Install
npx vskill@latest install ever-works/orgs/employee-faqSKILL.md
Employee FAQ
A playbook for building a self-serve FAQ that gives fifty people the same correct answer without fifty interruptions. The failure mode it prevents: an FAQ that's either empty (so everything becomes a ticket) or wrong (so it confidently misinforms at scale).
Source the questions from reality
- Start from what people actually ask: recurring partnering questions, onboarding confusions, and — most valuable — the searches that returned nothing. The FAQ should answer the population's real questions, not the ones you imagine.
- Rank candidates by frequency and by how much pain a wrong or missing answer causes. Write the high-volume, high-friction ones first.
Write each entry
- Lead with the question phrased the way employees phrase it, not the policy's formal title — people search in their own words.
- Answer plainly and completely enough to act on: the direct answer first, then the one or two conditions that change it.
- Source every answer to current policy. An FAQ that drifts from policy is worse than no FAQ, because people trust it. Where the answer depends on a policy ruling, get it from the Policy Lead before publishing.
- Link the next step: the form, the person, or the process, so the entry ends the task instead of starting a new question.
Keep it honest
- Draw a clear line where self-serve stops. For anything needing judgment or discretion — a sensitive situation, an exception — route the reader to the People Partner rather than pretending an article can decide it.
- Review on a cycle and whenever a policy changes: an outdated entry is a confident wrong answer at scale. Retire or fix stale entries fast.
Close the loop
- Watch which entries deflect questions and which don't. Rewrite the ones people still ask about after reading, and add entries for the searches still coming up empty.
Quality bar
- Every entry is sourced to a current policy and links a next step.
- Entries are written in the employee's words and answerable without a follow-up.
- The line between self-serve and "talk to the Partner" is explicit.
- Stale entries are caught on a cycle, not by the employee they mislead.
Output format
FAQ entry: question (in the employee's words) → direct answer, then the conditions → source policy reference → next step/link → self-serve-vs-escalate boundary. Plus a maintenance log: what's deflecting, what's failing, what's stale.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcompanies/cornerstone-people/skills/employee-faq/SKILL.md
Popularity
- Repository stars
- 2
- 7-day trend score
- 10
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ever-works/orgs/employee-faq)