Skip to main content
skill CX Codex

expertise-candidate-author — Claude Code skill: setup and usage

expertise-candidate-author is a Claude Code skill that drafts general guidelines from recurring human decisions. It keeps context links and edge cases visible.

MIT ★ 529 updated 2026-11-17

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ShuaiMXu/happyhands --skill expertise-candidate-author -a claude-code
Open on GitHub

What expertise-candidate-author does

This skill extracts reviewable principles from repeated project learnings. It relies on multiple human assessments, shared project context, and known counterexamples. Isolated preferences stay within project scope rather than turning into universal rules.

The output contains structured facts, deductions, proposed guidelines, and boundary conditions. If supporting records or human reviews are missing, the skill marks findings with needs-evidence. It forbids inventing arbitrary experience scores or promoting isolated observations.

What it helps with

  • turn recurring team decisions into documented principles
  • separate project-specific preferences from general guidelines
  • document exceptions and counterexamples systematically

Example prompts for the agent

  • Draft a coding guideline based on these PR comments about error handling
  • Convert repeated architectural decisions into a documented rule
  • Analyze team feedback on API schemas and outline general boundaries

How to install expertise-candidate-author

1Skills CLI (Vercel)

npx skills add ShuaiMXu/happyhands --skill expertise-candidate-author -a claude-code

2Manually: put the files in place

~/.claude/skills/expertise-candidate-author/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/expertise-candidate-author/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about expertise-candidate-author

How to install expertise-candidate-author in Claude Code?

Run npx skills add ShuaiMXu/happyhands --skill expertise-candidate-author -a claude-code. The file is stored at ~/.claude/skills/expertise-candidate-author/SKILL.md.

What does expertise-candidate-author do?

It drafts structured professional principles from repeated judgments while preserving context links and limitations.

When does the skill trigger needs-evidence?

It applies needs-evidence whenever required background inputs, counterexamples, or professional evaluations are absent.

Source text

SKILL.md · MIT
---
name: expertise-candidate-author
description: "Draft a general expertise candidate from repeated human judgments while preserving context and exceptions."
---

# Expertise Candidate Author

Turn repeated project learning into a reviewable professional principle.

## Required evidence

- multiple judgments
- shared context
- counterexamples

## Decisions

- Require repeated evidence
- State applicability and exceptions
- Keep provenance links

## Boundary

A single project preference should remain project memory.

Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule.

© ShuaiMXu · MIT · ShuaiMXu/happyhands

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set34

The whole set →
change-impact-mapper change-impact-mapper is a Claude Code skill that links code edits to affected routes, components, and user tasks. It helps agents choose what to review after a change. CX Codex +1 ★ 529repo stars error-recovery-reviewer error-recovery-reviewer is a Claude Code skill that inspects failure states, recovery flows, and data safety. It runs when evaluating critical user tasks against disruptions. CX Codex +1 ★ 529repo stars incremental-review-router incremental-review-router is a Claude Code skill that chooses review skills for the parts of a project affected by a change. It factors in relevant tasks, artifacts, and regression-related history. CX Codex +1 ★ 529repo stars token-normalizer token-normalizer is a Claude Code skill that turns repeated implementation values into reviewable semantic token proposals. It keeps existing names and flags exceptions instead of forcing merges. CX Codex +1 ★ 529repo stars skill-regression-evaluator skill-regression-evaluator is a Claude Code and Codex skill that audits skill versions against regression suites. Catches regressions before knowledge updates break established behavior. CX Codex +1 ★ 529repo stars responsive-reviewer responsive-reviewer is a Claude Code skill that checks matching desktop and mobile interface states. It focuses on whether the main task stays clear and usable across screen sizes. CX Codex +1 ★ 529repo stars regression-case-author regression-case-author is a Claude Code skill that turns reviewed product changes into portable regression test cases. It preserves concrete examples for future agent evaluations. CX Codex +1 ★ 529repo stars accessibility-reviewer accessibility-reviewer is a Claude Code skill that reviews interface accessibility using browser and source evidence. It checks semantics, keyboard behavior, contrast, and accessible states. CX Codex +1 ★ 529repo stars

Project sponsors

Companies that keep this analytics open