跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

challenge

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

AI 与智能体565plugins/elixir-phoenix/skills/challenge/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/oliver-kriska/claude-elixir-phoenix/challenge/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Challenge Mode Reviews

Rigorous, critical review patterns inspired by Boris Cherny's "Grill me" approach. Push beyond first solutions to ensure quality.

Iron Laws - Never Violate These

  1. No approval without verification - Don't approve until all concerns addressed
  2. Assume bugs exist - Look for edge cases, race conditions, missing handlers
  3. Question everything - Even "obvious" code can hide issues
  4. Demand proof - Ask for tests, show state transitions, verify behavior

Adversarial Lenses (Apply to ALL Modes)

  1. "What Would Break This?" — Production failure modes under load, during deploys, with unexpected data
  2. "Assumption Stress Test" — List every assumption; which are most fragile?
  3. "Contradictions Finder" — Find contradictions between tests/implementation, docs/behavior, or within the changeset

Challenge Modes

Ecto Challenge (/phx:challenge ecto)

Grill the developer on database changes:

Migration Safety

  • Will this migration lock the table in production?
  • What happens to existing records without the new field?
  • Is the migration reversible?
  • Are there any unsafe operations (column removal, type change)?

Query Performance

  • Have you introduced any N+1 queries?
  • Are there missing indexes for new WHERE clauses?
  • Will this query scale with data growth?

Schema Integrity

  • Are all constraints enforced at database level?
  • What happens during rolling deployment (old code, new schema)?
  • Are foreign key cascades correct?

Backward Compatibility

  • Will old code work during deployment?
  • Are there any breaking changes to the context API?

LiveView Challenge (/phx:challenge liveview)

Prove the LiveView handles all cases:

Event Coverage

  • List every handle_event clause and expected socket state
  • What happens if socket assigns are missing when event fires?
  • Are there race conditions between user events and server pushes?

PubSub Handling

  • List every handle_info clause and when it's triggered
  • Do all PubSub subscriptions have corresponding handlers?
  • What happens if a message arrives before mount completes?

State Transitions

  • Show the event → handler → state transition table
  • Are all error states handled gracefully?
  • What's the recovery path from each error state?

Memory & Performance

  • Are large lists using streams?
  • Is transient data using temporary_assigns?
  • What's the memory footprint per connected user?

PR Challenge (/phx:challenge pr)

Senior engineer review checklist:

Must Pass

  • No direct Repo calls in controllers/LiveViews
  • All Ecto queries use explicit preloads
  • Changesets validate all user input
  • No atoms created from params
  • Error cases handled (not just happy path)
  • Tests cover new functionality

Performance

  • No queries in Enum.map loops
  • LiveView streams for lists > 100 items
  • Indexes exist for WHERE clause columns

OTP

  • GenServers have supervision
  • Timeouts set for GenServer.call
  • No unbounded process spawning

Security

  • No SQL injection via raw queries
  • No path traversal in file handling
  • Authorization checks present

Prior Findings Deduplication (MANDATORY)

Run this before analysis so consecutive runs don't re-report identical issues.

  1. Search .claude/plans/*/reviews/ and .claude/reviews/ for prior findings
  2. Read ALL prior findings before analyzing code
  3. Check each finding against priors:
    • Fixed → SKIP | Still present → PERSISTENT (one line) | New → NEW (full analysis) | Reintroduced → REGRESSION
  4. Present: NEW first (full), then PERSISTENT (one-line), then REGRESSION

Example Challenge Output

## Challenge: Ecto — Orders Migration

### FINDING 1: Table lock risk (HIGH)
AddColumn on `orders` (2.1M rows) will lock table during deploy.
**Proof needed**: Run `SELECT count(*) FROM orders` — if >1M, use
`ALTER TABLE ... ADD COLUMN ... DEFAULT NULL` (no lock).

### FINDING 2: Missing index (MEDIUM)
New `WHERE status = ?` query on line 45 has no index.
**Action**: Add `create index(:orders, [:status])` to migration.

### Status: BLOCKED — 2 unresolved findings

Usage

Run /phx:challenge [mode] to initiate a rigorous review. The reviewer will not approve until all concerns are addressed with evidence.

Example workflow:

  1. Run /phx:challenge ecto after migration changes
  2. Answer each question with code references or test results
  3. Address all concerns before proceeding to PR

相似的 Skill

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI 与智能体

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI 与智能体

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI 与智能体

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 与智能体

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI 与智能体

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI 与智能体