problem-validation

A research checkpoint that challenges whether a proposed problem is worth pursuing before designing a method.

In plain words
What is it for?
It helps classify the project, test its originality, choose a realistic publication venue, and decide whether the work should proceed.
Why use it?
It exposes unclear goals, weak novelty, unsuitable publication targets, or projects that are not feasible before time and resources are spent.

Skill for Claude CodeCodex

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/evoclaw/amplify/problem-validation
Any agent
npx skills add EvoClaw/amplify --skill problem-validation
Clone the repo
git clone --depth 1 https://github.com/EvoClaw/amplify

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,408 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 $0.00058 $0.06408
Opus 5 $0.00029 $0.03204
Sonnet 5 $0.00012 $0.01282
Haiku 4.5 $0.00006 $0.00641

Measured 2d ago against content hash 66044467e0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

problem-validation 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 2d 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.

skills/problem-validation/SKILL.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

"It's just data analysis, no need for validation" is the #1 reason Type D projects fail. DO NOT SKIP THIS PHASE.

Problem Validation (Phase 2)

Overview

A direction that survived Phase 1 is a candidate, not a commitment. This skill stress-tests the research problem through adversarial questioning before resources are invested. Passing this skill is required to enter method design.

Activation Flow

digraph problem_validation {
    "G1 Passed" [shape=doublecircle];
    "Pre-Step:\nKnown answer?\nUser-specified?" [shape=diamond, style=filled, fillcolor="#f0f0f0"];
    "Tell user &\noffer alternatives" [shape=box];
    "Novelty\nLitmus Test" [shape=box, style=filled, fillcolor="#ffe0e0"];
    "Multi-Agent\nDeliberation\n(up to 5 rounds)" [shape=box, style=filled, fillcolor="#ffe0e0"];
    "Converged?" [shape=diamond];
    "Escalation:\nUser decides" [shape=box, style=filled, fillcolor="#ff9999"];
    "Project Intent\nClassification" [shape=box, style=filled, fillcolor="#e0e0ff"];
    "Venue Target\nPrecision" [shape=box, style=filled, fillcolor="#e0ffe0"];
    "Feasibility\nAssessment" [shape=box, style=filled, fillcolor="#fff0d0"];
    "All passed?" [shape=diamond];
    "Phase 3:\nMethod Design" [shape=doublecircle];
    "Return to\nPhase 1" [shape=doublecircle, style=filled, fillcolor="#ffcccc"];

    "G1 Passed" -> "Pre-Step:\nKnown answer?\nUser-specified?";
    "Pre-Step:\nKnown answer?\nUser-specified?" -> "Tell user &\noffer alternatives" [label="known answer"];
    "Pre-Step:\nKnown answer?\nUser-specified?" -> "Novelty\nLitmus Test" [label="proceed"];
    "Tell user &\noffer alternatives" -> "Novelty\nLitmus Test" [label="user chooses\nnew question"];
    "Novelty\nLitmus Test" -> "Multi-Agent\nDeliberation\n(up to 5 rounds)";
    "Multi-Agent\nDeliberation\n(up to 5 rounds)" -> "Converged?";
    "Converged?" -> "Project Intent\nClassification" [label="all PASS"];
    "Converged?" -> "Escalation:\nUser decides" [label="persistent FAIL\nor 5 rounds"];
    "Escalation:\nUser decides" -> "Return to\nPhase 1" [label="return to\nexploration"];
    "Escalation:\nUser decides" -> "Multi-Agent\nDeliberation\n(up to 5 rounds)" [label="try new\nformulation"];
    "Escalation:\nUser decides" -> "Project Intent\nClassification" [label="proceed\nas-is"];
    "Project Intent\nClassification" -> "Venue Target\nPrecision";
    "Venue Target\nPrecision" -> "Feasibility\nAssessment";
    "Feasibility\nAssessment" -> "All passed?";
    "All passed?" -> "Phase 3:\nMethod Design" [label="all ✅"];
    "All passed?" -> "Escalation:\nUser decides" [label="any ✗"];
}

Read the full file on GitHub · 591 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. 2d ago First seen · 591 lines · 58 tokens per session scan A 66044467e0a3

Subscribe to this mod's changes

problem-validation is a skill published in the GitHub repository EvoClaw/amplify (11 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 6,408 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

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

make_plan

For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.

agentscope-ai/QwenPaw · 51 tokens

pdf

当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。.

agentscope-ai/QwenPaw · 95 tokens

gpt-image-2

面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用:(A) Garden 本地模式,通过 OpenAI 兼容接口直接出图并落盘;(B) Host-Native 模式,把本 Skill 当作提示词工程指引,把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图;(C) Advisor 模式,宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板,覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.

ConardLi/garden-skills · 177 tokens

new

Create a new project to start development quickly.

clacky-ai/openclacky · 10 tokens

oss-upload

Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.

clacky-ai/openclacky · 40 tokens