Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Qwen38 Think

ASecurity

The thinking a small model skips, as steps it must write down: before the first edit, an assumptions table and a three-flaw check on the brief (contradiction, missing fact, impossible ask), each flaw checked by a command; when stuck, one observation, one hypothesis, one falsifying command; and a THINK report line. Pushback is a written line in the report, never a question that stops the work. Slice 2 of xeno-skills #355.

2 stars
0 votes
0 copies
0 views
Added 10/5/2026
toolsnodeaws

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add xenodeve/xeno-skills --skill qwen38-think --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Qwen38 Think?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Qwen38 Think
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/xenodeve-qwen38-think/badge)](https://www.skillsdirectory.com/skills/xenodeve-qwen38-think)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: qwen38-think
description: "The thinking a small model skips, as steps it must write down: before the first edit, an assumptions table and a three-flaw check on the brief (contradiction, missing fact, impossible ask), each flaw checked by a command; when stuck, one observation, one hypothesis, one falsifying command; and a THINK report line. Pushback is a written line in the report, never a question that stops the work. Slice 2 of xeno-skills #355."
target-model: Qwen3.8-27B
triggers:
  - /qwen38-think
  - think first
  - ตรวจโจทย์ก่อนทำ
  - โจทย์นี้มีอะไรผิดไหม
---

# Think first (`qwen38-think`)

**Before the first edit, write the two tables below into your answer. Then build. End with the THINK line.** Doing the work first and the tables after is a fail of this skill.

## 1. Assumptions table

Everything the brief leaves open that changes what you would build. Take the assumption; do not ask.

| open in the brief | the assumption you take | why this one |
|---|---|---|
| e.g. "ordering when quantities tie" | by sku, ascending | the brief orders by quantity; a stable secondary key is the usual reading |

Zero rows is allowed only if you write "none — the brief fixes every choice" and can point to where.

## 2. Three-flaw check — each one checked, not guessed

| flaw type | what you looked for | the command you ran | found? |
|---|---|---|---|
| **contradiction** — two sentences of the brief cannot both hold | e.g. "return None" and "return the remaining quantity" | `grep -n "return" <file>` / re-read the brief | yes / no |
| **missing fact** — a file, function, endpoint or value the brief names does not exist | e.g. `inventory/report.py` | `ls <path>` · `grep -rn "<name>" .` | yes / no |
| **impossible ask** — the brief forbids the only way to do what it asks | e.g. "make X O(1) without changing Y" | read the code path; name the line that makes it impossible | yes / no |

**When a flaw is found:** do not stop, do not ask, do not invent the missing thing. Write one line under the table — *"Pushback: the brief says A and B; I build A because …"* / *"Pushback: `inventory/report.py` does not exist; I did not create it; the nearest file is …"* / *"Pushback: not possible as stated because …; I did the possible part: …"* — and build the part that stands. The developer reads the report; a question asked **instead of** the work only stops it. In an interactive session you may ask once the report is delivered; in an unattended run there is nobody to answer, so the report is the whole channel.

## 2b. Thinking is for decisions, not for code

Decide in thinking — the structure, the file order, the risks — then build with tools. For work that spans files, write the order in one line (`index.html → css → js/scene.js → js/main.js`), then Write the first file. A file drafted in thinking is written twice (the draft, then the `Write`) and lost if the turn is cut: one GSQ turn was a 43,564-character thinking block with the whole page and both shaders in it, hit the output limit and wrote nothing; from the next turn, one file per turn after short thinking, all four files were done in 15 minutes (#377). Check what you built by running the check (`node --check`, the tests, the gate), not by re-reading it in thinking.

## 3. When stuck (a command fails twice, or the output makes no sense)

Write three lines before the next attempt:

```
Observed: <the exact last line of the failing output>
Hypothesis: <one cause>
Falsify: <one command whose result would rule it out>
```
Run the falsifying command. If the cause is a missing tool or package: one line "`<tool>` is not installed; continuing without it" — **never install, never search for an alternative, never spawn an agent** (`using-qwen38`).

## Report

```
THINK: assumptions <k> · flaws checked 3 · found <n> · pushback: <yes: the line | no>
```
The line is the **first** line of the final report, before the task's own gate line (`CODE GATE`, `GATE`) when there is one — a gate report that starts with "Done." and no `THINK:` line dropped a correct pushback on 2026-09-05 17:38.

## What this does not touch

How to build the thing — the task's own skill and gate. This file only makes the model write down what it would otherwise silently assume, and say what is wrong with a brief instead of working around it.

Attribution

xenodevexenodeve
View sourceSee grades on GitHubMore from xenodeve →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

ucoz-landing-skill

Create and edit uCoz homepage landing pages via MCP: custom templates, hero sections, lead forms, navigation menus, SEO, and responsive layout. Includes a visual design system (style selection, layout/grid, section recipes, typography/spacing, color tokens, component states, icons, modern CSS/JS, motion, imagery, social proof, copy/voice, accessibility). Uses ucoz-mcp tools for templates, site file uploads, and site modules.

107 votes

Paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

953191 votes

Pptx

Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.

471861 votes

Daw Music

Digital Audio Workstation usage, music composition, interactive music systems, and game audio implementation for immersive soundscapes.

761 votes

Instantly Rdsthomas Mission Control

Instantly.ai cold email outreach API - manage campaigns, leads, accounts, and analytics. Use for cold email automation, lead management, campaign creation/monitoring, and email account warmup.

761 votes
View all in tools →