Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Raw

ASecurity

**Text with markers**

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agents

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add welltraum/minto --skill raw --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Raw?

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

Security grade badge for Raw
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/welltraum-raw-cd31935f/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-cd31935f)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
01-big-chief__codex__control.md
## Audit

**Text with markers**

```
▲ This memorandum describes how project teams identify and deliver significant
profit improvements. [⚠ topic label, not an answer]

It is organized in six sections:

    ○ Background                                    [⚠ not same-kind as siblings]
    ○ Principles of the project-team approach        [⚠ mixed kind]
    ○ Definition of project work                     [⚠ mixed kind]
    ○ Organization of the program                     [⚠ mixed kind]
    ○ Distinctive benefits and results                [⚠ mixed kind]
    ○ Conditions required for success                 [⚠ mixed kind]
[⇄ no stated ordering principle] [⊕ no visible question the six answer]
```

**Findings**

| Location | Violation | Fix |
|---|---|---|
| Opening sentence | States the topic ("describes how...") rather than an answer; no reader question is posed or answered | Replace with the actual answer — what the memo concludes about identifying/delivering profit improvements |
| Six-item list | Not same-kind: mixes a stage ("Background"), a concept ("Principles..."), a definition ("Definition of..."), a structure ("Organization..."), a payoff ("Distinctive benefits...") and a precondition ("Conditions...") — six different grammatical and logical kinds under one plural noun that doesn't exist | Reclassify into 3–4 same-kind groups (e.g., what it is / how it works / why it pays off / what it requires), dropping "Background" as intro material, not a section |
| Six-item list | No order type is named or evident — not time, not structure, not ranking | Choose one order (e.g., structure: definition → mechanics → organization; or induction: evidence → benefit → conditions) and sequence accordingly |
| "Background" as section 1 | This is Situation/Complication material, not a first-level branch — a buried intro | Move out of the list into a short SCQ-style opening; it isn't a "kind" of content the reader is choosing among |
| Whole opening | No Situation → Complication → Question visible before the six-way split; reader doesn't know what question these six sections jointly close | Supply one line of Situation + Complication, and a stated or implied question, before the list |

**Score:** Top 0 · Same-kind groups 0 · Order 0 · MECE 1 (no obvious duplication, but "Background" doesn't belong; coverage of the six sections themselves can't be judged without the body) · Display 1 (list is visible, but not a hierarchy)

**Total: 2/10 — not structured yet**

**Three fixes with the most leverage**

1. State the actual answer as the opening line, not a description of the memo's contents.
2. Recast "Background" out of the list and reclassify the remaining five into 3–4 same-kind groups.
3. Name and apply one order type to whatever groups remain.

Attribution

welltraumwelltraum
View sourceMore from welltraum →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →