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

**Legend:** `▲` top/answer · `●` first-level group · `○` support · `⚠` violation · `↑` conclusion buried · `⇄` wrong order type · `⊗` overlap · `⊕` gap · `✂` cut or move to appendix

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-d39fe547/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-d39fe547)

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

Download with Pro
Files
01-big-chief__codex__control.md
**Legend:** `▲` top/answer · `●` first-level group · `○` support · `⚠` violation · `↑` conclusion buried · `⇄` wrong order type · `⊗` overlap · `⊕` gap · `✂` cut or move to appendix

## Annotated opening

```text
⚠ ✂ "This memorandum describes how project teams identify and deliver
   significant profit improvements." — statement of purpose, not an answer.
   Names the topic; the reader learns nothing they can act on.
⊕ No Situation, no Complication, no Question anywhere: the reader is never
   told what changed or what choice is open, so no question is live.
⚠ "It is organized in six sections:" — a table of contents standing in for
   a key line.

●⚠ Background                                  ✂ label, not a claim; and a
                                                  "Background" heading sits at
                                                  a different level of
                                                  abstraction than the rest
●⚠ Principles of the project-team approach      ⊗ overlaps "Definition" and
                                                  "Organization"
●⚠ Definition of project work                   ⊗ overlaps "Principles"
●⚠ Organization of the program                  ⊗ overlaps "Principles"
●⚠ Distinctive benefits and results             — the only element of the kind
                                                  the reader's question demands
●⚠ Conditions required for success              ⇄ requirements, a fourth kind
⇄ Six elements, no stateable ordering principle: not time, not structure,
   not ranking.
⊕ Every heading is a topic word, so nothing below is summarized by
   anything above — no parent on this list makes a claim its section
   could ground.
```

## Findings

| Location | Violation | Fix |
|---|---|---|
| First sentence | No answer anywhere in the visible opening — and none is promised. The reader deciding whether to adopt project teams needs the payoff stated: what they will gain and what it costs them. | Replace the purpose statement with the one-sentence answer the body supports |
| Whole opening | No SCQ: no Situation the reader accepts, no Complication forcing a choice, no Question the memo closes | Open with the situation and the turn, in prose, so the reader arrives at the question already asking it |
| Six headings | Mixed kinds in one group: concepts (Principles, Definition), a method (Organization), payoffs (Benefits and results), requirements (Conditions), plus a non-element (Background) | Re-derive the kind from the reader's question, then refill the group |
| Principles / Definition / Organization | Overlap — all three describe the same mechanics of how project teams work | Merge into one branch; the three become supports under it |
| Six headings | At most four first-level groups; six signals the split is by recall, not by structure | Regroup; the merge above already brings the count down |
| "Background" | Not a first-level element at all — a level-of-abstraction break | Delete the heading; its content becomes the Situation in the intro |
| Six headings | No explicable order | Choose and apply one order type |

## Score

| Axis | Score |
|---|---|
| Top | 0 — purpose statement, no answer |
| Same-kind groups | 0 — four kinds plus a non-element |
| Order | 0 — no stateable principle |
| MECE | 0 — three overlapping branches, no named field to check coverage against |
| Display | 1 — the six-part skeleton is visible, but the hierarchy is one flat list of topics |

**1 / 10 — not structured yet.**

## The three fixes that buy the most

1. State the answer in the first line: what project teams are worth to this reader, in one sentence.
2. Collapse Principles, Definition and Organization into a single mechanics branch, then find the second real payoff branch among them.
3. Turn "Background" into two or three sentences of Situation and Complication that make the question live, and put the question on the page.

Say the word and I'll run `write` on this — though the body isn't available, so it would be a skeleton, not a draft.

Attribution

welltraumwelltraum
View sourceMore from welltraum →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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".

1066601 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', ...

686011 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.

651 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 →