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 · `↑` buried conclusion · `⇄` 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-868e69de/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-868e69de)

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

Download with Pro
Files
01-big-chief__codex__control.md
## Audit — Fixture 07: headings audit

**Legend:** `▲` top/answer · `●` first-level group · `○` support · `⚠` violation · `↑` buried conclusion · `⇄` 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 — names the topic, answers nothing]
⊕ [no Situation the reader already accepts; no Complication; no Question; no Answer]
⚠ It is organized in six sections:  [table of contents standing in for a key line]

  ● Background                                    ⚠ ✂ label heading, not an idea
  ● Principles of the project-team approach       ⚠ kind: principles
  ● Definition of project work                    ⚠ kind: definition  ⊗ overlaps "Principles"
  ● Organization of the program                   ⚠ kind: mechanics ("how the system works")
  ● Distinctive benefits and results              ⚠ kind: reasons/payoff  ↑ the only branch that answers a decider
  ● Conditions required for success               ⚠ kind: conditions/caveats
  ⇄ [six headings in no statable order — not time, structure, ranking, deduction or induction]
```

### Findings

| Location | Violation | Fix |
|---|---|---|
| First sentence | No top: purpose statement instead of an answer. The document says what it *describes*, so the reader cannot be contradicted by it | State in one sentence what the reader should conclude or do about project teams |
| Whole opening | No reader's question on the page, and no reader named — six headings answer six different questions | Write one literal question the memo closes, and name who is deciding |
| Whole opening | No SCQ: nothing the reader already accepts, nothing that changed, no turn | Open with the situation and the complication that make project teams a live choice |
| Setout, all six lines | Mixed kinds — principles, a definition, mechanics, benefits, conditions cannot sit under one plural noun | Pick the kind the question demands (payoffs if the reader is deciding; actions if the reader has already decided) and refill the level |
| Setout order | No explicable ordering principle | Choose and show one order type |
| "Definition of project work" vs "Principles of the project-team approach" | `⊗` overlap: define-the-approach content fits both | Merge; keep the definition as a support |
| "Background" | Label heading at a different level of abstraction from the rest; it is intro material promoted to a branch | Fold into the running SCQ intro, not the key line |

Two further findings not tabled: "Distinctive benefits and results" is the one branch of a decider's kind and sits fifth of six (`↑`); six first-level groups exceed the 3–4 the reader can hold.

### Score — 2/10 (not structured yet)

| Axis | Score | Basis |
|---|---|---|
| Top | 0 | Purpose statement; no answer anywhere visible |
| Same-kind groups | 0 | Five distinct kinds across six headings |
| Order | 0 | No order type statable |
| MECE | 1 | One clear overlap; coverage unjudgeable without the body |
| Display | 1 | A setout exists and is scannable, but it mirrors a contents list, not a hierarchy |

Scope note: only the opening was assessed. The body is unavailable, so vertical logic (does each parent summarize its children) is untested, and gaps `⊕` below the first level are not claimed.

### Three fixes that buy the most

1. Replace the purpose statement with the answer — the one sentence about project teams the reader could argue with.
2. Write the reader's question, then discard any heading that answers a different one.
3. Collapse the six headings to 3–4 of a single kind, demoting Background, Definition and Organization to supports.

Say the word and I'll take this to `write`.

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 →