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

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

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

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-b904ea03/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-b904ea03)

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

Download with Pro
Files
01-big-chief__codex__control.md
## Marker legend

`▲` top / answer · `●` first-level group · `○` supporting detail · `⚠` 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, no Complication, no Question on the page]
⚠ It is organized in six sections:  [six, not three or four]

    ⚠ ✂ Background            [container word — could hold anything; not on the
                               same level of abstraction as the others]
    ● Principles of the project-team approach     [principles]
    ● Definition of project work                  [definition]
        ⊗ overlaps "Principles" and "Organization" — what the work is, what governs
          it and how it is run are not three separable claims
    ● Organization of the program                 [mechanics]
    ● Distinctive benefits and results            [reasons — the only heading of the
      ↑ kind the reader's question demands; sits fifth]
    ● Conditions required for success             [conditions / risks]
⚠ six headings, five different kinds, no ordering principle stated or visible
⊕ nothing answers "should we do this" — no recommendation, no top
```

## Findings

| Location | Violation | Fix |
|---|---|---|
| Opening sentence | No answer anywhere in the visible document — and the kind that belongs there is missing too: a reader deciding whether to commission project teams needs the reasons to do so (what they get, at what cost), not a description of how the approach works | Replace with the one-sentence answer the body supports, e.g. a recommendation with its payoff |
| Opening sentence | Statement of purpose in place of an introduction: no Situation, no Complication, no Question | Tell the story — what the reader already accepts, what changed, then the question the memo closes |
| Setout, all six | Mixed kinds in one group: principles, a definition, mechanics, benefits, conditions. No plural noun covers them | Re-derive the kind from the reader's question, then refill; make benefits the first level and demote mechanics under them |
| Setout, all six | Six first-level elements, no explicable order — not time, not structure, not ranking | Collapse to 3–4 and name the order |
| "Definition of project work" vs "Principles" / "Organization" | ⊗ Overlap: the same content can be filed under any of the three | Merge into one branch, or redraw the boundary |
| "Background" | Container heading; abstraction level does not match the key line; likely holds the Situation that belongs in the prose intro | Cut as a heading; fold its content into the introduction |
| "Distinctive benefits and results" | ↑ The reader's answer is buried in position five | Promote to the top and to the first branch |

## Score

| Axis | Score |
|---|---|
| Top | 0 — no answer, only a topic |
| Same-kind groups | 0 — five kinds in six headings |
| Order | 0 — no principle discernible |
| MECE | 0 — overlap across three headings, no answer-bearing category |
| Display | 1 — the setout is visible, but the hierarchy it shows is flat and one level deep |

**1 / 10 — not structured yet.**

## The three fixes that buy the most

1. Put the answer first: one sentence saying what the reader should do about project teams and what they get.
2. Rebuild the first level as reasons (the reader's payoff), and hang principles, definition and organization underneath as support.
3. Cut "Background" as a heading and turn the opening into a Situation → Complication → Question story, ending on the question the memo answers.

Say the word and I'll run `write` on the setout — restructuring only what is visible, with the missing body marked as gaps.

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 →