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

Scope note: only the opening is available. Findings below concern what is on the page; where a judgment would require the body, it is marked as unverifiable rather than assumed.

2 stars
0 votes
0 copies
0 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-bbcf5be6/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-bbcf5be6)

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

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

Scope note: only the opening is available. Findings below concern what is on the page; where a judgment would require the body, it is marked as unverifiable rather than assumed.

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

### Annotated opening

> ⚠ This memorandum describes how project teams identify and deliver significant
> profit improvements. 〔statement of purpose — names the topic, answers nothing; ⊕ no reader question, ▲ no answer〕
>
> ⚠ It is organized in six sections: 〔more than 3–4 groups; a list of headings is not a key line〕
>
> - ⚠ Background 〔run-up by definition — no Complication it can serve, ✂ candidate〕
> - ⚠ Principles of the project-team approach 〔topic label, kind: mechanics〕
> - ⚠ Definition of project work 〔topic label, kind: parts-of-a-whole; likely support, not a first-level group, ✂ demote〕
> - ⚠ Organization of the program 〔topic label, kind: mechanics; ⊗ probable overlap with "Principles"〕
> - ●↑ Distinctive benefits and results 〔the only heading shaped like a payoff — the reader's reason to care, buried fifth〕
> - ⚠ Conditions required for success 〔kind: requirements/risks — third kind in one group〕

### Findings

| # | Location | Violation | Fix |
|---|---|---|---|
| 1 | Opening sentence | No answer anywhere in the opening (statement of purpose, not SCQ); the reader's question — most plausibly "should we adopt the project-team approach / what will it get us" — is never raised, let alone answered | Replace the purpose statement with an SCQ intro in story form and a one-sentence answer |
| 2 | Section list | Six first-level groups against the 3–4 ceiling | Collapse to 3–4 groups of one kind |
| 3 | Section list | Mixed kinds: mechanics ("Principles", "Organization"), parts ("Definition"), payoff ("Benefits"), requirements ("Conditions") — no single plural noun covers them | Re-derive the kind from the reader's question; for "why should we do this", the first level is reasons/payoffs, with mechanics demoted underneath as supports |
| 4 | Section list | Order unexplainable — neither time, structure, ranking, nor deduction can be named for this sequence | Assign and name one order (ranking by size of benefit fits a reasons pyramid) |
| 5 | "Distinctive benefits and results" | Buried logic: the one element that answers "what do we get" sits fifth of six | Promote the payoff logic to the top/first level |
| 6 | "Background" / "Definition" | Run-up and definition presented as first-level peers of the argument; "Background" has no visible Complication to serve | Cut or fold into the SCQ intro; move "Definition" under the group it supports or to an appendix |
| 7 | "Principles" vs "Organization" | Probable overlap (⊗) — cannot be confirmed without the body; full MECE and vertical checks unverifiable from headings alone | Verify against the body; merge if their contents coincide |

### Score — 2 / 10 — not structured yet

| Axis | Score | Basis |
|---|---|---|
| Top | 0 | Topic label; no answer on the page |
| Same-kind groups | 0 | At least three kinds in one group |
| Order | 0 | No explicable ordering principle |
| MECE | 1 | Probable overlap visible; completeness unverifiable without the body |
| Display | 1 | Sections are listed, but headings are topic words — the skeleton carries no argument |

### Three fixes that buy the most

1. Open with the answer to the reader's real question (what adopting the approach is worth), framed by a short SCQ intro — delete the statement of purpose.
2. Promote "benefits and results" into the key line: make the first-level groups the payoffs, ordered by ranking, and hang principles/organization/definition under them as supports.
3. Cut "Background" and "Definition" from the first level — fold the minimum necessary context into the intro, the rest into an appendix.

I can rewrite the opening in `write` mode once the body (or at least its key facts) is available — the material for a proper answer-first top is not in this excerpt.

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 →