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 · ⚠ violation · ↑ buried conclusion · ⇄ wrong order · ⊕ gap · ✂ cut **Annotated text:** > This memorandum describes how project teams identify and deliver significant profit improvements. [⚠ topic label, not an answer — states what the document is about, not what it concludes] It is organized in six sections: [✂ table-of-contents framing substitutes for a key line] > > Background [⊕ not a claim — a label; unclear what it summarizes] > Principles of the project...

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-849e3dde/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-849e3dde)

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

Download with Pro
Files
01-big-chief__codex__control.md
**Legend:** ▲ top/answer · ⚠ violation · ↑ buried conclusion · ⇄ wrong order · ⊕ gap · ✂ cut

**Annotated text:**

> This memorandum describes how project teams identify and deliver significant profit improvements. [⚠ topic label, not an answer — states what the document is about, not what it concludes] It is organized in six sections: [✂ table-of-contents framing substitutes for a key line]
>
>     Background [⊕ not a claim — a label; unclear what it summarizes]
>     Principles of the project-team approach [⊠ kind unclear: mechanics or reasons?]
>     Definition of project work [⚠ mixed kind — this is "what it is", sitting beside "how it works" and "why it succeeds"]
>     Organization of the program [⚠ mechanics — same-kind as "principles", not separated]
>     Distinctive benefits and results [↑ this is the one section that could carry the answer — payoff belongs at the top, not buried as item 5 of 6]
>     Conditions required for success [⚠ different kind again — risk/prerequisite, not benefit or mechanism]

**Findings**

| Location | Violation | Fix |
|---|---|---|
| Opening sentence | Top is a topic label ("describes how..."), not an answer to a reader question | State the reader's question ("does this approach work, should we adopt it?") and answer it in one sentence |
| Six-item list overall | Six first-level groups — exceeds the 3–4 working-memory limit | Consolidate around 3–4 same-kind groups |
| Items 2, 3, 4 ("Principles", "Definition", "Organization") | Mixed kinds — one describes what the work is, two describe mechanics/structure, none states a reader payoff | Re-derive from the reader's question: if it's "why adopt this?", recast as reasons/benefits; if "how does it work?", recast as steps |
| Item 5 ("Distinctive benefits and results") | Buried conclusion — the one benefit-bearing heading sits mid-list instead of driving the top | Promote to the top-level answer; everything else becomes support for it |
| Item 6 ("Conditions required for success") | Different kind (prerequisites/risks) mixed in with structural and benefit headings | Separate into its own class, or fold under whichever top-level group it actually supports |
| No stated reader question anywhere | Cannot verify vertical or horizontal logic without knowing what question the memo closes | Supply the question explicitly before further structuring |
| "Background" | Gap-marker heading, not a claim — impossible to tell what it summarizes or whether it belongs at this level at all | Either state what it concludes, or fold it into the Situation/Complication of an SCQ intro rather than a first-level section |

**Score**

| Axis | Score | Note |
|---|---|---|
| Top | 0 | No answer, only a topic description |
| Same-kind groups | 0 | Six labels of at least three different kinds (structure, mechanism, definition, benefit, precondition) |
| Order | 0 | No stated or inferable ordering principle — reads as recall order |
| MECE | 1 | Some doubtful overlap (e.g., "Principles" vs. "Organization"); cannot fully assess without the body |
| Display | 1 | Headings are visible as a list, but the list is not a hierarchy — it's flat and unranked |

**Total: 2/10 — not structured yet**

**Three fixes that buy the most:**
1. Name the reader's question, then write the answer as a single sentence — replace the descriptive opening.
2. Promote "distinctive benefits and results" (or whatever it turns out to support) from item 5 to the top.
3. Collapse six headings into 3–4 same-kind groups once the kind the question demands is established.

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 →