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 · ⊗ overlap · ⊕ gap · ✂ cut/appendix

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

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-c6158fd2/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-c6158fd2)

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 · ↑ buried conclusion · ⇄ wrong order · ⊗ overlap · ⊕ gap · ✂ cut/appendix

## Annotated text

```
Subject: Period Graph Books
⚠ topic label, not an answer — the reader's question ("what do we do about this") is never posed or answered here

Since Period 5, Financial Analysis has been responsible for producing four
graph-presentation books previously handled by Corporate Planning. [Situation, fine as is]
This memo describes issues that appeared after the transfer.
⚠ statement of purpose — names the topic, proves and answers nothing

Production
↑ this whole section (steps 1–4) is a process description that never resolves into
a conclusion; it sits where the Complication/Answer should be

1. Gather data from divisional forms, internal documents, and telephone calls.
2. Calculate graph points manually or on the corporate computer, including
   rolling values for revenue, cost, and percentages.
3. Transcribe the points to input sheets. Analysts update the current period,
   then Color Graphics re-enters the points into its own database and generates
   the graphs.
4. Check the data and calculations.
● [these four are same-kind — process stages, correctly time-ordered — the one clean group in the memo]

Issues
⚠ heading names a topic, not a claim

The transfer inserted another person into an already fragmented process.
[Complication, buried here instead of in the intro — ↑ promote to the top]

Divisional staff and three corporate departments participate, and the same
information may be entered into computer systems three times.
⊕ gap — "three times" and "another person" are quantitative claims about the process
but never connected to which of the four production steps they occur at

For one book, divisional data are loaded into a dedicated corporate program,
calculated, transferred to Color Graphics input sheets, entered again, and
returned for updates.
⊗ overlap — this is a second, more detailed pass over the same "Production" steps
already given above, for one book only; reader cannot tell if this is representative
of all four books or an exception

Problems include inconsistent data between periods and regions, incorrect
variable-cost calculations, unexplained changes to points that were previously
correct, and prior-period data that must be re-entered.
⚠ mixed kinds — this list mixes symptoms (inconsistent data, unexplained changes)
with a description of rework (re-entry), not one plural noun
⇄ no order given — four items sit in recall order, not ranked by severity or
grouped by production stage where each occurs

Overall assessment

Most problems arise from a cumbersome fragmented process.
↑ this is the real top-level conclusion — it belongs at the front, not two-thirds
down the memo

No one controls the data from beginning to end, responsibility is unclear, and
errors can fall between stages.
● [these three are same-kind — causes/reasons — but arrive after the "problems"
list rather than organizing it]

The production process badly needs streamlining, both for each book and for
common calculations.
↑ second real conclusion, also buried — this is the closest the memo comes to an
Answer, and it appears as an aside inside "Overall assessment" rather than as the
top line

The current team cannot manage the required changes as well as ongoing
production.
⊕ gap — asserts a resourcing constraint with no evidence and no stated
implication (more staff? outside help? phased plan?) — the reader cannot act on it

Could we discuss how best to proceed?
⚠ non-answer close — after three paragraphs of symptoms, the memo asks the
reader to supply the structure the writer should have supplied
```

## Findings

| Location | Violation | Fix |
|---|---|---|
| Subject line | Top does not answer — topic label only | State the recommendation/decision needed: e.g. "Period Graph Books: process needs redesign and outside help — request to discuss" |
| Opening paragraph | Statement of purpose instead of Situation→Complication | Replace with SCQ story: Situation (transfer since Period 5) → Complication ("since then, errors and inconsistencies have appeared") → Question ("how do we fix this") |
| "Most problems arise from a cumbersome fragmented process" | Buried conclusion — the real top sits two-thirds down under "Overall assessment" | Promote to the first line, as the Answer |
| "Problems include..." list | Mixed kinds, no order — symptoms and rework tangled with no explicit ordering principle | Split into one same-kind group (symptoms) and order by severity or by production stage |
| One-book detail paragraph | Overlaps "Production" steps 1–4; unclear if representative of all four books | Either fold into the Production section as its illustrating case, or state explicitly it's an exception |
| "The current team cannot manage..." | Gap — asserted with no evidence and no actionable implication | Either support it (workload data) or cut it and state the resourcing need as an explicit ask |
| Closing question | Non-answer close — pushes structuring work onto the reader | Replace with a concrete next step tied to the (now-stated) top: what decision/resource is being requested, by when |

## Score

| Axis | Score | Note |
|---|---|---|
| Top | 0 | No answer anywhere; the two candidate conclusions are both buried mid-document |
| Same-kind groups | 1 | Production steps are clean; Issues/Problems list mixes symptoms and rework |
| Order | 1 | Production section is time-ordered; Issues section has no explicable order |
| MECE | 1 | Overlap between one-book detail and Production steps; gap on resourcing claim |
| Display | 1 | Headings exist but don't carry claims; conclusions sit in prose, not visible |

**Total: 4/10 — baseline workable, structure not yet doing its job.**

## Top three fixes

1. Take "the production process is cumbersome and fragmented and needs streamlining" out of "Overall assessment" and make it the opening line the whole memo answers to.
2. Rebuild the SCQ intro: one line each for Situation, Complication, and the literal question, before any process detail.
3. Split "Issues" into one same-kind list (causes: no end-to-end control, unclear responsibility, gaps between stages) ordered by where in the four-step process each occurs — drop the unresolved resourcing claim or turn it into a stated ask.

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 →