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

**To:** Engagement Manager **From:** [Consultant] **Subject:** TTW can take out roughly 10% of composing cost now, and we should size a further 20–50% gap You asked what two weeks in Aylesbury turned up on composing-room costs. It turns up an answer, not just data: TTW does not need to settle the argument about whether its costs are "high" before acting — the cost structure already shows where the money is, and three actions will release it. **Recommendation: run three actions at Aylesbury, i...

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

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-feab26f4/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-feab26f4)

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

Download with Pro
Files
01-big-chief__codex__control.md
**To:** Engagement Manager
**From:** [Consultant]
**Subject:** TTW can take out roughly 10% of composing cost now, and we should size a further 20–50% gap

You asked what two weeks in Aylesbury turned up on composing-room costs. It turns up an answer, not just data: TTW does not need to settle the argument about whether its costs are "high" before acting — the cost structure already shows where the money is, and three actions will release it.

**Recommendation: run three actions at Aylesbury, in this order of payoff.**

---

**1. Simplify quality control on inexpensive titles — up to 10% of total composing cost.**

- Every title passes through essentially the same quality-control stages, whether it is a complex reference book or a simple novel; the checks priced for reference work are being applied to novels.
- The saving available from fewer or differently timed checks may reach 10% of total composing cost — the largest single figure we have, against a cost base that is ~40% of hardback and 50–55% of paperback cost.
- Test it on selected jobs and measure the effect on quality and on customers before generalising. George Kennedy is willing to run this test.

**2. Commission a methods study on the composing method — the gap is 20–50%.**

- Measured productivity at TTW trails the industry benchmark by 20–50%; industry comparisons point to weak productivity and high cost.
- A gap of that width is a method problem, not a diligence problem, and only a methods study will convert it into a number we can bank. Kennedy is also willing to test why measured productivity trails the benchmark.
- `[data needed: the specific saving a change of composing method would yield — this note cannot size it]`

**3. Fix pay and capacity in manual composition — overtime is already 50% over budget.**

- TTW pays below local market rates, cannot hire or retain compositors, and has just lost two employees.
- The department is overloaded, manual composition most acutely; most jobs now run late.
- The cost of that shortfall is being paid twice: overtime more than 50% over budget, and a union claim now on the table that a below-market pay position makes hard to resist.

---

**What I need from you:** agreement to start action 1 with Kennedy next week, and a decision on whether the methods study (action 2) is in scope for this engagement or a follow-on.

**Omitted or demoted:** the proposed comparison with three other printers — a simple comparison will not settle whether TTW's costs are excessive, and actions 1 and 2 answer the underlying question directly. Also demoted: that managers disagree about whether costs are high (they all accept an investigation, so it blocks nothing), and the record of interviews with Roy Walter, Brian Thompson and George Kennedy, which is source, not argument.

```mermaid
flowchart TD
    A["Run three actions at Aylesbury: ~10% now, plus a sized 20-50% gap"] --> B1["Simplify QC on cheap titles — up to 10% of composing cost"]
    A --> B2["Commission a methods study — 20-50% productivity gap"]
    A --> B3["Fix pay and capacity in manual composition — overtime 50% over budget"]
    B1 --> C11["All titles carry identical QC stages, novel or reference book"]
    B1 --> C12["Test on selected jobs; Kennedy willing to run it"]
    B2 --> C21["Measured productivity trails benchmark by 20-50%"]
    B2 --> C22["Gap of that width is a method problem, not diligence"]
    B3 --> C31["Below-market pay; cannot hire or retain; two just lost"]
    B3 --> C32["Overload, late jobs, overtime over budget, union claim"]
```

**What changed structurally:** the note now opens with the recommendation instead of a record of activity, and its first level holds three actions ranked by payoff rather than a mix of findings, interviews and hedged conclusions; the facts that formerly carried the note — the overload, the pay position, the benchmark gap — sit underneath the action each one justifies.

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".

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', ...

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.

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 →