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

**Situation.** Fieldbook has run for two quarters in Central, East, South and West, and you're deciding at the quarterly meeting whether to extend it to North and Islands in Q1. **Complication.** The four regions split sharply: Central and East paid back Fieldbook's running cost within the second quarter; South and West are only at break-even. Three specific, fixable causes — not the platform — explain that gap. **Question.** Should we extend Fieldbook to North and Islands in Q1? **Answer.** ...

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-bb30deb0/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-bb30deb0)

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

Download with Pro
Files
01-big-chief__codex__control.md
# Fieldbook Rollout — Q1 Extension Decision

**Situation.** Fieldbook has run for two quarters in Central, East, South and West, and you're deciding at the quarterly meeting whether to extend it to North and Islands in Q1.

**Complication.** The four regions split sharply: Central and East paid back Fieldbook's running cost within the second quarter; South and West are only at break-even. Three specific, fixable causes — not the platform — explain that gap.

**Question.** Should we extend Fieldbook to North and Islands in Q1?

**Answer.** **Extend to North and Islands in Q1, conditional on closing three known causes first — not as-is, and not delayed.** Done, the economics reproduce Central/East's payback; done, they risk repeating South/West's two-quarter underwater run.

---

## Options

| | Option | Verdict |
|---|---|---|
| A | Extend now, unchanged process | Repeats the West pattern: same single-session training, same unscoped integrations. Two quarters underwater on current evidence. |
| B | Delay to Q2/Q3 until fixed | Forfeits schedule for no reason — all three fixes are small and already offered by the vendor/IT, not multi-quarter projects. |
| **C** | **Extend in Q1, conditional on three fixes completed first** | **Recommended** — achievable before go-live, and reproduces the fast-adoption economics. |

## Why C: the three causes, and why each is closeable before Q1

1. **Training reached technicians once, not all of them.** A single classroom session per region left late hires and absentees to learn secondhand — this is what slowed South (11 weeks to 80%) and West (still 71%, 34 of 118 never trained), drove 44% of all support tickets, and forced the shadowing that cost 380 technician-hours. Fix: schedule a second wave (or staggered onboarding) before North/Islands go live — an organizational change, not a platform one.
2. **Fieldbook never received equipment history from the asset register.** Technicians work blind, which caused 9% of audited jobs to replace already-warrantied parts and left the audit trail empty for disputes. IT calls the connector straightforward; it was simply never scoped. Fix: commission the nightly export before go-live.
3. **Completion codes don't match the invoicing system.** This forces ~300 manual re-keys a week, produces the billing errors customers catch, and causes the 2–4% weekly gap between Fieldbook and invoicing job counts. The vendor's mapping table takes about a day to configure; it only needs an owner on Kestrel's side. Fix: assign that owner now.

(A fourth, minor defect — duplicate customer records from postcode-only search — costs ~70 manual merges a week but doesn't materially affect payback; worth fixing but not a go/no-go condition.)

## Guardrail

Every South/West symptom was visible in Central by week four; the program had no mechanism to act on it early, so it repeated in each region. For North and Islands, track week-4 adoption against the Central/East curve as an explicit checkpoint — if it tracks West instead, halt further spend and revisit before Islands follows North.

## Next step

Approve extension at the quarterly meeting on the condition above; program office closes the three fixes before North training begins.

---

```mermaid
flowchart TD
    A["Extend Fieldbook to North & Islands in Q1,\nconditional on three fixes first"] --> B1["Central/East prove the economics work\nwhen adoption is fast"]
    A --> B2["South/West's shortfall traces to\nthree specific, closeable causes"]
    A --> B3["All three fixes are achievable\nbefore Q1 go-live"]
    B1 --> C11["Payback within Q2 in Central/East;\nbreak-even only where adoption lagged"]
    B2 --> C21["Single training session missed\nlate hires/absentees"]
    B2 --> C22["No asset-register feed\n→ blind jobs, warranty rework"]
    B2 --> C23["Code mismatch\n→ manual re-keying, billing errors"]
    B3 --> C31["Second training wave: organizational,\nno vendor dependency"]
    B3 --> C32["Asset feed: connector exists,\nIT calls it straightforward"]
    B3 --> C33["Code mapping: vendor solution,\n~1 day, needs an owner"]
```

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 →