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

Fieldbook has improved productivity and reduced operating costs in the four live regions, but uneven onboarding and unresolved integrations made South and West only break even. The COO should approve a Q1 extension to North and Islands conditional on a redesigned onboarding plan and named owners delivering the asset-history and invoicing integrations before go-live.

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

Works with

cli

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-f7090a55/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-f7090a55)

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

Download with Pro
Files
10-rollout-review__codex__control.md
# Fieldbook rollout: extend to North and Islands in Q1 only after readiness conditions are approved

Fieldbook has improved productivity and reduced operating costs in the four live regions, but uneven onboarding and unresolved integrations made South and West only break even. The COO should approve a Q1 extension to North and Islands conditional on a redesigned onboarding plan and named owners delivering the asset-history and invoicing integrations before go-live.

## Why extension remains the right direction

- Scheduling performance improved materially across the live regions: completed jobs per technician per day rose from 4.6 to 5.3, travel time between jobs fell 18%, and same-day emergency insertion now takes a median four minutes rather than dispatcher phone calls.
- The operational gains are translating into financial results: overtime is down 12% quarter over quarter and fuel cost per job is down 9%.
- Central and East reached full adoption within six weeks and paid back Fieldbook’s running cost within the second quarter.
- Fieldbook is now the source of record for job status; regional managers use its dashboard in Monday reviews. Vendor response times remain within contract, and the known product gaps have available vendor solutions.
- Extending to North and Islands adds £13,500 per month in licences. The economics are favourable if the Central and East adoption pattern is reproduced.

## The extension must not repeat the South and West rollout model

- South took eleven weeks to exceed 80% of orders in Fieldbook; West remains at 71% after nine weeks. In contrast, all 41 dispatchers adopted scheduling in week one because the legacy spreadsheet was switched off and no alternative remained.
- The common cause in the slower regions was incomplete onboarding: each received only one two-day classroom course. New hires and technicians absent from it relied on colleagues; in West, 34 of 118 technicians attended no session.
- Improvised shadowing worked, but consumed an estimated 380 technician-hours of route time. Support absorbed the remaining training gap: 44% of 1,940 tickets were password resets or login issues, concentrated among technicians who missed training and the supported login window.
- Weekly one-hour webinars reach only 20–30 technicians, although attendance is strongest in regions where classroom places were missed. Ticket volume peaks in each region’s third week and then declines, showing that supported onboarding can prevent rather than merely absorb the demand.
- Winter travel makes a single classroom event especially unsuitable for North and Islands.

**Condition for approval:** fund and schedule repeatable onboarding before go-live: multiple training cohorts covering absences and new hires, a supported first-login window, and protected local champions rather than ad hoc shadowing.

## The integrations need owners and completion dates before expansion

- Technicians lack equipment service history because Fieldbook receives no feed from the legacy asset register. They compensate by calling the back office or customers; in 9% of audited jobs, they replaced parts already replaced under warranty in the prior year.
- The empty equipment-history panel also hides warranty state, splits the audit trail needed for disputes, and leaves a month-two request for a nightly export still in the asset-register backlog.
- Fieldbook completion codes do not match the invoicing system. Billing manually re-keys roughly 300 records weekly, has needed a temporary clerk costing £8,400 over two quarters, and introduces invoice errors customers catch.
- The mismatch causes a 2–4% weekly difference between Fieldbook and invoicing completed-job counts, requiring manual month-end finance reconciliation.
- The vendor says a configurable code-mapping table takes roughly one day to set up. Its catalogue also lists connectors for the asset-register database and the invoicing import format. IT considers both integrations straightforward, but none was scoped and no Kestrel owner was assigned.
- A separate search limitation drives duplicate customer records: technicians cannot find records when postcodes differ from the exact search match, and support manually merges about 70 duplicates a week. This splits customer job histories until corrected.
- The parts-ordering screen is unpopular, but testing shows it works correctly; this is an adoption habit to address in training, not a product defect requiring rollout delay.

**Condition for approval:** assign accountable business and IT owners to schedule the code mapping, evaluate and implement the asset-register and invoicing connectors, and address the customer-search limitation with the vendor.

## Governance should turn early evidence into fixes before the next region launches

- Every negative pattern in the review was visible by week four of the Central go-live, yet no mechanism converted field observations into programme-level fixes; the same issues then recurred in later regions.
- The rollout programme was staffed for deployment and training, not integration delivery, leaving known vendor solutions without internal ownership.
- North and Islands should therefore launch only after a readiness review confirms onboarding capacity, integration ownership and milestones, first-login support, and a weekly cross-region issue review with authority to make programme-wide changes.

## Decision requested

Approve conditional Q1 extension of Fieldbook to North and Islands, with go-live gated on:

1. A complete multi-cohort onboarding and supported first-login plan.
2. Named owners and scheduled delivery for asset-history and invoicing integrations.
3. A pre-launch readiness review and weekly mechanism to escalate and resolve repeatable issues across regions.

Top: Approve a conditional Q1 extension to North and Islands, because Fieldbook’s operational and financial gains are real but depend on fixing onboarding, integrations and rollout governance before go-live.
  1. Extension can reproduce proven operating and financial gains
     - Jobs per technician per day rose from 4.6 to 5.3.
     - Travel time fell 18%; overtime fell 12%; fuel cost per job fell 9%.
     - Central and East adopted quickly and repaid running cost in Q2.
  2. Redesigned onboarding can prevent the adoption losses seen in South and West
     - Single classroom courses left technicians untrained and drove shadowing and support demand.
     - West remains at 71% adoption after nine weeks; 34 of 118 technicians missed training.
     - Multi-cohort training and supported first login are required before launch.
  3. Owned integrations can remove the current operational and financial leakage
     - Missing asset history contributes to repeat warranty replacements.
     - Code mismatch causes 300 weekly re-keys, invoice errors and reporting discrepancies.
     - Vendor solutions and connectors exist but require Kestrel ownership and scheduling.
  4. Readiness governance can stop known issues recurring region by region
     - Problems were visible by week four but were not converted into programme fixes.
     - Go-live should be gated by readiness review and weekly cross-region issue resolution.

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 →