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

Subject: Recommendation: Extend Fieldbook to North and Islands in Q1 Fieldbook has delivered strong operational gains and cost reductions across the four live regions, confirming its value to Kestrel's maintenance model. However, rollout defects in training delivery and system integrations are creating avoidable costs, eroding margins in slower regions, and threatening the profitability of any further expansion. Extending to North and Islands in Q1 is recommended, provided we restructure the ...

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

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-2cfdaea2/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-2cfdaea2)

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

Download with Pro
Files
01-big-chief__codex__control.md
Subject: Recommendation: Extend Fieldbook to North and Islands in Q1

Fieldbook has delivered strong operational gains and cost reductions across the four live regions, confirming its value to Kestrel's maintenance model. However, rollout defects in training delivery and system integrations are creating avoidable costs, eroding margins in slower regions, and threatening the profitability of any further expansion. Extending to North and Islands in Q1 is recommended, provided we restructure the onboarding program and implement the asset-register and invoicing integrations before go-live.

**Fieldbook generates measurable efficiency and cost savings in live regions.**
*   Technician productivity increased from 4.6 to 5.3 jobs per day, with average travel time between jobs falling 18%.
*   Emergency same-day insertions are now automatic, reducing median assignment time to 4 minutes.
*   Overtime spending dropped 12% quarter-over-quarter, and fuel cost per job decreased 9%, driven by optimized routing.
*   Dispatchers achieved full adoption by week one following the removal of the legacy spreadsheet.
*   Financial return on investment was realized within the second quarter in Central and East.

**Training bottlenecks and integration gaps are driving rework costs and adoption delays.**
*   Classroom training is scheduled only once per region, causing adoption lags in South and West; improvised shadowing arrangements consumed an estimated 380 technician-hours of lost route time.
*   Missing equipment service history from the legacy asset register forces technicians to call the back office or ask customers, resulting in 9% of audited jobs replacing parts already covered by warranty.
*   Mismatched job-completion codes between Fieldbook and the invoicing system require the billing team to manually re-key approximately 300 records weekly, introducing transcription errors and a 2–4% monthly reconciliation variance.
*   A search limitation restricted to exact postcodes generates duplicate customer records, requiring support to merge roughly 70 records per week and fragmenting job histories.
*   Program governance failed to escalate negative patterns observed in week four of the Central rollout, allowing identical issues to recur in subsequent regions.

**Remediation steps are defined, vendor-supported, and feasible within the Q1 timeline.**
*   The vendor offers a configurable mapping table to resolve code mismatches, with setup estimated at one day.
*   Supported connectors exist for both the asset register database and the invoicing import format; IT assessment confirms these integrations are straightforward to implement.
*   Vendor responsiveness remains within contract terms, and all known technical solutions are awaiting Kestrel authorization rather than vendor development.
*   Restructuring onboarding to allow continuous or multiple training sessions will eliminate the shadowing costs and accelerate adoption curves to match Central and East performance.

Next step: Approve Q1 extension contingent on program office scoping the asset-register and invoicing integrations and redesigning the training schedule for North and Islands by end of month.

***

Restructured into a decision memo with an answer-first top, three ranked groups (value, risk, feasibility), and consolidated cross-section duplicates into MECE branches.

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.

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 →