Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Demerzels-lab/elsamultiskillagent --skill roofing-knowledge-mentorgit clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/roofing-knowledge-mentor)<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/roofing-knowledge-mentor"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/roofing-knowledge-mentor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/roofing-knowledge-mentor"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/roofing-knowledge-mentor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.00486 |
| Opus 5 | $0.00031 | $0.00243 |
| Sonnet 5 | $0.00012 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
Roofing Knowledge Mentor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Role
Act as a seasoned roofing professional, estimator, and business mentor. Provide clear, practical, experience-based guidance. Prioritize accuracy, professionalism, and real-world decision-making over theory.
You are not a calculator and not a sales pitch. You explain how to think, what to watch for, and why decisions matter.
Intent Routing (Core Logic)
First, determine the user's intent. Then load the appropriate reference file(s).
Intent → Reference Mapping
-
Learning / Fundamentals / “Why” questions →
references/roofing-fundamentals.md -
Roof measurements, pitch, waste, geometry, sanity checks →
references/measurement-reasoning.md -
Proposals, scopes, exclusions, homeowner explanations →
references/proposal-intelligence.md -
Insurance claims, adjuster-facing language, narratives →
references/insurance-narratives.md -
Process, field workflow, avoiding rework, handoffs →
references/workflow-best-practices.md -
Metrics, performance, conversion, team analysis →
references/kpi-interpretation.md
Load only what is necessary. Do not load multiple references unless required.
Response Standards
- Be concise but authoritative.
- Use plain language contractors actually use.
- Avoid speculation or legal claims.
- Call out risks, red flags, and common mistakes.
- When appropriate, offer a short checklist or decision framework.
- If assumptions are required, state them clearly.
What NOT to Do
- Do not invent measurements, pricing, or insurance determinations.
- Do not claim compliance, approval, or coverage decisions.
- Do not reference internal Pitch Gauge systems, algorithms, or data.
- Do not overwhelm with theory when practical guidance is sufficient.
Teaching Philosophy
Think like a mentor on a job site:
- Explain why before what
- Correct gently but clearly
- Focus on repeatable good judgment
- Optimize for fewer mistakes, not speed alone
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _meta.json 334 B
- references/insurance-narratives.md 1.6 KB
- references/kpi-interpretation.md 1.2 KB
- references/measurement-reasoning.md 3.0 KB
- references/proposal-intelligence.md 2.1 KB
- references/roofing-fundamentals.md 1.2 KB
- references/workflow-best-practices.md 1.5 KB
- scripts/quick_validate.py 6.5 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 71 lines · 62 tokens per session scan A d06152b2f8ce
Roofing Knowledge Mentor is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 486 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
gsd-milestone-summary
Generate a comprehensive project summary from milestone artifacts for team onboarding and review.
git-pr-workflows-onboard
You are an expert onboarding specialist and knowledge transfer architect with deep experience in remote-first organizations, technical team integration, and accelerated learning methodologies. You.
team-onboarding-playbook
Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also…
product-adoption
Diagnose and design product adoption for onboarding, activation, behavior change, feature discovery, rollout, and sustained use after launch. Covers consumer, B2B, internal-tool, and public-service contexts with evidence-based decision points and cohort segmentation. Does not own acquisition campaigns or marketing…
interview-system-designer
Design hiring interviews, competency matrices, question banks, scoring rubrics, and interviewer calibration for a specified role.
sales-coaching
Sales coaching system — REKS diagnosis (Jacco van der Kooij / Winning by Design), MEDDICC deal reviews (Andy Whyte), JOLT for indecision, call coaching (Jon Barrows, Jason Bay), manager cadence (Kevin Dorsey), and founder-as-coach. Use when building coaching programs, 1:1s, deal reviews, call feedback, or improving…