Portwood: Skill for Claude Code

.claude/skills/triage-report/SKILL.md

triage-report is a skill for Claude Code from Portwood-Global-Solutions/Portwood. It costs 70 tokens per session (1,518 once invoked), scanned A, original, Apache-2.0.

A decision guide for investigating Portwood reports about incorrect PDFs, missing merge tags, images, charts, or layouts.

In plain words
What is it for?
Use it to gather the needed template and output, distinguish HTML from DOCX problems, and decide whether the issue belongs to engineering or template authoring.
Why use it?
Many apparent software bugs are caused by the template, especially unsupported CSS, so the guide requires reproduction and template checks before code changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Portwood-Global-Solutions/Portwood's own configuration. It tells Claude Code how to work on Portwood itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Portwood configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Portwood-Global-Solutions/Portwood. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Portwood-Global-Solutions/Portwood/main/.claude/skills/triage-report/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Portwood-Global-Solutions/Portwood

Made for: Claude Code.

Wrote 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.

agentmods badge for triage-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/portwood-global-solutions/portwood/triage-report/github.svg)](https://agentmods.dev/skills/portwood-global-solutions/portwood/triage-report)
Your own site
<a href="https://agentmods.dev/skills/portwood-global-solutions/portwood/triage-report"><img src="https://agentmods.dev/badge/skills/portwood-global-solutions/portwood/triage-report/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.

agentmods 80×15 button for triage-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/portwood-global-solutions/portwood/triage-report"><img src="https://agentmods.dev/badge/skills/portwood-global-solutions/portwood/triage-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01518
Opus 5 $0.00035 $0.00759
Sonnet 5 $0.00014 $0.00304
Haiku 4.5 $0.00007 $0.00152

Measured 12d ago against content hash 28f198619151, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

triage-report 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 12d 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.

.claude/skills/triage-report/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triaging a Portwood report

Most reports are template issues, not code defects. Work through this before calling anything a bug. A report that turns out to be an authoring problem gets answered as guidance and closed with the template-help label — it does not become engineering work.

Step 1 — Reproduce it

Do not skip to a diagnosis from the description. Get the template, the record, and the output format. If you can't reproduce, ask for the template body and the generated file before anything else.

The single most useful question to ask a reporter: "Is the template HTML or DOCX?" It splits the decision tree in half.

Step 2 — Rule out the template

These account for the majority of "it looks wrong" reports.

CSS 3 in an HTML template

The PDF engine is Blob.toPdf → Flying Saucer, which is CSS 2.1 plus a small CSS 3 subset. These are silently ignored — the page renders, but layout collapses to default block flow:

  • display: flex, display: grid, gap
  • linear-gradient(...) and other gradient functions
  • calc(...)
  • CSS custom properties / variables
  • most CSS 3 layout features

Grep the template body first:

grep -nE "display:\s*(flex|grid)|gap:|linear-gradient|calc\(|var\(--" template.html

Any hit → template issue. The fix is <table>-based layout and solid colors.

The tbody selector trap

table > tbody > tr > td silently matches nothing, because the parser's tree doesn't have the implied <tbody> the browser inserts. Use td attributes or class-only selectors instead. A stylesheet that "does nothing" usually has one of these.

A chart style the output format can't render

Charts work in Word, PowerPoint, Excel, PDF and HTML — but not every style works in every format, and the mismatch is silent. Check the style against the format before calling it a bug:

Style Word / PPTX / XLSX HTML → PDF HTML in a browser
bar ✅ PNG ✅ CSS-bar
pivot ✅ CSS table
clustered, stacked ✅ PNG ✅ CSS table
column, pie, donut, line, area ✅ PNG ❌ needs SVG ✅ with htmlRender=svg

Read the full file on GitHub · 138 lines

Changes

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.

  1. 12d ago First seen · 138 lines · 70 tokens per session scan A 28f198619151

Subscribe to this mod's changes

triage-report is a skill published in the GitHub repository Portwood-Global-Solutions/Portwood (122 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 1,518 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 2026-08-30.

Related

Other skills, from other repositories

nebula-logger-instrumentation

Use this skill when the user wants to add or update Nebula Logger instrumentation in Apex, LWC, Aura, Flow, or OmniStudio. Covers logging APIs, save patterns, record association, scenarios, tags, async transaction linking, and save method selection.

jongpie/NebulaLogger · 60 tokens

nebula-logger-best-practices

Use this skill when the user wants to review, harden, or standardize Nebula Logger usage across a Salesforce team. Covers operational logging standards, environment-aware settings, limit-aware design, and governance guardrails.

jongpie/NebulaLogger · 52 tokens

nebula-logger-console

Use this skill when the user wants to browse, filter, or investigate Nebula Logger data in the Salesforce UI. Covers the Logger Console app, list views on Logc / LogEntryc / LogEntryTagc / LoggerScenarioc / LoggerTagc, related-list navigation, the Log record page and its LWCs, and how admins and support engineers use…

jongpie/NebulaLogger · 98 tokens

sf-debug

Debug and troubleshoot Salesforce applications using debug logs, governor limit monitoring, error diagnosis, and performance profiling. Use when analyzing debug logs, diagnosing governor limit violations, interpreting stack traces, resolving common Salesforce errors, or profiling Apex performance. Activate on .log…

Clientell-Ai/salesforce-skills · 89 tokens

docx_skill

Word document generation, supports headings/paragraphs/tables, generates professional format reports.

sunchaokun/zensers · 20 tokens

analytics-dataflow-development

Use this skill when building, debugging, or optimizing CRM Analytics dataflows — defining node types (sfdcDigest, Append, Augment, computeExpression, computeRelative, Flatten, dim2mea, sfdcRegister), scheduling runs, handling run failures, and tuning performance. NOT for doing the same transformation in a Data Prep…

PranavNagrecha/AwesomeSalesforceSkills · 103 tokens