plugins marketplace
← All plugins

report-analyst

v0.1.0

Skeptical analyst toolkit for long reports — verdict, structured extraction, and executive summary skills with a built-in 'jaded reader' persona that won't hand out gold stars for filler.

Claude Code12 skills

by Daniel RosehillMIT0updated 3 months ago

Source

git clone https://github.com/danielrosehill/Claude-Report-Analyst-Plugin

Clone the source, then follow the repository's marketplace instructions for your runtime. The repository root is the plugin root.

Layout

report-analyst/
├── .claude-plugin/plugin.json
├── skills/anything-interesting/SKILL.md
├── skills/comprehensive-analysis/SKILL.md
├── skills/exec-summary/SKILL.md
├── skills/export-analysis/SKILL.md
├── skills/extract-case-studies/SKILL.md
├── skills/extract-key-snippets/SKILL.md
├── skills/extract-main-arguments/SKILL.md
├── skills/extract-noteworthy-findings/SKILL.md
├── skills/extract-stats/SKILL.md
├── skills/load-report/SKILL.md
├── skills/original-thinking/SKILL.md
└── skills/worth-the-read/SKILL.md

Skills12

anything-interestingskills/anything-interesting/SKILL.md

Surface anything genuinely interesting in a report — original ideas, noteworthy statistics, strong opinions — or confirm there's nothing worth flagging. Use when the user wants a signal-finder pass without committing to a full read or extraction.

comprehensive-analysisskills/comprehensive-analysis/SKILL.md

Full critical analysis of a report — read/skim/skip verdict, opinionated executive summary, quantitative analysis, case-study deep dive, key quotes, synthesis, and metadata. Use when the user wants the complete report-analyst treatment in one bundle, saved to disk.

exec-summaryskills/exec-summary/SKILL.md

Generate a critical executive summary of a report — bottom-line findings plus an evaluation of credibility, originality, and methodology. Use when the user wants a one-page brief that doubles as a skeptical review, not a polite recap.

export-analysisskills/export-analysis/SKILL.md

Render a markdown report-analyst output to a styled PDF via Typst (preferred) or pandoc (fallback). Use when the user wants the analysis bundle as a shareable document rather than raw markdown.

extract-case-studiesskills/extract-case-studies/SKILL.md

Pull case studies from a report and group them by what they demonstrate. Use when the user wants the report's examples extracted as a reference, including company/entity context, the point each case supports, and significant quotes.

extract-key-snippetsskills/extract-key-snippets/SKILL.md

Pull memorable, citable passages from a report — soundbites, well-summarised key issues, sharp findings worth quoting on social media or in further writing. Use when the user wants pull-quotes rather than analysis.

extract-main-argumentsskills/extract-main-arguments/SKILL.md

Pull the report's main arguments — core thesis, supporting arguments, evidence strength, counterarguments — into a structured table. Use when the user wants to quickly understand what the authors are trying to prove and how convincingly.

extract-noteworthy-findingsskills/extract-noteworthy-findings/SKILL.md

Pull only the unexpected, contradictory, or paradigm-shifting findings from a report — skipping confirmatory and well-known results. Use when the user wants the surprises rather than the executive summary.

extract-statsskills/extract-stats/SKILL.md

Pull every meaningful statistic from a report and group them thematically with page references. Flags unsourced or repackaged stats. Use when the user wants the report's quantitative spine extracted as a reference table, not a summary.

load-reportskills/load-report/SKILL.md

Normalise a report file (PDF, DOCX, HTML, large markdown) into Claude-readable text with page anchors preserved. Use as the input adapter for the other report-analyst skills when the user passes a path on disk rather than pasted text.

original-thinkingskills/original-thinking/SKILL.md

Assess whether a report contains genuinely original thinking or is just regurgitated content. Use when the user suspects a report is filler / restated common knowledge and wants confirmation, with the truly-original claims (if any) ranked separately from the rest.

worth-the-readskills/worth-the-read/SKILL.md

Quick READ / SKIM / SKIP verdict on a long report — does it justify the reader's time? Use when the user has a report (PDF, DOCX, MD) and wants a fast filter before committing to read it. Output is a verdict, a 1-5 rating across originality and length-justification, and a short rationale.

Manifests1

.claude-plugin/plugin.json
{
  "name": "report-analyst",
  "version": "0.1.0",
  "description": "Skeptical analyst toolkit for long reports — verdict, structured extraction, and executive summary skills with a built-in 'jaded reader' persona that won't hand out gold stars for filler.",
  "author": {
    "name": "Daniel Rosehill",
    "url": "https://github.com/danielrosehill"
  },
  "homepage": "https://github.com/danielrosehill/Claude-Report-Analyst-Plugin",
  "repository": "https://github.com/danielrosehill/Claude-Report-Analyst-Plugin",
  "license": "MIT",
  "keywords": [
    "analysis",
    "reports",
    "summarisation",
    "extraction",
    "research"
  ]
}