Skip to content
Agentmart
Submit a tool

critical-reading

Skill for decomposing complex source documents — court decisions, academic papers, opposing affidavits, technical specifications, statutes, expert reports…

Skill by dmang69

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying critical-reading?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dmang69-critical-reading

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Skill for decomposing complex source documents — court decisions, academic papers, opposing affidavits, technical specifications, statutes, expert reports, contracts. Covers structural analysis (what kind of document is this, what work is each section doing), argument extraction (what is the author actually claiming and why), evidence-vs-assertion sorting, hidden assumption surfacing, weakness identification, and productive marginalia. ALWAYS trigger when: user uploads or references a court decision, RTB decision, opposing submission, affidavit, academic paper, technical spec, contract, statute section, expert report, or any dense document they need to understand or respond to; user asks to "break down", "analyze", "pull apart", "find the holes in", or "understand" a document. Pairs with supreme-court-litigation-counsel (for legal analysis), argument-architecture (for identifying opposing argument structure), canlii-boa-builder (for reading cases before citing them), and cognitive-awareness (for calibrating confidence in interpretive claims).

Use cases: documents, research, legal

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/critical-reading

What's inside

Skill name
critical-reading
Description
Skill for decomposing complex source documents — court decisions, academic papers, opposing affidavits, technical specifications, statutes, expert reports, contracts. Covers structural analysis (what kind of document is this, what work is each section doing), argument extraction (what is the author actually claiming and why), evidence-vs-assertion sorting, hidden assumption surfacing, weakness identification, and productive marginalia. ALWAYS trigger when: user uploads or references a court decision, RTB decision, opposing submission, affidavit, academic paper, technical spec, contract, statute section, expert report, or any dense document they need to understand or respond to; user asks to "break down", "analyze", "pull apart", "find the holes in", or "understand" a document. Pairs with supreme-court-litigation-counsel (for legal analysis), argument-architecture (for identifying opposing argument structure), canlii-boa-builder (for reading cases before citing them), and cognitive-awareness (for calibrating confidence in interpretive claims).
License
MIT
Instructions
445 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • description: longer than 1024 characters

Files (9)

  • SKILL.md
  • academic-paper-reading-protocol.md · references/
  • affidavit-reading-protocol.md · references/
  • contract-reading-protocol.md · references/
  • court-decision-reading-protocol.md · references/
  • argument-extraction.md · templates/
  • response-ready-extraction.md · templates/
  • section-purpose-table.md · templates/
  • weakness-log.md · templates/

SKILL.md (first lines)

# Critical Reading Skill

Slow reading, structured.

Most documents you'll encounter — court decisions, opposing affidavits,
academic papers, contracts — reward decomposition. Read once fast to get
the shape. Read again slowly, with a structure. This skill is that structure.

---

## Skill Tree

| Module | Domain |
|---|---|
| 1 | Document Type Recognition — what you're actually reading |
| 2 | Structural Decomposition — what work each section does |
| 3 | Argument Extraction — what the author claims and why |
| 4 | Evidence vs Assertion Sorting |
| 5 | Hidden Assumption Surfacing |
| 6 | Weakness Identification |
| 7 | Cross-Reference Mapping |
| 8 | Productive Marginalia — what to write in the margins |
| 9 | Reading for Response — what you'll need to answer |
| 10 | The Second Read |

---

## Module 1: Document Type Recognition

Before you can read a document well, you need to know what kind of
document it is. Different types do different work.

### The Document Type Taxonomy

```
LEGAL DOCUMENTS
  Court decisions       — reasoning applied to facts, binding force varies
  Tribunal decisions    — same, lower binding force
  Affidavits            — sworn statements of fact
  Petitions/factums     — argumentative pleadings
  Statutes              — enacted rules
  Regulations           — subordinate rules
  Contracts             — negotiated obligations
  Expert reports        — opinion evidence with methodology
  Legal memos           — internal analysis, not binding

ACADEMIC DOCUMENTS
  Peer-reviewed papers  — claims with methodology and evidence
  Preprints             — same, without peer review filter
  Theses                — extended arguments with literature review
  Books                 — extended treatments
  Textbooks             — synthesized state of a field
  Reviews / surveys     — meta-treatments of a literature
  Conference papers     — shorter, sometimes higher-velocity

TECHNICAL DOCUMENTS
  Specifications        — normative descriptions of a system
  RFCs                  — standards proposals
  API docs              — reference material
  Design documents      — proposals with rationale
  Post-mortems          — retrospective analysis
  Whitepapers           — hybrid academic/marketing
```

Each type has a different reading protocol. A court decision is read
differently from an affidavit which is read differently from a spec.

### Type-Specific Notes

- **Court decisions** — separate reasoning (ratio) from asides (obiter);
  identify the standard of review, the test applied, and the specific
  findings; note dissents if any
- **Affidavits** — everything is sworn; distinguish knowledge (personal),
  information & belief (secondhand), and argumentative statements
  (usually improper)
- **Academic papers** — separate the CONTRIBUTION from the CONTEXT;
  most papers are 80% context; the load-bearing claim usually fits in 1-2
  paragraphs
- **Specs** — identify normative language (MUST, SHOULD, MAY per RFC 2119
  convention); note ambiguities

---

## Module 2: Structural Decomposition

Every document has structure. Some documents make it explicit (headings,
numbered sections). Some hide it (long affidavits, dense academic prose).
Extract the structure either way.

### The Section-Purpose Table

For any substantial document:

```
SECTION | PURPOSE                | LOAD-BEARING?
────────┼────────────────────────┼──────────────
[1]     | [what this section does] | [Y/N]
[2]     | [what this section does] | [Y/N]
[3]     | [what this section does] | [Y/N]
...
```

Load-bearing sections carry the argument. Non-load-bearing sections
frame it, provide background, or fill space.

### Load-Bearing Section Signals

Load-bearing sections usually:
- Introduce a novel claim
- Apply a rule to specific facts
- Present evidence that supports a conclusion
- State a holding
- Draw a distinction the rest of the document depends on

Non-load-bearing sections usually:
- Restate what's already been said
- Provide historical or general context
- Handle procedural or administrative matters
- Acknowledge counterarguments only to dismiss them briefly

From dmang69/bc-legal-ai, MIT.

More from dmang69/bc-legal-ai

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Jul 29, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from dmang69

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get critical-reading running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying critical-reading?

CallGet help
Cite this page

critical-reading skill. Agent Mart. https://agentmart.dev/skills/dmang69-critical-reading (last updated 2026-10-24)