Borrowing it
Nothing to install: this file belongs to AlessandroCaforio/Academic-Writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlessandroCaforio/Academic-Writing/main/.claude/skills/write-section/SKILL.mdgit clone --depth 1 https://github.com/AlessandroCaforio/Academic-WritingWrote 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/alessandrocaforio/academic-writing/write-section)<a href="https://agentmods.dev/skills/alessandrocaforio/academic-writing/write-section"><img src="https://agentmods.dev/badge/skills/alessandrocaforio/academic-writing/write-section/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/alessandrocaforio/academic-writing/write-section"><img src="https://agentmods.dev/badge/skills/alessandrocaforio/academic-writing/write-section.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 | $0.00020 | $0.02352 |
| Opus 5.5 | $0.00008 | $0.00941 |
| Sonnet 5.5 | $0.00004 | $0.00470 |
| Haiku 4.5 | $0.00002 | $0.00235 |
Grade A, and why
write-section 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Section Skill
Write or revise a section of the thesis. This is a generalizable skill that adapts to any chapter based on section-specific templates and the established conventions from Chapters 3-5.
Arguments
introduction— Redirects to the/write-introductionskill (specialized)literature [section]— Write/revise a section of Ch.2 (e.g.,literature 2.1.4)abstract— Write the thesis abstract (~250 words)conclusion— Write Ch.6 (Conclusion)appendix Aorappendix B— Write appendix contentrevise <chapter>— Revise an existing chapter (e.g.,revise data,revise methodology)
If argument is introduction, invoke the /write-introduction skill instead.
Pre-Writing Protocol (ALL sections)
Before writing any section, you MUST:
- Read the target file to understand current state (stub? outline? partial draft? complete?)
- Read
thesis/CLAUDE.mdfor conventions, bib keys, custom commands - Read
CLAUDE.md(root) for project context, measure definitions, findings - Read
.claude/reference/literature-evidence.mdfor concrete findings from 20+ papers — use for any section that references literature - Read at least 40 lines from
03_data.tex,04_methodology.tex, and05_results.texto internalize the writing style - Read
references.bibto know which citations are available
Using the Narrative Architect
For literature-heavy sections (Ch.2 subsections, Ch.1 Antecedents, Ch.6 Interpretation), dispatch the narrative-architect agent BEFORE drafting. Provide:
- Goal: What the section needs to establish
- Target section: e.g., "§2.2 — Economic Shocks and Political Behavior"
- Constraints: Length, must-cite papers, emphasis points
The architect returns a paragraph-by-paragraph outline with specific paper citations and transition strategies. Use this as the backbone for your draft.
Style Requirements (from Chapters 3-5)
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.
- 1mo ago First seen · 268 lines · 20 tokens per session scan A b7bf6d5cd43e
write-section is a skill published in the GitHub repository AlessandroCaforio/Academic-Writing (23 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 2,352 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
proofcheck
A systematic checker for mathematical proofs in statistics and machine-learning research papers.
theory-simulation
Bridge between theoretical results and Monte Carlo simulation, built to top-stat-journal standards (AoS, JASA, JRSS-B, Biometrika, Bernoulli). Two modes: (1) DESIGN mode — for each theoretical claim, design new simulations that verify rates, coverage, stress-test assumptions, and reveal theory-improvement…
proof-repair
Generate self-consistent repair plans for mathematical proof issues found by /proofcheck, with literature-backed support. For each problematic assumption, model, proposition, or theorem, proposes fixes that preserve the full dependency chain and searches arXiv, Semantic Scholar, and Google Scholar for new references…
theory-sharpen
A framework for testing whether a research paper’s theoretical results can be made stronger, such as by using fewer assumptions or proving faster rates. It also checks whether the theory matches the model, experiments, and existing research.
theory-design
Design a coherent theoretical framework for a new statistics / ML theory research topic, paper-type aware. Three modes — Theory paper (explain phenomena or provide new theoretical tools), Methodology paper (propose a new method with theoretical guarantees), Application paper (apply existing methods to scientific data…
proof-writer
A proof-writing aid for mathematical results in machine learning and artificial intelligence theory. It checks whether the stated assumptions actually support each proof step.