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 mimaowang/econ-writing-skills --skill write-economics-introductiongit clone --depth 1 https://github.com/mimaowang/econ-writing-skillsWrote 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/mimaowang/econ-writing-skills/write-economics-introduction)<a href="https://agentmods.dev/skills/mimaowang/econ-writing-skills/write-economics-introduction"><img src="https://agentmods.dev/badge/skills/mimaowang/econ-writing-skills/write-economics-introduction/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/mimaowang/econ-writing-skills/write-economics-introduction"><img src="https://agentmods.dev/badge/skills/mimaowang/econ-writing-skills/write-economics-introduction.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 | $0.00186 | $0.01733 |
| Opus 5 | $0.00093 | $0.00866 |
| Sonnet 5 | $0.00037 | $0.00347 |
| Haiku 4.5 | $0.00019 | $0.00173 |
Grade A, and why
write-economics-introduction 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write an Economics Introduction
Write an English introduction that lets an informed reader recover the paper's question, answer, credibility, main findings, and verified place in the literature without receiving a false impression. An introduction is an argument about a completed or substantially developed paper, not a longer abstract and not a fixed paragraph template.
Start here
Read references/runtime-core.md completely on every invocation. It contains the closed-world evidence rules, cold classification, fact and literature ledgers, contribution test, composition spine, and private final audits. Do not draft from this file or the frontmatter alone.
Treat detailed references as normative resources that are loaded when their issue arises. Read only the routed sections unless a route says to read the whole file. Search headings first, then read the complete selected section with enough neighboring text to preserve qualifications.
Choose the mode
Infer the narrowest mode that fulfills the request:
- draft writes a new introduction from the paper body and verified positioning material.
- rewrite reconstructs existing prose so its hierarchy and claims match the delivered paper.
- outline provides paragraph functions and their evidence needs without silently turning them into prose.
- audit diagnoses factual fidelity, argument, positioning, structure, length, and style; it rewrites only when asked.
- fact-check maps claims to manuscript and cited-source evidence and identifies conflicts or unsupported additions.
- positioning examines gaps, closest work, contributions, and citation support without rewriting unrelated prose.
Polishing never authorizes factual, causal, mechanism, scope, citation, or novelty drift. Do not alter manuscript files unless the user explicitly asks for file edits.
Route the detailed knowledge
First cold-read the user's materials and privately freeze the mode, evidence universe, central object, headline claim type, paper type, positioning burden, and readiness. Do this before reading type examples, calibration cases, evals, or historical test feedback. Examples are diagnostic counterexamples, never evidence for the current paper.
What ships with it
17 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.
- agents/openai.yaml 351 B
- evals/evals.json 5.0 KB
- evals/files/causal-school-attendance-paper.md 5.3 KB
- evals/files/incomplete-literature-paper.md 1.6 KB
- evals/files/structural-grid-queues-paper.md 4.4 KB
- evals/files/theory-ai-screening-paper.md 3.5 KB
- evals/trigger-eval.json 2.8 KB
- references/composition-and-length.md 12 KB
- references/evidence-and-positioning-protocol.md 30 KB
- references/final-delivery-gate.md 3.1 KB
- references/introduction-knowledge.md 19 KB
- references/literature-positioning-and-contributions.md 18 KB
- references/paper-type-patterns.md 17 KB
- references/quality-and-sources.md 20 KB
- references/runtime-core.md 16 KB
- references/sparse-packet-protocol.md 8.5 KB
- scripts/validate_output.py 4.8 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.
- 12d ago First seen · 67 lines · 186 tokens per session scan A 85c63be717f5
write-economics-introduction is a skill published in the GitHub repository mimaowang/econ-writing-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 1,733 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
journal-adapt
Dynamic academic writing skill generator. Combines optional static writing skills with target-journal, field-top, or user-provided reference corpora, then revises a manuscript with a reviewable temporary skill. Use when the user wants to adapt an academic paper to a target journal, build a corpus-grounded writing…
humanize-mba-text
A Chinese-language rewriting tool for making AI-generated text sound more natural in the style of a Chinese MBA thesis. It focuses on practical, evidence-based, academically structured writing.
paper-reviewer
Deep pre-submission review of a scientific manuscript, modeled on Google's Paper Assistant Tool (PAT). Segments the manuscript, allocates a reasoning budget per segment, dispatches deep reviewers in parallel (each with the full text as context), and consolidates into a single report with severity, quoted evidence, and…
paper-writer
Segmented drafting of a scientific manuscript, with mandatory grounding in declared project artifacts and a project-defined authorial voice. Segments what remains to be written, allocates a reasoning budget per segment, dispatches writers in parallel (each with the full manuscript as context), and consolidates into a…
deslop
Detect, critique, and rewrite text to remove AI writing patterns — makes content sound human, specific, and credible. Use this skill whenever: writing any client-facing or published content from scratch; editing/polishing any draft that might sound "corporate AI"; asked to "make this sound more human", "remove AI…
diataxis-check
Review one existing technical-documentation page or small fragment using Diátaxis as a content-design framework. Use when the user asks whether a documentation page is well structured, logically scoped, organized around the intended reader's need, appropriate for its audience, or how it could be improved according to…