claude-skill

claude-skill is a skill for Claude Code from cmertdalli/polisci-review. It costs 0 tokens per session (507 once invoked), scanned A, a copy of polisci-review, MIT.

A manuscript-checking workflow for political science papers before they are sent to a journal. It uses journal-specific reviewer perspectives and checks suited to the paper’s review stage.

In plain words
What is it for?
Use it to review a political science manuscript and its related files, such as appendices, figures, tables, and bibliographies, then produce review reports.
Why use it?
It helps find problems before journal reviewers do, while tying each reported issue to evidence in the manuscript.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to review a political science manuscript and its related files, such as appendices, figures, tables, and bibliographies, then produce review reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cmertdalli/polisci-review/claude-skill
Install

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.

Any agent
npx skills add cmertdalli/polisci-review --skill claude-skill
Clone the repo
git clone --depth 1 https://github.com/cmertdalli/polisci-review

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 claude-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmertdalli/polisci-review/claude-skill/github.svg)](https://agentmods.dev/skills/cmertdalli/polisci-review/claude-skill)
Your own site
<a href="https://agentmods.dev/skills/cmertdalli/polisci-review/claude-skill"><img src="https://agentmods.dev/badge/skills/cmertdalli/polisci-review/claude-skill/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 claude-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmertdalli/polisci-review/claude-skill"><img src="https://agentmods.dev/badge/skills/cmertdalli/polisci-review/claude-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 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.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00507
Opus 5 $0.00000 $0.00253
Sonnet 5 $0.00000 $0.00101
Haiku 4.5 $0.00000 $0.00051

Measured 12d ago against content hash 347ebb8849db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-skill 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.

Origin

This is a copy

100% identical to polisci-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

templates/claude-skill/SKILL.md · 41 lines

What it actually says


description: Run a public-facing political science pre-submission audit with journal personas, stage gating, and evidence-grounded issue reporting argument-hint: [journal] [track] [stage] [path]

You are coordinating a rigorous political science pre-submission audit.

This installed skill is self-contained. Read the canonical review files in this directory before reviewing:

  1. ./core/invocation-spec.md
  2. ./core/journal-manifest.json
  3. ./core/paper-discovery.md
  4. ./core/track-stage-rules.md
  5. ./core/issue-taxonomy.md
  6. ./core/references/guardrails.md
  7. ./core/references/journal-signals.md
  8. ./core/references/journal-personas.md
  9. the relevant module specs in ./core/modules/
  10. ./core/report-template.md

Then:

  1. Parse $ARGUMENTS using the canonical invocation contract.
  2. Discover the manuscript and any linked .tex, appendix, figure, table, and bibliography files. Prefer .tex whenever available; support .docx, .md, .txt, and text-readable .pdf on a best-effort basis.
  3. Detect the stage and track if they were omitted.
  4. Run the 9-module review structure defined in ./core/modules/.
  5. Write two output files in the main manuscript directory when a manuscript path is available; otherwise write them in the current working directory:
    • review-report.md using the canonical report template
    • review-report.json conforming to ./core/issue-schema.json
  6. Before finishing, make sure review-report.json is valid JSON and briefly confirm the paths you wrote.

Mandatory guardrails:

  • Do not merely describe the outputs. Write the files unless the environment prevents file output.
  • If the environment cannot write files, say so explicitly and return the Markdown report plus the JSON artifact directly in the response.
  • Every issue must include a module, location anchor, evidence status, and journal_policy_ref.
  • Do not claim missing references, broken cross-references, or absent robustness checks without checking the files.
  • If .docx or .pdf text cannot be read reliably, say so and ask for exported text instead of guessing.
  • Proposals and dissertations must be reviewed with stage-aware expectations.
  • Use PA for Political Analysis.
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 · 41 lines · 0 tokens per session scan A 347ebb8849db

Subscribe to this mod's changes

claude-skill is a skill published in the GitHub repository cmertdalli/polisci-review (18 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 507 tokens. A static security scan graded it A with 0 findings. It is 100% identical to polisci-review, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

ieee-letter

Write or compress an IEEE communications LETTER for WCL (IEEE Wireless Communications Letters) or CL (IEEE Communications Letters): a single-contribution paper with a compressed introduction, no standalone related-work section, one system model, one core result (an algorithm OR a closed-form expression), and a tight…

TenWalk/ieee-skills · 209 tokens

ieee-experiments

Design and audit IEEE communications simulation and numerical-results sections for JSAC, TWC, TCOM, WCL, and CL. Covers benchmark schemes, Monte-Carlo protocol, BER/SER/outage/rate/EE metrics, SNR/antenna/user sweeps, analysis-vs-simulation validation, convergence and complexity, learning-based evaluation, ISAC…

TenWalk/ieee-skills · 137 tokens

ieee-polishing

Polish academic prose to IEEE-journal style at the sentence level — clarity, sentence length, section-appropriate tense, calibrated hedging, US English, acronym discipline, numbered-citation phrasing, and unit/number formatting. Also translate Chinese drafts into IEEE-style English. Use this whenever the user wants to…

TenWalk/ieee-skills · 152 tokens

ieee-response

Draft the two letters an IEEE submission needs — the point-by-point response to reviewers and the cover letter to the editor — so every comment is answered, every change is traceable to the revised manuscript, and the tone stays cooperative without conceding more than the evidence requires. Use this whenever the user…

TenWalk/ieee-skills · 151 tokens

ieee-writing

Draft, restructure, or plan IEEE communications-journal manuscript sections (JSAC, TWC, TC/TCOM, WCL, CL): abstract + Index Terms, introduction with a contributions list, related work, system model, problem formulation, proposed solution/algorithm, performance analysis (theorems/proofs), numerical results, discussion…

TenWalk/ieee-skills · 198 tokens

ieee-figure

Produce publication-grade result figures for IEEE communications papers (JSAC, TWC, TC/TCOM, WCL, CL) — correct column widths, embedded fonts, vector output (PDF/EPS), grayscale- and colorblind-safe palettes, readable fonts, and the comms-standard plot types: BER/outage vs SNR on a log y-axis, achievable/sum rate vs…

TenWalk/ieee-skills · 262 tokens