agentic-reviewer: Skill for Claude Code

.cursor/skills/compile-report/SKILL.md

compile-report is a skill for Claude Code, Cursor from FilippoScaramuzza/agentic-reviewer. It costs 40 tokens per session (490 once invoked), scanned A, original, MIT.

A review step that combines five separate academic-paper assessments into one report. The assessments cover scope, methods, writing, statistics, and ethics.

In plain words
What is it for?
Use it after the individual reviews exist to produce a recommendation such as accept or reject, with ranked issues, strengths, and suggested fixes.
Why use it?
It removes the need to read and combine reviewer notes yourself, while highlighting missing files, disagreements, and the most important problems.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is FilippoScaramuzza/agentic-reviewer's own configuration. It tells Claude Code and Cursor how to work on agentic-reviewer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-reviewer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FilippoScaramuzza/agentic-reviewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FilippoScaramuzza/agentic-reviewer/main/.cursor/skills/compile-report/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FilippoScaramuzza/agentic-reviewer

Made for: Claude Code, Cursor.

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 compile-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/filipposcaramuzza/agentic-reviewer/compile-report/github.svg)](https://agentmods.dev/skills/filipposcaramuzza/agentic-reviewer/compile-report)
Your own site
<a href="https://agentmods.dev/skills/filipposcaramuzza/agentic-reviewer/compile-report"><img src="https://agentmods.dev/badge/skills/filipposcaramuzza/agentic-reviewer/compile-report/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 compile-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/filipposcaramuzza/agentic-reviewer/compile-report"><img src="https://agentmods.dev/badge/skills/filipposcaramuzza/agentic-reviewer/compile-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 490 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 original No closer match found 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 $0.00040 $0.00490
Opus 5 $0.00020 $0.00245
Sonnet 5 $0.00008 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 9d ago against content hash e7f8642e68a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compile-report 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 9d 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.

.cursor/skills/compile-report/SKILL.md · 57 lines

What it actually says

Compile Report

Synthesize all individual reviewer assessments into one unified, comprehensive, actionable review report.

Prerequisites

Before compiling, read ALL individual review files from the report directory:

  1. <report-directory>/05-scope-review.md
  2. <report-directory>/06-methodology-review.md
  3. <report-directory>/07-writing-style-review.md
  4. <report-directory>/08-statistics-review.md
  5. <report-directory>/09-ethics-review.md

If any file is missing, note the gap in the report but compile what is available.

Compilation Guidelines

Synthesize, Don't Copy

  • Read all reviews and create a cohesive narrative
  • Resolve contradictions between reviewers fairly
  • Present the most critical issues upfront

Prioritize Issues

  • Rank issues by impact on acceptance/rejection
  • Distinguish between blocking issues (must fix) and improvements (should fix)
  • Consider the journal's typical threshold when making recommendations

Be Fair

  • Highlight strengths as well as weaknesses
  • Don't let one weak dimension dominate the entire assessment
  • Consider the overall balance of issues

Determining the Recommendation

  • ACCEPT: All dimensions ≥ 4/5, no blocking issues
  • REVISE (MINOR): Most dimensions ≥ 4/5, minor issues addressable in revision
  • REVISE (MAJOR): Several dimensions 3/5, significant issues needing substantial work
  • REJECT: Multiple dimensions ≤ 2/5, fundamental problems, or scope misfit

Handle Contradictions

If reviewers disagree: present both perspectives, note the disagreement explicitly, and provide your own assessment.

Overall Rating

Calculate the overall rating as the mean of all dimension ratings. Use trend icons:

  • ✅ (4–5): Strong, no major concerns
  • ⚠️ (3): Adequate with concerns
  • ❌ (1–2): Problematic, needs significant work

Output Location

Save to <report-directory>/10-final-review-report.md, then generate the PDF using the generate-pdf skill.

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. 9d ago First seen · 57 lines · 40 tokens per session scan A e7f8642e68a9

Subscribe to this mod's changes

compile-report is a skill published in the GitHub repository FilippoScaramuzza/agentic-reviewer (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 490 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

wiki-ingest

Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…

AvalancheAI-labs/agent-wiki-kit · 77 tokens

ingest-wiki

The write engine for the twoweeks wiki. Use this skill for four modes: ingest (process files staged in rawinput/), direct-update (apply explicit wiki edits), lint (validate structure, links, metadata, and drift), and save-output (persist an answer, audit, analysis, or report to wiki/outputs/). Read WIKISCHEMA.md first…

panamini/Pagecraft · 114 tokens

ingest-wiki

The hybrid write engine for a wiki vault that combines twoweeks-style durable knowledge management with Karpathy-style execution discipline. Supports four modes: ingest, direct-update, lint, and save-output. Read WIKISCHEMA.md first if present, then CLAUDE.md. Mutating operations require CLAUDE.md.

panamini/Pagecraft · 68 tokens

karpathy-guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

panamini/Pagecraft · 46 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

security-audit

Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.

omnigent-ai/omnigent · 64 tokens