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 Muuuun/luxas --skill reviewgit clone --depth 1 https://github.com/Muuuun/luxasWrote 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/muuuun/luxas/review)<a href="https://agentmods.dev/skills/muuuun/luxas/review"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/review/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/muuuun/luxas/review"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.02084 |
| Opus 5 | $0.00048 | $0.01042 |
| Sonnet 5 | $0.00019 | $0.00417 |
| Haiku 4.5 | $0.00010 | $0.00208 |
Grade A, and why
review 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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Skill
Stacking is the default failure mode of autonomous review projects: "Smith et al. did X, found Y. Jones et al. extended to Z..." paragraph after paragraph, with no unifying thesis and no synthesis of tensions. Top-tier reviews do the opposite — they lead with a claim, pull disparate work into one frame, and leave the reader smarter than when they started.
This skill encodes the rhetorical and structural conventions of landmark reviews across 10 domains, mined from real corpus text (RMP, Chem. Rev., Nat. Rev. X, Annu. Rev., Bull. AMS, Science / Nature Reviews, and the domain-specific tier-1 venues). Inject a domain's style guide, follow the 3-step pipeline, obey the hard rules — and the output should pass the Turing test for an editor at its target venue.
When to use which venue voice
┌──────────────────────────────────────────────────┬──────────────────┐
│ Target length / audience │ Voice │
├──────────────────────────────────────────────────┼──────────────────┤
│ Monograph (50–150 pp), pedagogical, archival │ RMP / Chem.Rev. │
│ → equations, boxes, glossary, deep derivation │ / Phys.Rep. │
│ Specialist (20–40 pp), claim-dense, tutorial │ Annual Reviews │
│ → thesis-per-section, figure-rich │ │
│ Short assessment (5–15 pp), stance-forward │ Nat. Rev. X / │
│ → abstract-caliber thesis per ¶, citation-dense │ Trends / Curr.Op. │
│ Opinionated essay (5–20 pp), single author │ Nat Comment / │
│ → warm first-plural, polemical beat │ Nobel lecture │
└──────────────────────────────────────────────────┴──────────────────┘
See references/decision_tree.md for full venue taxonomy.
The 3-step pipeline (mandatory)
Skip no step. Each exists because stacker projects skip exactly this step.
Step 1 — Outline with thesis per section (BEFORE any prose)
Produce notes/report_outline.md first (canonical path — the finish-gate's
outline check reads exactly this file; first line MUST be type: survey).
For the annotated gold-standard skeleton, see
skills/review/references/exemplar_survey_outline.md:
What ships with it
16 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.
- references/anti_patterns.md 5.2 KB
- references/decision_tree.md 5.1 KB
- references/exemplar_survey_outline.md 3.6 KB
- references/synthesis_rubric.md 4.4 KB
- references/transition_moves.md 4.0 KB
- scripts/sync_style_guides.sh 865 B runs code
- style_guides/astronomy.md 9.6 KB
- style_guides/biology.md 9.5 KB
- style_guides/chemistry.md 13 KB
- style_guides/computer_science.md 13 KB
- style_guides/earth_environment.md 9.2 KB
- style_guides/economics.md 11 KB
- style_guides/materials.md 9.2 KB
- style_guides/mathematics.md 14 KB
- style_guides/medicine.md 13 KB
- style_guides/physics.md 14 KB
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.
- 9d ago First seen · 177 lines · 97 tokens per session scan A dd10e8c85590
review is a skill published in the GitHub repository Muuuun/luxas (991 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 2,084 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
research-rigor
A structured method for doing research and analysis with explicit assumptions, evidence checks, scoring criteria, independent review, and later accuracy checks. The description is mainly in Chinese and does not define a specific software integration.
nature-academic-search
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv). Use when the user needs coordinated multi-step literature workflows beyond a…
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
neuroskill-bci
Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app…
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.