Awesome Journal Skills is a collection of agent skill packs tailored to hundreds of academic journals across fields including economics, social science, medicine, science, and engineering. Researchers use the packs for tasks such as choosing topics, designing empirical strategies, preparing tables and figures, submitting papers, and responding to reviewers. The catalogue entries are the project's journal-specific skills and related plugins.
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 brycewang-stanford/Awesome-Journal-Skills --skill asplos-topic-selectiongit clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-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/brycewang-stanford/awesome-journal-skills/asplos-topic-selection)<a href="https://agentmods.dev/skills/brycewang-stanford/awesome-journal-skills/asplos-topic-selection"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/asplos-topic-selection/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/brycewang-stanford/awesome-journal-skills/asplos-topic-selection"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/asplos-topic-selection.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 | $0.00085 | $0.01593 |
| Opus 5 | $0.00043 | $0.00796 |
| Sonnet 5 | $0.00017 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
asplos-topic-selection 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 today.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASPLOS Topic Selection
ASPLOS's self-description is unusually operational: it seeks work that improves the core disciplines — operating systems, programming languages, computer architecture — and their intersection, and its 2027 rapid-review round explicitly prioritizes submissions at that intersection (CFP, checked 2026-07-08). Venue fit is therefore not a prestige question here; it is a screening variable. A technically strong paper that lives cleanly inside one community can be filtered in the first round not because it is bad but because a single-community venue owns its reviewers.
The deletion test
Ask, for each layer the paper touches: if this layer's content were deleted, would a publishable paper remain?
- Delete the software half and a full paper remains → the work is an ISCA/MICRO/HPCA candidate wearing an ASPLOS template.
- Delete the hardware half and a full paper remains → it is a SOSP/OSDI/EuroSys or PLDI paper.
- Delete either half and nothing defensible remains → the coupling is real; ASPLOS is a first-choice target.
The exemplars library shows what passing looks like in award-validated form: an
accelerator argued from data movement, a scheduler premised on hardware
heterogeneity, an interrupt-delivery boundary redrawn between hypervisor and silicon
(see ../../resources/exemplars/library.md).
Routing table
| If the core claim is... | Stronger first target | ASPLOS becomes right when... |
|---|---|---|
| A microarchitectural structure (predictor, cache policy, pipeline) | ISCA / MICRO / HPCA | The structure exists to serve a named software behavior, and software changes with it |
| A language design, type system, or compiler optimization | PLDI / POPL / CGO / OOPSLA | The compiler co-evolves with an ISA, accelerator, or OS interface |
| An OS/distributed-systems design on commodity hardware | SOSP / OSDI / EuroSys / ATC | Hardware assumptions are load-bearing: new memory technology, custom hints, near-data compute |
| HPC-scale performance engineering | SC / PPoPP | The result generalizes into an architectural or systems principle beyond one machine |
| ML training/serving systems on stock stacks | MLSys | The ML workload drives a hardware/software interface change, not just better scheduling |
| Security via hardware mechanisms | IEEE S&P / USENIX Security / CCS | The defense requires co-designed architecture + systems support and its evaluation is performance-shaped |
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.
- today First seen · 126 lines · 85 tokens per session scan A 4b452e3bf48d
asplos-topic-selection is a skill published in the GitHub repository brycewang-stanford/Awesome-Journal-Skills (1,109 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,593 once invoked, about $0.0004 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 2026-09-15.
Other skills, from other repositories
test-research-code
Make research code runnable and repeatable for artifact review by auditing README, dependencies, seeds, entrypoints, data instructions, result commands, and smoke tests with reprocheck.py. Use for smoke tests, seed pinning, environment capture, reproducibility checks, or works-on-my-machine cleanup.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
test-setup
Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow. Run once during Technical Setup phase before the first sprint begins.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
team-polish
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
test-iterate-loop
Autonomously diagnose a codebase, apply minimal fixes, and rerun tests until they pass or a real blocker is reached. Use when the user explicitly requests an iterative fix-until-green loop across Python, R, Julia, or HPC workflows.