SkillAgentSearch skills...

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include…

Install / Use

npx skills add brycewang-stanford/Awesome-Journal-Skills --skill asplos-writing-style

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

90/100

Supported Platforms

Universal

Our assessment of asplos-writing-style

asplos-writing-style scores 90/100 on our quality scale, 438th of 1,148 Content & Media skills we index (top 39%).

Its SKILL.md is 6.5 KB long, well organised into 11 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.

With 1,158 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
18/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so asplos-writing-style is actively maintained.
  • Our last check on 2026-10-30 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

asplos-writing-style compared with similar skills

All 4 of these similar skills score higher than asplos-writing-style; compare them before choosing.

SkillScoreStarsUpdatedFormat
asplos-writing-style (this skill)by brycewang-stanford901.2k2mo agoSKILL.md
Agent-Reachby Panniantong100114.0ktodayCLAUDE.md
headroomby headroomlabs-ai10080.5ktodayCLAUDE.md
Scraplingby D4Vinci100104.9k5d agoMCP Server
crawl4aiby unclecode10087.7k2d agoMCP Server

Frequently asked questions

How do I install asplos-writing-style?
Run npx skills add brycewang-stanford/Awesome-Journal-Skills --skill asplos-writing-style. The install tabs above show the steps for each supported agent.
Which AI agents does asplos-writing-style work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is asplos-writing-style safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is asplos-writing-style still maintained?
The repository was last updated about 2 months ago, so asplos-writing-style is actively maintained.

name: asplos-writing-style description: Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and footnotes.

ASPLOS Writing Style

Two 2027 mechanics dictate ASPLOS prose (CFP, checked 2026-07-08): the rapid review reads only the first two pages, and the 11-page limit counts all text, figures, tables, and footnotes — references excluded. The first makes pages 1-2 a survival organ; the second makes every figure a budget decision. Style here is mostly resource allocation.

Engineering pages 1-2 as a standalone document

By the bottom of page 2, a screener must hold four things. Audit for them mechanically, in order:

| Element | Test | Common failure | |---|---|---| | Cross-layer problem | Can a reader from any of the three communities restate it? | A single-community problem with "co-design" sprinkled on | | One-sentence insight | Is there a sentence a screener could quote in their note? | Insight diffused across three paragraphs, or a category ("we co-design X and Y") instead of an idea | | Mechanism sketch | Does the reader know what each layer does? | Architecture described, software hand-waved (or vice versa) | | Headline evidence | Result + platform class (silicon/FPGA/simulator) + baseline named? | "Significant improvements on a variety of workloads" |

Corollary: background sections, notation, and roadmaps do not belong on pages 1-2. The worked example (../../resources/worked-examples/01-introduction.md) shows a full before → after against exactly this table.

The insight sentence

The load-bearing sentence in an ASPLOS paper names information or capability that crosses a layer boundary: what the hardware knows that the OS needs, what the compiler can prove that the microarchitecture can exploit. Drafting discipline:

Weak:   "We propose a hardware/software co-designed approach to memory tiering."
        (names a category and a topic; contains no idea)
Strong: "The contention data the OS needs already passes through the memory
        controller on every access; the fix is a narrow architectural channel,
        not a smarter kernel heuristic."
        (names the information, its current location, and the boundary moved)

If this sentence cannot be written, the problem is usually fit, not prose — return to asplos-topic-selection.

Structuring the mechanism across layers

Give each layer its own subsection with its own contribution statement, then a section for the interface between them — the interface is the paper's actual thesis and deserves first-class treatment (encoding, semantics, virtualization behavior, failure modes). Reviewers from different communities will each read "their" subsection closely; the interface section is where they meet.

Claim calibration, systems dialect

  • Bound claims by construction: "never regresses more than 2% on our non-tiered suite" is a stronger sentence than "negligible overhead."
  • Attach the instrument to the number in the same sentence: "1.18× gmean on real hardware (14 workloads)" vs "up to 3.4× in simulation" are different epistemic objects and must not blend.
  • Write the losing case in the same register as the winning ones. One honestly analyzed regression buys more reviewer trust than a page of wins.

The 11-page budget with figures inside it

Because figures count against the limit, they compete with prose on equal terms:

  • Every figure must either carry a claim or explain the mechanism; delete gallery plots and merge panels that make one point.
  • Prefer one annotated diagram of the boundary/interface over three block diagrams of components — reviewers cite the diagram that explains the idea.
  • Compression order when over budget: cut duplicate-message plots → collapse per-workload bars into summary + appendix grid → tighten mechanism prose → never touch template geometry (mandatory template; violations risk rejection unread).

House-rule details that mark a native submission

  • References carry every author's full first and last name — no "et al." — with hyperlinked in-text numbers and DOIs per entry; a hygiene-signaling detail reviewers notice early.
  • Third-person self-citation throughout; no "removed for blind review" text.
  • GenAI assistance, if any, disclosed per ACM policy (Acknowledgments, immediately before References).

A load-order for the abstract

Six sentences, in this order, cover what both the rapid screener and the eventual citer need: (1) the friction two layers create today; (2) the insight sentence; (3) the mechanism, one clause per layer; (4) the headline number with instrument and baseline; (5) the bound on the downside; (6) what the interface enables beyond this paper. Most first drafts invert 1 and a background sentence — delete the background sentence; ASPLOS readers do not need to be told memory matters.

Section skeleton that serves three readerships

A cross-layer paper defaults well to: motivation-with-evidence (measured, not asserted — a characterization figure beats three citations); design overview around one boundary diagram; per-layer mechanism sections; the interface section; evaluation ordered by the claim matrix; related work by lanes (asplos-related-work); then discussion of what the boundary change costs. Each community's reviewer should be able to find "their" section from the table of contents alone — a paper organized by implementation chronology instead forces reviewers to reconstruct the design, and annoyed reconstruction reads as "unclear writing" in reviews.

Revision-aware prose

Because Major Revision is a standing outcome, write sentences that can absorb revision without rewiring: quantitative claims phrased with their scope ("across the 14-workload suite") extend gracefully when workloads are added; hard-coded superlatives ("the first", "the fastest") require re-litigation at every resubmission and are the first phrases a shepherd strikes.

Output format

[Two-page audit] problem / insight-sentence / mechanism / evidence — each Y/N + fix
[Insight sentence] <quoted verbatim>
[Layer structure] per-layer subsections + interface section present: Y/N
[Claim calibration] unbounded adjectives found: N · instrument attached per number: Y/N
[Figure budget] figures: N · pages consumed: N · deletions/merges proposed
[House rules] citations format / self-cite person / GenAI disclosure — pass/fail

Related Skills

View on GitHub
GitHub Stars1.2k
CategoryContent
Updated2mo ago
Forks153

Languages

Stata

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions