New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Micro Writing Style

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when drafting or revising a MICRO paper's prose and structure — building the characterization-motivated introduction, budgeting 11 appendix-free pages, drawing the mechanism…

MITAuto-check passedBusiness, Finance & HR

Install Micro Writing Style

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill micro-writing-style -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills micro-writing-style --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/MICRO-Skills/skills/micro-writing-style .claude/skills/micro-writing-style && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
micro-writing-style
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
745 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when drafting or revising a MICRO paper's prose and structure — building the characterization-motivated introduction, budgeting 11 appendix-free pages, drawing the mechanism…

  • Works in 4 steps: Characterization beat. Open with… → Insight beat. One sentence naming the… → Mechanism beat. A block diagram plus a… → …
  • Revising a MICRO papers prose and structure — building the characterization-motivated introduction
  • SKILL.md covers The four-beat argument, Page budget for 11 content…, Sentence-level calibration and Figure discipline, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Micro Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when drafting or revising a MICRO paper's prose and structure — building the characterization-motivated introduction, budgeting 11 appendix-free pages, drawing the mechanism walkthrough a microarchitect can re-implement, and pairing every speedup claim with its area, storage, and power cost line.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Brand voice and tone and Budgeting and forecasting. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.

When your agent uses it

  • Revising a MICRO papers prose and structure — building the characterization-motivated introduction
  • Budgeting 11 appendix-free pages
  • Drawing the mechanism walkthrough a microarchitect can re-implement
  • Pairing every speedup claim with its area

Example prompts

  • “/micro-writing-style”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Characterization beat. Open with measured evidence that the exploitable
  2. Insight beat. One sentence naming the property your hardware will exploit
  3. Mechanism beat. A block diagram plus a walkthrough at the level of tables,
  4. Accounting beat. Speedup is half a result. The other half: area or storage

What it can do on your machine

Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Micro Writing Style loads about 1.7k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 745 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 745 words, ~1,664 tokens.

Download SKILL.mdSave it as .claude/skills/micro-writing-style/SKILL.md (or your agent's skills folder).
name
micro-writing-style
description
Use when drafting or revising a MICRO paper's prose and structure — building the characterization-motivated introduction, budgeting 11 appendix-free pages, drawing the mechanism walkthrough a microarchitect can re-implement, and pairing every speedup claim with its area, storage, and power cost line.

MICRO Writing Style

A MICRO paper is an engineering argument: this pattern exists in real workloads, here is a piece of hardware that exploits it, here is what it costs, here is what it pays. The style rules below encode how the microarchitecture community reads.

The four-beat argument

  1. Characterization beat. Open with measured evidence that the exploitable behavior exists — a miss-pattern histogram, a stall-cycle breakdown, a reuse-distance CDF — from real workloads, before any mechanism appears. MICRO reviewers trust a paper that observed the machine before modifying it.
  2. Insight beat. One sentence naming the property your hardware will exploit ("dead blocks announce themselves by burst-then-silence access"). If the insight sentence could headline three different mechanisms, sharpen it.
  3. Mechanism beat. A block diagram plus a walkthrough at the level of tables, counters, comparators, and state machines — detailed enough that a reader could size the SRAM. Include the storage budget table (bits per entry × entries).
  4. Accounting beat. Speedup is half a result. The other half: area or storage overhead, power, added latency on the critical path, and what happens on the workloads the mechanism does not help (the tax on non-beneficiaries).

Page budget for 11 content pages, no appendix

The 2026 guidelines permit no appendix, so the body must be self-sufficient — proofs of concept, sensitivity sweeps, and methodology detail all compete for the same 11 pages (references are unlimited and free).

SectionPagesNon-negotiable content
Intro + characterization2.0Motivating data figure by page 2
Background / threat model1.0Only what the mechanism needs
Mechanism2.5Block diagram, walkthrough, storage table
Methodology1.0Simulator, configs, workloads, power model — exact versions
Evaluation3.0Headline result, ablations, sensitivity, overhead accounting
Related work + conclusion1.5Deltas against nearest mechanisms

Squeezing tricks (\vspace, tightened lists, sub-9pt figure text) are barred by the guidelines and checked visually — recover space by cutting content, not leading.

Sentence-level calibration

  • Tie every performance number to its instrument: "8.4% geomean speedup on SPEC CPU2017 rate-1 in cycle-level simulation" — never let a simulated number read as a silicon number.
  • Prefer mechanism verbs (filters, throttles, bypasses, coalesces) over marketing verbs (unlocks, revolutionizes, dramatically improves).
  • State the baseline aggressively and early: "against an 8-way OoO core with a state-of-the-art stride+SMS prefetcher" beats "against a baseline core."
  • Quantify the negative space: which workload class regresses, by how much, and why the mechanism's guard logic bounds it.

Figure discipline

text
Fig. 1  motivating characterization (the "why" figure)   — page 1-2
Fig. 2  mechanism block diagram (the "what" figure)      — mechanism section
Fig. 3  headline bar chart, geomean marked, baseline = 1 — first evaluation page
Fig. 4+ ablation / sensitivity, one question per figure
Every figure: axis labels >= 9pt after scaling; caption states config + workload set.

A MICRO reader flips to Fig. 2 and Fig. 3 before reading a word — both must stand alone with their captions.

Show full SKILL.md (330 more words)Show less

Naming and terminology conventions

  • Name the mechanism once, early, and use the name relentlessly. MICRO papers are remembered by mechanism name (UCP, McPAT, DaDianNao); a design referred to as "our approach" for eleven pages has no handle for reviewers to discuss it by.
  • Keep the community's units: IPC and speedup for performance, MPKI for misses/branch events, KB/mm² for cost, nJ/pJ per access for energy. Converting a miss-rate percentage where the reader expects MPKI adds friction.
  • "Baseline" means the unmodified reference machine; "prior work" means the best published competitor — never blur the two in prose or legends.
  • Threat-model vocabulary (for security mechanisms): attacker capability, channel, and what is explicitly out of scope, stated before the mechanism, not after.

Title and abstract conventions

The title should carry the mechanism name plus the structure touched ("Ghostline: Demand-Triggered Dead-Block Reclamation for Shared LLCs") — searchable by the structure, memorable by the name. The abstract executes the four beats in miniature, each beat with a number attached; see resources/worked-examples/01-introduction.md for a full before → after.

Anti-patterns the PC flags

  • Characterization-free introductions that open with "Moore's law" boilerplate.
  • Mechanisms described only in prose, with no sizeable structure — unimplementable.
  • Evaluation sections that tour benchmarks instead of answering ordered questions.
  • Overhead numbers missing, or buried in a sentence instead of a table row.
  • IPC arithmetic averaged instead of geomean'd, or speedup over an unnamed baseline.
  • "Details omitted due to space" — with no appendix allowed, that reads as "details do not exist."

Revision passes, in order

  1. Argument pass — do the four beats appear, in order, with a number each?
  2. Claim-audit pass — every performance sentence checked for instrument label, baseline name, and metric correctness (geomean, MPKI).
  3. Skeptic pass — a co-author plays the methodology-forensics reviewer (micro-review-process) and attacks configs, sampling, and baselines; fix in text what they had to ask about.
  4. Compression pass — apply micro-supplementary triage until the body sits at 11 pages without squeezing tricks.
  5. Format pass — the micro-submission gate table, on paper, by eye.

Output format

text
[Argument beats] characterization / insight / mechanism / accounting: present-missing each
[Insight sentence] <quoted from draft, or ABSENT>
[Storage budget table] present at bit-level: yes / no
[Cost line] area-storage-power-latency all quantified: yes / partial / no
[Page budget] section over/under vs table above
[Figure audit] Fig1 motivates / Fig2 rebuildable / Fig3 geomean+baseline: pass-fail
[Calibration issues] <list of simulated-vs-silicon or baseline-vagueness sentences>

© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in MICRO-Skills/skills/micro-writing-style of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Micro Writing Style next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Micro Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Micro Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.7kAutomated safety check: PassMIT
Car Writing Stylefranklee16/academic-research-skills2231 repos~960Automated safety check: PassNone
Longbridge Researchhelsome/folio2713 repos~2.1kAutomated safety check: PassMIT
Bet SizingJoelLewis/finance_skills206—~2.5kAutomated safety check: PassMIT
Cre Asset Managementahacker-1/cre-agent-skills113—~1.8kAutomated safety check: PassApache-2.0
Dd LogsDataDog/pup1k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Car Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when polishing the prose of a Contemporary Accounting Research (CAR) manuscript — a front-loaded research question, disciplined accounting terminology, the ≤300-word abstract…

    223 GitHub starsUsed in 1 repo~960 tokens
    Business, Finance & HRAuto-check passed

  • Longbridge Research

    helsome/folio

    Institution ratings, consensus price targets, EPS/revenue forecasts, finance calendar, shareholder data, fund holders, insider trades (SEC Form 4), short interest, industry rankings, peer group…

    271 GitHub starsUsed in 3 repos~2.1k tokens
    Business, Finance & HRAuto-check passed

  • Bet Sizing

    JoelLewis/finance_skills

    Determine how much capital to allocate to individual positions within a portfolio.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed

  • Cre Asset Management

    ahacker-1/cre-agent-skills

    CRE Asset Management analysis suite — 9 specialist skills for post-acquisition multifamily operations including annual budgeting, monthly variance analysis, rent collection, renewal decisions…

    113 GitHub stars~1.8k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

  • Dd Logs

    DataDog/pup

    Official

    Log management - search, pipelines, archives, and cost control.

    1k GitHub stars~1.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

  • Cash Flow Forecast

    WellApp-ai/Well

    Forecast cash flow and runway for a Well workspace from booked invoices and collected bank transactions.

    345 GitHub stars~567 tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo

  • Aaag Data Analysis

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Rebuttal

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…

    1.2k GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Research Design

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…

    1.2k GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Review Process

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Submission

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…

    1.2k GitHub stars~1.6k tokensUpdated 13 days ago
    Auto-check passed

Categories

Questions about Micro Writing Style

What does Micro Writing Style do?

A skill your agent uses when drafting or revising a MICRO paper's prose and structure — building the characterization-motivated introduction, budgeting 11 appendix-free pages, drawing the mechanism…. Micro Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when drafting or revising a MICRO paper's prose and structure — building the characterization-motivated introduction, budgeting 11 appendix-free pages, drawing the mechanism walkthrough a microarchitect can re-implement, and pairing every speedup claim with its area, storage, and power cost line.

When should I use Micro Writing Style?

Micro Writing Style fits situations like: revising a MICRO papers prose and structure — building the characterization-motivated introduction; budgeting 11 appendix-free pages; drawing the mechanism walkthrough a microarchitect can re-implement; pairing every speedup claim with its area.

How do I install Micro Writing Style in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill micro-writing-style -a claude-code`. Or copy the skill folder (MICRO-Skills/skills/micro-writing-style in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/micro-writing-style in your project. Claude Code loads it when a task matches its description.

How do I install Micro Writing Style in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill micro-writing-style -a codex`. Or copy the skill folder (MICRO-Skills/skills/micro-writing-style in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/micro-writing-style in your project. Codex loads it when a task matches its description.

Can I use Micro Writing Style in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill micro-writing-style -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/micro-writing-style, .gemini/skills/micro-writing-style, .github/skills/micro-writing-style and .opencode/skills/micro-writing-style in your project.

What does Micro Writing Style need to run?

SKILL.md names no scripts, command-line tools or credentials: Micro Writing Style is instructions for the agent only.

Does Micro Writing Style access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Micro Writing Style safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Micro Writing Style use?

Micro Writing Style is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Micro Writing Style use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Micro Writing Style?

Skills that share tags, products or a category with Micro Writing Style: Car Writing Style (franklee16/academic-research-skills, 223 stars), Longbridge Research (helsome/folio, 271 stars), Bet Sizing (JoelLewis/finance_skills, 206 stars) and Cre Asset Management (ahacker-1/cre-agent-skills, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Micro Writing Style?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.

Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.