AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Writing

skill-msimchowitz-writing-skills-writing · by msimchowitz

Route writing and editing work to the smallest relevant focused skill. Use when a request involves prompts, general prose, AI-pattern removal, academic voice, research abstracts, cadence, semantic usage, human-readable writing guides, presentations, reviewer rebuttals, literature reviews, research papers, grant strategy, or grant proposals and no narrower writing skill has already been selected.

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-msimchowitz-writing-skills-writing

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-msimchowitz-writing-skills-writing)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
14d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Writing? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Writing Router

Select the primary deliverable, load only the matching sibling skill, and follow that skill before acting. Keep unrelated writing guidance out of context.

Route the request

  1. Identify the artifact the user is producing or revising.
  2. Infer the primary writing job from the artifact and requested outcome.
  3. Read the selected SKILL.md completely.
  4. Do not read the other sibling skills unless the request has a second,

materially distinct deliverable.

| Primary job | Load | | --- | --- | | Clarify and rewrite a prompt while preserving the user's natural prompting style | ../prompt-improving/SKILL.md | | Run the standalone Wikipedia-derived AI-pattern removal pass or explicitly invoke Humanizer | ../humanizer/SKILL.md | | Write research exposition in a thoughtful, precise, reader-minded academic voice | ../academic-voice/SKILL.md | | Draft, revise, or diagnose a research abstract as a reader-facing argument | ../abstract-writing/SKILL.md | | Revise staccato, monotonous, or mechanically contrastive prose for purposeful cadence | ../writing-cadence/SKILL.md | | Revisit a completed draft's title, subtitle, headings, paragraph heads, and transitions with global knowledge of the argument | ../non-autoregressive-writing-pass/SKILL.md | | Repair grammatical but semantically mismatched word combinations or missing intermediate relations | ../better-usage/SKILL.md | | Edit prose for clarity, voice, directness, or AI-sounding patterns; audit prose without rewriting | ../general-writing/SKILL.md | | Create, revise, compile, or review a human-readable writing guide or its PDF | ../improve-human-writing-guide/SKILL.md | | Plan, create, revise, or review slides, speaker notes, PowerPoint, Keynote, or Beamer decks | ../presentation-making/SKILL.md | | Answer reviewer comments or write a response letter, author response, or point-by-point rebuttal | ../rebuttal-writing/SKILL.md | | Research, structure, draft, or verify a literature review, survey, evidence map, or related-work synthesis | ../literature-review/SKILL.md | | Plan, draft, or revise a full research paper, introduction, related work, methods, results, discussion, or conclusion | ../paper-writing/SKILL.md | | Ideate, compare, reframe, or select grant stories, concept notes, scientific questions, team strategy, feasibility, or scope before application drafting | ../grant-planning/SKILL.md | | Draft or revise grant or fellowship application prose, including aims, significance, approach, impact, broader impacts, and sponsor responses | ../grant-writing/SKILL.md |

Control context

  • Load one primary skill by default.
  • Never treat ../../for-humans/human-writing-guide/ as a skill. The

paper-writing skill may point to it or consult the relevant chapter for an explicit template-use, teaching, or human-instruction request. Inspect or edit the guide itself only when the user asks to work on that human-readable artifact.

  • Do not load general-writing automatically for every domain task. Add it only

when the user explicitly requests voice editing or AI-slop removal, or when the selected domain skill directs a final prose pass.

  • When a selected skill invokes general-writing, let general-writing own

the Humanizer dependency and pass order. Do not load or run Humanizer a second time.

  • If the user explicitly invokes a subskill, bypass this router and use that

subskill directly.

  • If the artifact spans categories, choose the skill governing the requested

output. For example, route a presentation about a paper to presentation-making, not paper-writing.

  • If two outputs are requested, complete them in stages and load each skill only

for its stage.

  • Preserve repository instructions, templates, factual claims, notation,

citations, and format constraints. A routed skill supplements those requirements; it does not override them.

Handle ambiguity

Infer the route when the artifact makes it clear. Ask one concise question only when choosing the wrong skill would materially change the work.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.