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

Science Polishing

skill-shikaijieskj-science-skills-science-polishing · by shikaijieskj

Polish, restructure, or translate academic prose into concise Science/AAAS-family English. Use when the user asks to improve an abstract, introduction, Results paragraph, Discussion, title, cover-letter paragraph, rebuttal sentence, or Chinese academic draft for Science, Science Advances, Science Robotics, Science Translational Medicine, or adjacent high-impact journals.

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

Install

$ agentstack add skill-shikaijieskj-science-skills-science-polishing

✓ 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-shikaijieskj-science-skills-science-polishing)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo 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 Science Polishing? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Science Polishing

Use this skill to improve prose without hiding weak logic. Fix argument first, then style.

Default stance

  • Preserve the author's evidence and intended meaning.
  • Do not invent data, citations, novelty, mechanism, ethics approvals, or journal acceptance claims.
  • Prefer concise, concrete sentences over ornate academic phrasing.
  • Make broad significance specific and testable.
  • Convert vague Chinese academic phrases into evidence-linked English.
  • Avoid em dashes by default; use commas, parentheses, or full stops unless the user asks otherwise.

Open extra files

| File | Open when | |---|---| | [references/style-guardrails.md](references/style-guardrails.md) | Need sentence-level Science-family style, mechanics, overclaim checks, or title guardrails | | [references/section-moves.md](references/section-moves.md) | Polishing a specific section: abstract, introduction, Results, Discussion, methods, or cover letter | | [references/phrase-patterns.md](references/phrase-patterns.md) | Need reusable phrase families for gap, evidence, contrast, limitation, or implication |

Editing workflow

  1. Diagnose the main problem:

argument, section job, claim-evidence mismatch, paragraph flow, or sentence clutter.

  1. Reverse-outline the paragraph in one line: this paragraph says [message].
  2. Check whether each claim has evidence or a boundary.
  3. Rewrite for Science-family sequence:

context/gap -> claim -> evidence -> implication/boundary.

  1. Tighten sentences:
  • subject and verb appear early
  • one sentence carries one main action
  • modifiers sit near the words they modify
  • vague intensifiers are removed
  1. Return a polished version plus a short note on substantive changes.

Style targets

  • concrete nouns over abstract nominalizations
  • active verbs when agency is known
  • measured hedging where evidence is partial
  • quantitative detail when supplied
  • short signposting phrases only when they clarify logic
  • no inflated claims such as revolutionary, unprecedented, or paradigm-shifting

Output format

Default:

Polished version
[text]

What changed
- [2-5 concise notes]

Risk flags
- [unsupported claim, missing evidence, ambiguous term, or "None"]

For Chinese source text, output polished English first, then a short Chinese note explaining any meaning-preserving structural changes.

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.