science-writing
Write, revise, or review scientific prose for papers, theses, conference material, research proposals, technical analysis, claims, evidence, methods, results…
Skill by nvnunes
Chalk Labs
Need help deploying science-writing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nvnunes-science-writing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/science-writing
What's inside
- Skill name
science-writing- Description
- Write, revise, or review scientific prose for papers, theses, conference material, research proposals, technical analysis, claims, evidence, methods, results, and interpretation. Use when scientific claim discipline matters, not general project docs, README files, or execution plans.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- science.md · references/
SKILL.md (first lines)
# Science Writing Use this skill for scientific and research prose. Pair with `$technical-writing` for common prose discipline, then read `references/science.md` for scientific claim, evidence, methods, and uncertainty rules. Preserve the author's technical intent. Tighten claims to match evidence, separate observation from inference, and make uncertainty or validation limits explicit. Do not add unsupported conclusions or smooth over methodological gaps. When the prose is part of a research log, pair with `$research-logging` for entry structure, provenance, and retrieval conventions.
From nvnunes/astro-agents, MIT.
More from nvnunes/astro-agents
- 0.570score
research-logging
nvnunes
Perform, record, reproduce, review, and validate investigations in project-native research logs by implementing and running scripts, retaining and analyzing…
SkillAFreshness: AClaude Code +9 - 0.561score
code-quality-review
nvnunes
Review source-code quality, architecture, ownership, contracts, lifecycle clarity, public API boundaries, tests, validation behavior, abstractions, and…
SkillAFreshness: AClaude Code +9 - 0.529score
plan-execution
nvnunes
Implement or resume work governed by an existing plan, coordinate explicitly authorized delegated Tasks for named plan files, maintain progress, perform…
SkillBFreshness: BClaude Code +9 - 0.526score
agent-surface-review
nvnunes
Review agent surfaces, AGENTS.md files, SKILL.md files, prompt files, instruction scope, workflow behavior, documentation-surface integration, and validation…
SkillBFreshness: BClaude Code +9 - 0.524score
plan-writing
nvnunes
Write, develop, shard, revise, or review implementation plans, roadmaps, migration plans, sequencing documents, and explicit delegated Task assignments.
SkillBFreshness: BClaude Code +9 - 0.521score
project-upgrade-planning
nvnunes
Assess project upgrade readiness against the shared astro-agents upgrade model and plan upgrade grouping, sequencing, documentation profile choices…
SkillBFreshness: BClaude Code +9 - 0.521score
skill-md-writing
nvnunes
Write, revise, or review SKILL.md files and skill packages, including frontmatter descriptions, selection boundaries, progressive-disclosure references…
SkillBFreshness: BClaude Code +9 - 0.521score
documentation-surface-review
nvnunes
Review documentation surfaces, documentation surface profiles, source-of-truth docs, README scope, public Python docs, private/default docs, and documentation…
SkillBFreshness: BClaude Code +9 - 0.521score
python-code-writing
nvnunes
Write, edit, or refactor Python source code, including APIs, lifecycle clarity, contracts, tests, docstrings, package structure, and project-local Python…
SkillBFreshness: BClaude Code +9 - 0.479score
pubify-authoring
nvnunes
Work on pubify-pubs and pubify-ppt publication and presentation workflows, including pubs and ppt CLI behavior, pubify.yaml workspaces, configured publication…
SkillCFreshness: CClaude Code +9 - 0.474score
technical-writing
nvnunes
Write, revise, or review general technical prose using shared discipline for clarity, structure, audience fit, scope control, and restrained style.
SkillCFreshness: CClaude Code +9 - 0.474score
readme-writing
nvnunes
Write, revise, or review README.md files, including project overviews, folder-level README files, setup orientation, navigation, and entrypoint documentation.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 30, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/nvnunes/astro-agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from nvnunes
- 0.570score
research-logging
nvnunes
Perform, record, reproduce, review, and validate investigations in project-native research logs by implementing and running scripts, retaining and analyzing…
SkillAFreshness: AClaude Code +9 - 0.561score
code-quality-review
nvnunes
Review source-code quality, architecture, ownership, contracts, lifecycle clarity, public API boundaries, tests, validation behavior, abstractions, and…
SkillAFreshness: AClaude Code +9 - 0.529score
plan-execution
nvnunes
Implement or resume work governed by an existing plan, coordinate explicitly authorized delegated Tasks for named plan files, maintain progress, perform…
SkillBFreshness: BClaude Code +9 - 0.526score
agent-surface-review
nvnunes
Review agent surfaces, AGENTS.md files, SKILL.md files, prompt files, instruction scope, workflow behavior, documentation-surface integration, and validation…
SkillBFreshness: BClaude Code +9 - 0.524score
plan-writing
nvnunes
Write, develop, shard, revise, or review implementation plans, roadmaps, migration plans, sequencing documents, and explicit delegated Task assignments.
SkillBFreshness: BClaude Code +9 - 0.521score
project-upgrade-planning
nvnunes
Assess project upgrade readiness against the shared astro-agents upgrade model and plan upgrade grouping, sequencing, documentation profile choices…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get science-writing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
science-writing skill. Agent Mart. https://agentmart.dev/skills/nvnunes-science-writing (last updated 2026-10-24)