plainspoken-writing
Plainspoken prose pass for drafted or revised text: make it specific, direct, evidence-grounded, and proportionate.
Skill by lucavb
Chalk Labs
Need help deploying plainspoken-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/lucavb-plainspoken-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
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 and code. Checked Nov 2, 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/plainspoken-writing
What's inside
- Skill name
plainspoken-writing- Description
- Plainspoken prose pass for drafted or revised text: make it specific, direct, evidence-grounded, and proportionate.
- License
- MIT
- Instructions
- 129 lines in SKILL.md · view on GitHub
Files (3)
- CITATIONS.md
- README.md
- SKILL.md
SKILL.md (first lines)
# Plainspoken writing Use this pass for prose. The leading word is **plainspoken**: specific facts, direct syntax, proportionate emphasis, and evidence-based authority. The warning signs below are diagnostic. Fix the underlying defect; retain a flagged word when the context gives it precise work. ## Pass ### 1. Ground the content For each factual or interpretive claim: - Anchor every claim in known facts or supplied sources. - Name the person, source, or group behind an opinion. Match the breadth of the attribution to the evidence; one critic is not "critics" or "observers." - Separate a source's statement from your inference. Ground analysis in facts rather than declaring what a fact highlights, reflects, symbolizes, ensures, or contributes to. - Describe the subject before assessing its importance. Include significance, influence, legacy, notability, and media attention only when concrete evidence makes them part of the subject. - Replace generic claims about broader trends, debates, landscapes, cultural meaning, ecological importance, or ongoing efforts with the relevant fact. - State uncertainty precisely. When information is missing, name the exact gap and omit speculation about privacy, scarcity, documentation, or likelihood. **Done when:** every claim has a known basis, every opinion has an exact owner, and no sentence turns missing evidence into a story. ### 2. Make the prose direct - Prefer `is`, `are`, and `has` when they carry the same meaning as `serves as`, `stands as`, `marks`, `represents`, `boasts`, `features`, or `offers`. - Prefer the ordinary precise verb: `wrote`, `used`, `moved`, `tried`, or `died` when a grander synonym adds no meaning. - Reuse the right term. Stable terminology beats synonym rotation. - Let the facts set the tone. Replace promotional, travel-guide, press-release, and ceremonial language with concrete description. - Use contrast for a real contrast. Flatten reflexive patterns such as "not only X but also Y," "not X but Y," and "X rather than Y" when they merely dramatize the point. - Use the number of examples or modifiers the content requires. Break a forced rule of three. - Keep sentence openings and endings functional. Replace trailing `-ing` clauses that append unsupported importance or impact. - Match the requested register and variety of English. Preserve the author's established voice where one exists; keep human texture natural rather than manufactured. Scan for clusters of stock diction, then rewrite the thought rather than thesaurus-swapping the token: `Additionally`, `align with`, `bolstered`, `crucial`, `deep dive`, `delve`, `emphasizing`, `enduring`, `enhance`, `fostering`, `garner`, `highlight`, `interplay`, `intricate`, `key`, `landscape`, `meticulous`, `pivotal`, `robust`, `showcase`, `tapestry`, `testament`, `underscore`, `valuable`, `vibrant`, `groundbreaking`, `renowned`, `rich`, `profound`, `nestled`, `in the heart of`, `commitment to`, and `diverse array`. **Done when:** the shortest accurate construction wins, repeated terms remain stable, and emphasis comes from facts rather than stock cadence or diction. ### 3. Give the content its natural shape - Organize around the reader's questions instead of a generic article outline. - Add a heading only when it helps navigation. Use sentence case, preserve heading levels, and give each section content of its own. - Let the surrounding format supply the document title rather than repeating it as a first heading. - Use paragraphs by default. Use lists for actual sets or sequences and tables for comparisons that become clearer in rows and columns. - Use the target venue's markup and keep Markdown, raw formatting tokens, and unsupported syntax out of other output formats. - Use bold sparingly for functional emphasis. Use emoji only when the requested medium calls for them. - Use punctuation for syntax, not punch. Replace formulaic em dashes with a comma, colon, parentheses, or a new sentence as appropriate. - Follow the venue's quote and apostrophe convention consistently. Curly quotes are not a defect by themselves. - Keep decorative section dividers, empty parent headings, repetitive `**Label:** explanation` lists, and canned sections such as "Challenges and future prospects" or "Awards and recognition" only when the material genuinely requires them. - End on the last substantive point. A generic summary, optimistic outlook, balanced "despite these challenges" paragraph, or claim about future relevance needs concrete content to earn a place. **Done when:** every structural and formatting choice carries information or improves navigation. ### 4. Remove chatbot residue - Deliver the requested prose directly: greetings, praise, "of course," "here is," "I hope this helps," offers to do more, and operator instructions belong outside the reader-facing text. - Let the text demonstrate neutrality, completeness, sourcing, compliance, clarity, or improvement rather than asserting those qualities. - Replace knowledge-cutoff disclaimers and references to available search results with a precise limitation that matters to the reader, if one does. - Resolve every template token, placeholder, dummy date, example URL, bracketed instruction, and drafting note before delivery. - Keep headings and summaries proportional to the message. A short answer earns a miniature report structure only when the content needs it. **Done when:** the output contains only reader-facing content and no trace of the conversation, prompt, drafting scaffold, or self-certification. ### 5. Audit sources When the prose uses citations, load [`CITATIONS.md`](CITATIONS.md) and complete its source audit. **Done when:** the citation audit's completion criterion in `CITATIONS.md` is true. ### 6. Cross-check
From lucavb/skills, MIT.
More from lucavb/skills
- 0.604score
review-tribunal
lucavb
Review tribunal for pull requests or local Git diffs: intake, review-core blind critics (including alternatives), tribunal, adversarial validation, then local…
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
scrum-next
lucavb
Scrum board next-work triage.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
review-core
lucavb
Shared adversarial review engine: blind parallel critics (including alternatives), tribunal adjudication, and adversarial re-validation.
SkillAFreshness: A★ 3Claude Code +9 - 0.569score
refining-jira-tickets
lucavb
Pre-scrum refinement of Jira stories for engineering readiness.
SkillBFreshness: B★ 3Claude Code +9 - 0.569score
atlassian-jira-adf-formatting
lucavb
Round-trip Jira story descriptions via Atlassian MCP ADF — fetch full doc, edit in files, validate, file-backed editJiraIssue.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
gh-fetch
lucavb
GitHub fetch — gh CLI for GitHub URLs; checkout when multiple file accesses are foreseen.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
closing-ritual
lucavb
Closing ritual — surface doubts, blind spots, and unverified claims before work is accepted.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
conversation-handoff
lucavb
Summarize the current conversation into a copy-pasteable handoff message for a fresh chat.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
ticket-to-pr-pipeline
lucavb
ticket-to-pr-pipeline: Jira ticket through plan, build, review-core, and PR in one continuous run.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
writing-commit-messages
lucavb
Required before every git commit.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
angular
lucavb
Angular zoneless conventions — signals, toSignal, shells, encapsulated styles.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
discover-before-planning
lucavb
Do discovery during planning — explore the codebase and close open questions before presenting a plan.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 19, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lucavb/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lucavb
- 0.604score
review-tribunal
lucavb
Review tribunal for pull requests or local Git diffs: intake, review-core blind critics (including alternatives), tribunal, adversarial validation, then local…
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
scrum-next
lucavb
Scrum board next-work triage.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
review-core
lucavb
Shared adversarial review engine: blind parallel critics (including alternatives), tribunal adjudication, and adversarial re-validation.
SkillAFreshness: A★ 3Claude Code +9 - 0.569score
atlassian-jira-adf-formatting
lucavb
Round-trip Jira story descriptions via Atlassian MCP ADF — fetch full doc, edit in files, validate, file-backed editJiraIssue.
SkillBFreshness: B★ 3Claude Code +9 - 0.569score
refining-jira-tickets
lucavb
Pre-scrum refinement of Jira stories for engineering readiness.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
conversation-handoff
lucavb
Summarize the current conversation into a copy-pasteable handoff message for a fresh chat.
SkillBFreshness: B★ 3Claude 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 plainspoken-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
plainspoken-writing skill. Agent Mart. https://agentmart.dev/skills/lucavb-plainspoken-writing (last updated 2026-10-24)