holistic-writing
Author, substantially revise, or editorially review whole prose artifacts, including reports, essays, prompts, instructions, skills, and documentation.
Skill by jyn514
Chalk Labs
Need help deploying holistic-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/jyn514-holistic-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: design, 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 1, 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/holistic-writing
What's inside
- Skill name
holistic-writing- Description
- Author, substantially revise, or editorially review whole prose artifacts, including reports, essays, prompts, instructions, skills, and documentation. Use for selection, explanatory development, causal relationships, diction, rhythm, voice, factual fidelity, and the complete reading experience, including after substantial drafting or rewriting. Specialized owners retain authority over substance and behavior. Not for documentation placement or tree restructuring, design selection, human-owned product briefs, or bounded local polishing; use the relevant owner or tighten-prose.
- License
- Unlicense
- Instructions
- 135 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- consolidation.md · references/
- reading-examples.md · references/
SKILL.md (first lines)
# Holistic writing Write for readers without the originating conversation, investigation, or design session. Establish the context for standalone writing or whole-artifact review, then use the shared editorial pass. ## Scope and authority Specialized owners decide the artifact’s substance; an editorial pass does not expand permission to change it. A review request does not authorize prose edits. For review-only work, report findings, evidence, consequences, and the smallest useful corrections. For authoring with no named artifact, establish the intended reader, purpose, and deliverable before drafting. Ask when missing context would materially change the result rather than inventing its audience or authority. When a dedicated skill owns the requested writing or review, start there rather than running this workflow separately. Specialized owners link directly to the [shared editorial pass](references/editorial-pass.md) under their own invocation conditions. An editorial-only request can start here when the artifact's dedicated skill does not cover that review. Reuse established decisions rather than restarting their workflows. For documentation-specific reader tasks, forms, prerequisites, commands, links, and workflow checks, use [Documentation](references/documentation.md). For placement alone, use [Documentation placement](../references/documentation-placement.md); a small addition or new heading does not require this whole-artifact workflow. Use adjacent owners only for their tasks, not as compulsory stages of this pass: - `readme-writing` owns introductory README writing and review, not every file named README. - `reorganize-docs` owns existing documentation trees, page splits, renames, consolidation, and navigation. - `new-tool-development` owns its tool lifecycle and human-authored product briefs. Agents may review those briefs and add only the TODO comments it permits, not write or rewrite brief prose. - `requirements-definition` owns requirements authoring from an approved product brief. - `human-review-packets` owns selection and framing of human decision questions and approval handoffs. - [Spec review](../spec-review/SKILL.md) audits specification contracts for consistency, traceability, unsupported restrictions, and stage-appropriate completeness. - `skill-authoring` owns skill behavior, discovery, and procedure; this skill owns written presentation without silently changing those decisions. - `typst` owns Typst syntax; use it when the artifact needs that markup, not for every prose review. - `tighten-prose` owns bounded sentence- and paragraph-level polishing within an established explanation. If an owner is unavailable, preserve its boundaries, state the limitation, and do not claim that its specialized review occurred. ## 1. Establish the artifact and context For direct authoring or review, establish any missing reader, purpose, requirements, and factual evidence. Use the brief, relevant entry points, authoritative inputs, and representative uses. For creation, inspect the material the new artifact must explain and any established destination or form. If another procedure has already established this context, reuse it. Do not reconstruct the investigation or reopen settled design decisions. ## 2. Use the shared editorial pass Read and follow the [editorial pass](references/editorial-pass.md) with the artifact, established context, and authoring or review-only authority. It covers explanatory development, reading experience, factual fidelity, revision, and validation through completion. Specialized owners retain authority over substance and behavior; this entry point does not start their workflows as compulsory editorial stages.
From jyn514/dotfiles, Unlicense.
More from jyn514/dotfiles
- 0.570score
architecture-design
jyn514
Design, assess, or choose a bounded software architecture: subsystem ownership, dependency direction, data/effect and lifecycle contracts, API shape…
SkillAFreshness: AClaude Code +9 - 0.570score
creative-inquiry
jyn514
Explore a task's purpose, assumptions, and unexpected connections to discover possible approaches.
SkillAFreshness: AClaude Code +9 - 0.570score
delegation
jyn514
Divide and coordinate work among agents.
SkillAFreshness: AClaude Code +9 - 0.570score
mutation-testing
jyn514
Set up, scope, run, and analyze mutation-testing campaigns using project-compatible tools or bounded hand-selected mutations.
SkillAFreshness: AClaude Code +9 - 0.565score
implementation-plan
jyn514
Create or review a concrete, repository-specific implementation plan for a selected change.
SkillAFreshness: AClaude Code +9 - 0.565score
new-tool-development
jyn514
Orchestrate lifecycle and stage gates for a newly introduced independently invoked tool, CLI, service, or reusable executable subsystem.
SkillAFreshness: AClaude Code +9 - 0.565score
autonomous-work
jyn514
Pursue an explicitly requested autonomous or unattended task, or an active user-authorized tracked goal, through verified completion.
SkillAFreshness: AClaude Code +9 - 0.565score
goal-to-issue-graph
jyn514
Turn a brief or broad goal into an actionable issue graph with observable root acceptance, bounded tickets, justified dependencies, and integration checks.
SkillAFreshness: AClaude Code +9 - 0.565score
issue-reporting
jyn514
Draft or revise upstream bug reports, support questions, and design discussions for maintainers.
SkillAFreshness: AClaude Code +9 - 0.565score
jj-workflow
jyn514
Use when a task involves inspecting file or revision history, establishing change provenance or ownership, comparing revisions, or shaping history through…
SkillAFreshness: AClaude Code +9 - 0.565score
opportunity-scan
jyn514
Find the highest-leverage project improvement without anchoring on recent changes, current work, churn, or already-completed corrective campaigns.
SkillAFreshness: AClaude Code +9 - 0.565score
performance-investigation
jyn514
Diagnose unexpected execution delay, hangs, observed contention, and quota-constrained operations, or perform explicitly requested profiling and benchmarking.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 4
- Last commit (this folder)
- Oct 23, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Unlicense
- Repository
- github.com/jyn514/dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jyn514
- 0.570score
creative-inquiry
jyn514
Explore a task's purpose, assumptions, and unexpected connections to discover possible approaches.
SkillAFreshness: AClaude Code +9 - 0.570score
architecture-design
jyn514
Design, assess, or choose a bounded software architecture: subsystem ownership, dependency direction, data/effect and lifecycle contracts, API shape…
SkillAFreshness: AClaude Code +9 - 0.570score
mutation-testing
jyn514
Set up, scope, run, and analyze mutation-testing campaigns using project-compatible tools or bounded hand-selected mutations.
SkillAFreshness: AClaude Code +9 - 0.570score
delegation
jyn514
Divide and coordinate work among agents.
SkillAFreshness: AClaude Code +9 - 0.565score
autonomous-work
jyn514
Pursue an explicitly requested autonomous or unattended task, or an active user-authorized tracked goal, through verified completion.
SkillAFreshness: AClaude Code +9 - 0.565score
new-tool-development
jyn514
Orchestrate lifecycle and stage gates for a newly introduced independently invoked tool, CLI, service, or reusable executable subsystem.
SkillAFreshness: AClaude 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 holistic-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
holistic-writing skill. Agent Mart. https://agentmart.dev/skills/jyn514-holistic-writing (last updated 2026-10-24)