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/iamthenop-prose-discipline
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: agent-building
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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/prose-discipline
What's inside
- Skill name
prose-discipline- Description
- Always-required standard wherever prose is used. Governs human legibility and semantic drift in documentation, instructions, reports, comments, reviews, and agent interaction. Use whenever prose is read, written, reviewed, or transformed.
- License
- MIT
- Metadata
- skill-type: standard
- Instructions
- 252 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- complexity-settings.md · references/
- check-prose.py · scripts/
- check-readability.py · scripts/
- source.py · scripts/
SKILL.md (first lines)
# Prose style Prose governs what humans read; code governs what machines run. They need different disciplines. A correct but unreadable document has failed its reader. ## Applicability This standard is always required wherever prose is used. It applies to prose in governing text, documentation, instructions, workorders, reports, comments, reviews, and agent interaction, regardless of profile, deliverable, workflow, or user interaction. Human legibility and drift control are the same reliability concern. LLMs operate through human language; if prose is difficult for a human to interpret reliably, treat the model input or output as defective. ## Summary This skill sets the minimum prose quality bar. Clarity comes before compression, and the reader should understand on one pass. Precision limits semantic drift for humans and language models. ## Priority order When principles conflict, resolve in this order: 1. **Clarity** — the reader understands on one pass 2. **Accessibility** — concepts are introduced before being compressed 3. **Accuracy** — the content is structurally correct 4. **Compression** — no word is wasted Clarity and compression frequently conflict. Clarity wins. ## Voice Prose governed by this standard is: * calm — no urgency, no alarm, no hype * authoritative — states facts, not opinions dressed as facts * understated — the structure carries the argument; the prose does not push it * pragmatic — oriented toward consequence, not description for its own sake Authority is earned through clarity. It is not asserted through volume, repetition, or confident-sounding language. ## Accessibility The reader should not need to decode meaning. Every sentence should be clear on first contact. * introduce a concept before compressing it * reduce cognitive load — if two readings of a sentence are possible, eliminate one * do not use ambiguity as a stylistic device * prefer explicit nouns over pronouns unless the referent is unambiguous * the reader should feel guided, not tested ## Sentence structure * short declarative sentences for emphasis — use selectively * explanation before compression — never the reverse * one conceptual move per paragraph * paragraphs of one to three sentences as the default * one-line paragraphs reserved for structural conclusions, not for every point * avoid long runs of one-line paragraphs — they create pressure without context ## Section flow Each section completes one conceptual cycle: 1. observation — what is true 2. explanation — why it is true or how it works 3. operational implication — what follows from it 4. structural resolution — the conclusion, stated plainly A section that stops at observation or explanation is unfinished. A section that opens with its conclusion before establishing the context is unreadable. ## Structural lines A structural line is a compressed statement that resolves a section's argument. It must: * be preceded by sufficient explanation * resolve a clearly established idea * feel inevitable given the preceding context If a structural line can be removed without loss of meaning, remove it. If it cannot be understood without re-reading the section, expand the section first. One structural line per section is the norm. Two is the maximum. ## Subject discipline Keep the system, process, or document as the primary subject of each sentence. Avoid unnamed human actors when the action can be expressed through the mechanism itself. Preferred: ``` The workorder authorizes the change. The validator rejects the file. The boundary holds. ``` Avoid: ``` Someone needs to authorize the change. You should run the validator. They held the boundary.
From iamthenop/infurnet-skills, MIT.
More from iamthenop/infurnet-skills
- 0.563score
purrification
iamthenop
Apply sparse feline phonetic slips to creative dialogue or monologues, using cross-language IPA similarity and salience-based spacing.
SkillAFreshness: AClaude Code +9 - 0.529score
api-docs
iamthenop
Author and structure API and interface documentation for HTTP APIs, internal RPC surfaces, and inbound webhooks.
SkillBFreshness: BClaude Code +9 - 0.529score
brand-designer
iamthenop
Author and structure brand identity documentation — brand books, style guides, logo/color/type systems, voice and slogans, and platform-specific…
SkillBFreshness: BClaude Code +9 - 0.529score
schema-design
iamthenop
Database schema design discipline — initialization strata, stratum boundaries, SQL design and comments, privileges, writers, seeds, and schema validation.
SkillBFreshness: BClaude Code +9 - 0.529score
code-comments
iamthenop
Decide whether a source comment belongs, what it may contain, and where displaced information goes instead.
SkillBFreshness: BClaude Code +9 - 0.529score
deploy-standard
iamthenop
Container build, distribution, and release promotion discipline.
SkillBFreshness: BClaude Code +9 - 0.529score
doc-comment-tags
iamthenop
Write structured documentation comments using the custom architectural tag system (@layer, @owner, @boundary, @authority, @privacy, @temporary, and related…
SkillBFreshness: BClaude Code +9 - 0.529score
java-standard
iamthenop
Java implementation rules for source layout, test placement, and documentation.
SkillBFreshness: BClaude Code +9 - 0.529score
plan-review
iamthenop
Review an agent's proposed work plan before execution begins.
SkillBFreshness: BClaude Code +9 - 0.529score
project-bindings
iamthenop
Author and maintain the repository bindings file — the single mutable declaration of project-specific values that standards dereference.
SkillBFreshness: BClaude Code +9 - 0.526score
builder
iamthenop
Assigned Builder profile.
SkillBFreshness: BClaude Code +9 - 0.526score
designer
iamthenop
Assigned Designer profile.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Sep 6, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/iamthenop/infurnet-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from iamthenop
- 0.563score
purrification
iamthenop
Apply sparse feline phonetic slips to creative dialogue or monologues, using cross-language IPA similarity and salience-based spacing.
SkillAFreshness: AClaude Code +9 - 0.529score
api-docs
iamthenop
Author and structure API and interface documentation for HTTP APIs, internal RPC surfaces, and inbound webhooks.
SkillBFreshness: BClaude Code +9 - 0.529score
brand-designer
iamthenop
Author and structure brand identity documentation — brand books, style guides, logo/color/type systems, voice and slogans, and platform-specific…
SkillBFreshness: BClaude Code +9 - 0.529score
code-comments
iamthenop
Decide whether a source comment belongs, what it may contain, and where displaced information goes instead.
SkillBFreshness: BClaude Code +9 - 0.529score
deploy-standard
iamthenop
Container build, distribution, and release promotion discipline.
SkillBFreshness: BClaude Code +9 - 0.529score
doc-comment-tags
iamthenop
Write structured documentation comments using the custom architectural tag system (@layer, @owner, @boundary, @authority, @privacy, @temporary, and related…
SkillBFreshness: BClaude Code +9
Cite this page
prose-discipline skill. Agent Mart. https://agentmart.dev/skills/iamthenop-prose-discipline (last updated 2026-10-24)