Not in the top 1,000 by GitHub stars
Gabberflast/prose-revision-skill-ht-anthony-lee-zhang
A Claude Skill for revising draft prose — essays, papers, memos, reports — on the principle of idea flow before linguistic flow. Diagnoses structure before wording, leads with the main claim, preserves the author's voice and claim strength, and knows when to leave a good draft alone. Distinct from proofreading.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6fa28a6300f0
No earlier version was observed for comparison.
Heat
4.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
prose-revision-skill-ht-anthony-lee-zhang
When your agent uses it
Revise draft prose by designing the reader's path through the ideas the user already wants to express. The goal is clear logical movement supported by natural, elegant language: idea flow first, linguistic flow second. Prose revision is different from proofreading. Prose revision takes a relatively unpolished draft and gets the prose into good shape. Proofreading takes a close-to-done draft and catches mistakes, typos, obvious phrasing problems, and final copy-editing issues. Prose revision logically comes first.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
1,874 tokensWhen the skill is activated
Reference documents
691 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The reader's path
- Default stance
- Workflow
- What to improve
- Output style
- Worked example
Files
LICENSEasset1,068 bytesREADME.mddoc3,043 bytesSKILL.mdcore9,347 bytesSKILL.mdcore9,347 bytes
Read SKILL.md
# Prose Revision
## The reader's path
Treat revision as designing the route a reader takes through the argument. Walk the draft the way a reader would, one sentence at a time, and at each step ask: what does the reader understand now, what are they expecting or wondering because of what they just read, and does the next sentence meet that expectation or set up the right next one?
A well-revised passage gets the reader to the intended understanding without three kinds of trouble:
- **Leaps** — a step the reader cannot make from what they have been given, because a connection or premise was left implicit.
- **Detours** — material that pulls the reader off the route without paying off where they are.
- **Backtracking** — having to reread or reinterpret earlier sentences because something needed to understand them arrives only later.
Aim for the shortest path the reader can reliably follow, which is not the same as the fewest words. Sometimes the fix is cutting a detour; sometimes it is adding a bridging sentence that makes explicit a step the author skipped. Most of the work is ordering, connecting, and weighting the ideas. Wording, transitions, and rhythm come afterward, and their job is to keep the reader on the route.
Skills included
- prose-revision-skill-ht-anthony-lee-zhang
Repository facts
- License
- MIT
- Created
- Jul 14, 2026
- Last pushed
- Oct 13, 2026
- Forks
- 2
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 2 network referencesin 1 file: README.md:33
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 2 signals by file
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 2 facts
- Network access in prose of documentationREADME.md:33Low confidence
- Network access in prose of documentationREADME.md:34Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
