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/gbencke-zinsser
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. 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/zinsser
What's inside
- Skill name
zinsser- Description
- Rewrites text using William Zinsser's "On Writing Well" method. Strips clutter, enforces clarity, brevity, simplicity, and humanity. Use when user says "zinsser this", "apply zinsser", "clean up my writing", "rewrite with zinsser", or invokes /zinsser.
- License
- MIT
- Instructions
- 167 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Zinsser Method Skill Apply William Zinsser's *On Writing Well* principles to any text. The goal is one thing: **strip every sentence to its cleanest components**. Cut what doesn't earn its place. Keep what does. ## The Four Principles Every rewrite is judged against these four: | Principle | What it means | |-----------|---------------| | **Clarity** | The reader should never wonder what you mean. One idea per sentence. | | **Simplicity** | Short word beats long word. Simple structure beats complex structure. | | **Brevity** | Most first drafts can be cut 50% without losing meaning. Cut them. | | **Humanity** | Write as a person, not a bureaucrat. Use active voice. Own the sentence. | --- ## The Rewriting Process Run these five passes in order. Do not skip passes or merge them — each targets a different layer of clutter. ### Pass 1 — Clutter Audit Read the full text. Mark every word, phrase, or sentence that fails this test: > *"Is this word doing new work that isn't done anywhere else in this sentence?"* Flag anything that is: - Redundant pairs: "each and every", "first and foremost", "true and accurate" - Throat-clearing openers: "It is important to note that…", "The fact of the matter is…", "As we can see…" - Inflated phrasing: "at this point in time" → "now", "in the event that" → "if", "due to the fact that" → "because" - Hollow qualifiers: "very", "quite", "rather", "somewhat", "pretty much", "basically", "essentially" - Zombie nouns (nominalisations): "make a decision" → "decide", "provide a recommendation" → "recommend", "conduct an investigation" → "investigate" ### Pass 2 — Word Surgery Replace long words with short ones. Apply this substitution table ruthlessly: | Cut | Keep | |-----|------| | assistance | help | | numerous | many | | facilitate | ease / help | | individual | person | | remainder | rest | | initial | first | | implement | do | | sufficient | enough | | attempt | try | | referred to as | called | | in order to | to | | utilize | use | | prioritize | rank / focus on | | leverage | use | | methodology | method | | functionality | feature / function | | on a daily basis | daily | | at the present time | now | | in close proximity | near | | has the ability to | can | | is able to | can | | due to the fact that | because | | in spite of the fact that | although | | with regard to | about | | in the near future | soon | | going forward | from now on | ### Pass 3 — Voice and Structure 1. **Active voice.** Find every passive construction. Flip it. - "The report was written by Sarah." → "Sarah wrote the report." - "Mistakes were made." → Name who made them. 2. **Cut adverbs.** Most adverbs confess that you chose the wrong verb. - "ran quickly" → "sprinted" - "said loudly" → "shouted" - "smiled happily" → "beamed" 3. **Kill adjective pileups.** One precise adjective beats three vague ones. - "a large, impressive, high-quality result" → "an exceptional result" 4. **Short sentences.** Long sentences hide weak thinking. When a sentence runs past 25 words, split it. 5. **Short paragraphs.** A wall of text intimidates. Break paragraphs at natural thought boundaries. Three to five sentences is a healthy paragraph. ### Pass 4 — Cliché Hunt Read every sentence aloud. Flag any phrase you've heard a hundred times: - "at the end of the day", "move the needle", "low-hanging fruit", "circle back", "synergy", "bandwidth" (for capacity), "deep dive", "touch base", "paradigm shift", "game-changer", "robust", "seamless" Replace each cliché with a precise, concrete description of the actual thing you mean. ### Pass 5 — Read Aloud Read the revised text aloud at normal speaking pace. - Where you stumble: the sentence is still too complex. Simplify. - Where you rush: the sentence may be doing too much. Split it. - Where you sound like a robot: inject the writer's own voice. Own the statement. - Where you sound redundant: cut the repeat. --- ## Output Format When you finish all five passes, deliver: 1. **Rewritten text** — clean, applying all five passes. 2. **Change summary** — a brief bulleted list of the main patterns you cut. Not a line-by-line explanation. Pattern-level only. 3. **Word count delta** — original vs. rewritten. Aim for ≥ 30% reduction without losing meaning. --- ## Execution Rules - Never preserve clutter out of deference to the original author's style. Style is not an excuse for fog. - Never add content. Only cut and rephrase existing ideas. - Never change the meaning. If a cut risks changing meaning, flag it explicitly: `[⚠ possible meaning change: …]` - Never revert to passive voice "for variety". Active voice is not a stylistic choice here — it is a requirement.
From gbencke/dotfiles, MIT.
More from gbencke/dotfiles
- 0.622score
token-diagnostics
gbencke
Diagnose where an AI coding agent's tokens go over the last 7 days and produce a standard summary with ranked optimisation findings.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
review-change
gbencke
Evidence-backed PR, branch, or patch review with cumulative finding reconciliation, invariant coverage, and sequential propose → challenge → judge phases.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
review-consolidate
gbencke
Run repository/lens reviews in separate processes, then consolidate validated, scope-aware full reports.
SkillAFreshness: A★ 6Claude Code +9 - 0.618score
action-items
gbencke
Manage Guilherme Bencke's personal action-item log at 00.Tasks/ACTION_ITEMS.guilherme_bencke.md.
SkillAFreshness: A★ 6Claude Code +9 - 0.618score
daily-workstream-update
gbencke
Run the daily workstream update workflow for the Obsidian vault.
SkillAFreshness: A★ 6Claude Code +9 - 0.582score
review-change
gbencke
Adversarial review of a change: a PR, a branch diff, or a patch file.
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
review-consolidate
gbencke
Review many repos under every lens — one OS process per (repo × lens), all in parallel — then consolidate every findings.json into ONE cross-repo document…
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
spotify
gbencke
Query the Spotify Web API (search tracks/artists/albums, fetch artist, album, playlist, audio features, recommendations) using SPOTIFY_CLIENT_ID /…
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
book-digest
gbencke
Research and write a 90-day digest of software-development and technology books released by O'Reilly Media, Manning, Pragmatic Bookshelf, Packt…
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
daily-digest
gbencke
Generate The Architect's Digest — a daily curated briefing of the most relevant stories in architecture, distributed systems, cloud, languages, tooling, AI…
SkillBFreshness: B★ 6Claude Code +9 - 0.579score
review-repo
gbencke
Adversarial review of an entire repository, run inline in a single process: propose → kill → judge, one lens per run.
SkillBFreshness: B★ 6Claude Code +9 - 0.532score
article-reorganization
gbencke
Reorganize a long, scattered Markdown article into a clean hierarchy of Parts and Chapters, then regenerate its PDF with Pandoc (--top-level-division=part).
SkillCFreshness: C★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 15, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/gbencke/dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gbencke
- 0.622score
token-diagnostics
gbencke
Diagnose where an AI coding agent's tokens go over the last 7 days and produce a standard summary with ranked optimisation findings.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
review-change
gbencke
Evidence-backed PR, branch, or patch review with cumulative finding reconciliation, invariant coverage, and sequential propose → challenge → judge phases.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
review-consolidate
gbencke
Run repository/lens reviews in separate processes, then consolidate validated, scope-aware full reports.
SkillAFreshness: A★ 6Claude Code +9 - 0.618score
daily-workstream-update
gbencke
Run the daily workstream update workflow for the Obsidian vault.
SkillAFreshness: A★ 6Claude Code +9 - 0.618score
action-items
gbencke
Manage Guilherme Bencke's personal action-item log at 00.Tasks/ACTION_ITEMS.guilherme_bencke.md.
SkillAFreshness: A★ 6Claude Code +9 - 0.582score
spotify
gbencke
Query the Spotify Web API (search tracks/artists/albums, fetch artist, album, playlist, audio features, recommendations) using SPOTIFY_CLIENT_ID /…
SkillBFreshness: B★ 6Claude Code +9
Cite this page
zinsser skill. Agent Mart. https://agentmart.dev/skills/gbencke-zinsser (last updated 2026-10-24)