New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Defensive Writing Editor

by lennney in lennney/stop-that-shit

Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

MITAuto-check passedWriting & Content

Install Defensive Writing Editor

skills CLI
$ npx skills add lennney/stop-that-shit --skill stss -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lennney/stop-that-shit stss --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lennney/stop-that-shit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/stss .claude/skills/stss && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
stss
GitHub stars
2.5k
Used in
1 other repo
Token cost
~1.2k tokens
SKILL.md length
629 words
Files
3 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

  • Works in 3 steps: Who will use this sentence? → What understanding or decision does it… → What becomes false or misleading if it…
  • Tightening a project proposal that is buried in disclaimers
  • SKILL.md covers Stay in scope, Select the mode, Record the claims and Test each defensive sentence, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

You choose a mode. Rewrite returns a tighter version of your text and is the default when you give none, while audit lists the defensive spans with the smallest useful fix for each and does not rewrite the whole piece. Before editing, the agent builds a private ledger of the claims in your material: facts and numbers, named actors and sources, evidence strength, stated uncertainty and scope, and the action the reader is asked to take. The ledger stays hidden unless you ask, and the edit may not add facts, sources, numbers, certainty or causality.

Each defensive sentence goes through a three-question test: who uses it, what decision it changes, and what becomes false or misleading without it. The verdict is DROP for sentences that only narrate diligence or apologize, CALIBRATE to turn stacked hedges into one precise limitation, RELOCATE to move an important caveat next to the claim it affects, or KEEP for legal, safety, financial, methodological, contractual or scope limits. The skill stays narrow: it does not judge whether text sounds machine-written or tidy unrelated prose, and text that is already direct comes back unchanged.

When your agent uses it

  • Tightening a project proposal that is buried in disclaimers
  • Auditing an executive summary for stacked hedging
  • Rewriting a research contribution statement so it leads with the claim
  • Checking a plan for sentences that only narrate diligence

Example prompts

  • “Rewrite this grant proposal summary so it leads with the request and drops the apologies.”
  • “Audit the executive summary in ./docs/launch-plan.md for defensive wording and tell me what to keep.”
  • “Cut the stacked hedges in this research contribution paragraph down to one precise limitation.”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Who will use this sentence?
  2. What understanding or decision does it change for this reader?
  3. What becomes false or misleading if it is removed?

What it can do on your machine

Read from SKILL.md and the folder at commit 694bbd5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Defensive Writing Editor loads about 1.2k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 629 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lennney/stop-that-shit at commit 694bbd5, republished under its MIT licence (© lennney). 629 words, ~1,171 tokens.

Download SKILL.mdSave it as .claude/skills/stss/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
stss
description
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve meaningful limits; do not perform general style cleanup or ordinary code work.
license
MIT

Stop That Shit Slop

别再废话。

Make the point without writing for an imaginary critic. Preserve limitations that change what the reader understands or decides.

Stay in scope

Reduce defensive wording in reader-facing prose, including captions and introductions. Do not classify text as AI-written, promise to remove an "AI voice," humanize unrelated prose, or perform a general style cleanup.

Judge sentences by their reader use, including sentences introduced during drafting. A request to describe a project's evolution calls for that history; it does not by itself call for an account of how the article's sources were checked.

Select the mode

  • rewrite: Return a tighter version. This is the default when the user provides text without a mode.
  • audit: Identify defensive writing and propose the smallest useful fix. Do not rewrite the full text.

Follow an explicit mode. Infer the mode from the request only when none is given.

For a drafting request, create the requested artifact from the supplied material and apply the rewrite checks before returning it.

Record the claims

Before editing, build a private Claim Ledger from the supplied material:

  • facts and numbers;
  • named actors and sources;
  • evidence strength;
  • stated uncertainty and scope;
  • what the reader needs to understand or do.

Do not print the ledger unless the user asks for it. Do not add facts, sources, numbers, certainty, or causality.

Keeping facts accurate does not require printing every editorial note. Keep verification logs and source-checking process in working notes unless the reader needs them. Preserve useful attribution, actual methods, and conditions that affect a claim.

Test each defensive sentence

Apply the Sentence Consumer Test:

  1. Who will use this sentence?
  2. What understanding or decision does it change for this reader?
  3. What becomes false or misleading if it is removed?

Choose one action:

  • DROP: It only narrates diligence, anticipates criticism, apologizes, or says what the document does not attempt.
  • CALIBRATE: It contains real uncertainty but uses stacked hedges. Keep one precise limitation.
  • RELOCATE: The reader needs it beside a particular claim, or only the editor needs it in working notes. Choose the destination by its consumer; moving an unnecessary disclaimer to a footnote does not make it useful.
  • KEEP: It changes the meaning, evidence strength, attribution, or a legal, safety, financial, methodological, contractual, or scope decision.

Do not decide from a keyword alone. The same phrase can be waste in one context and necessary in another.

Show full SKILL.md (230 more words)Show less

Rewrite

  1. Lead with the requested subject, claim, decision, or proposal.
  2. State scope positively: say what the work covers.
  3. Replace stacked hedges with one evidence-matched qualifier.
  4. Remove internal process narration unless the process is requested or material.
  5. Put a necessary limitation beside the claim it limits.
  6. Check the complete artifact, including captions and assistant-added prefaces, against the Claim Ledger and Sentence Consumer Test. Do not reintroduce dropped defenses in the delivery note.

Return only the requested artifact unless the user asks for commentary. If the text is already direct and faithful, return it unchanged.

Audit

Report only actionable findings. For each finding, give:

  • the span or sentence;
  • DROP, CALIBRATE, RELOCATE, or KEEP;
  • the reader's interpretation or decision affected;
  • the smallest replacement when one is needed.

Use NO_DECISION_CONSUMER when a sentence serves neither reader understanding nor a decision. If there are no actionable findings, say so and stop.

Check the claim diff

Before returning the result, verify:

  • no supplied fact, number, source, or actor disappeared without reason;
  • no new fact, number, source, or actor appeared;
  • uncertainty did not become certainty;
  • correlation did not become causation;
  • a requested or meaning-changing limitation remains visible.

Run one claim-preserving pass. Do not add a score, a probability that text is AI-written, a change diary, or repeated self-review.

Read references/examples.md when the boundary is ambiguous or the user asks for examples.

© lennney, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/stss of lennney/stop-that-shit.

  • SKILL.md
  • agents/openai.yaml
  • references/examples.md

Open the folder on GitHubat commit 694bbd5

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in lennney/stop-that-shit, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Defensive Writing Editor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Defensive Writing Editor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Defensive Writing Editor this skilllennney/stop-that-shit2.5k1 repos~1.2kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
Chinese Technical Writingleter/zh-tech-writing334—~656Automated safety check: PassMIT
Oil Tone Chinese Writing Styleoil-oil/oil-tone230—~517Automated safety check: PassMIT
ISO 24495-1 Plain LanguageGaZmagik/iso-244951891 repos~2kAutomated safety check: PassMIT
Declaudingoaustegard/claude-skills150—~5.2kAutomated safety check: PassMIT

Similar skills

  • Natural Japanese Business Writing

    coji/natural-japanese

    Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Chinese Technical Writing

    leter/zh-tech-writing

    Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.

    334 GitHub stars~656 tokensUpdated 14 days ago
    Writing & ContentAuto-check passed

  • Oil Tone Chinese Writing Style

    oil-oil/oil-tone

    Chinese-language style guide that keeps articles, scripts and product copy natural, readable and fact-grounded, with a lint script that flags tired phrasing.

    230 GitHub stars~517 tokensUpdated 15 days ago
    Writing & ContentAuto-check passed

  • ISO 24495-1 Plain Language

    GaZmagik/iso-24495

    Makes the agent write every user-facing reply by the four plain-language principles of ISO 24495-1:2023: relevant, findable, understandable and usable.

    189 GitHub starsUsed in 1 repo~2k tokens
    Writing & ContentAuto-check passed

  • Declauding

    oaustegard/claude-skills

    Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts.

    150 GitHub stars~5.2k tokensUpdated today
    Writing & ContentAuto-check passed

  • Simple English Rewriter

    vinta/hal-9000

    Rewrites docs, READMEs, issues, comments or UI text in plain Global English that translates well and still sounds native, keeping every fact intact.

    138 GitHub stars~1.1k tokensUpdated today
    Writing & ContentAuto-check passed

More from lennney/stop-that-shit

  • Scope Creep Guard

    lennney/stop-that-shit

    Keeps an agent focused on the requested work by applying a five-step ladder that checks for direct solutions, real gaps and speculative defenses before adding anything.

    2.5k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

Categories

Questions about Defensive Writing Editor

What does Defensive Writing Editor do?

Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision. You choose a mode. Rewrite returns a tighter version of your text and is the default when you give none, while audit lists the defensive spans with the smallest useful fix for each and does not rewrite the whole piece.

When should I use Defensive Writing Editor?

Defensive Writing Editor fits situations like: tightening a project proposal that is buried in disclaimers; auditing an executive summary for stacked hedging; rewriting a research contribution statement so it leads with the claim; checking a plan for sentences that only narrate diligence.

How do I install Defensive Writing Editor in Claude Code?

Run `npx skills add lennney/stop-that-shit --skill stss -a claude-code`. Or copy the skill folder (skills/stss in lennney/stop-that-shit) into .claude/skills/stss in your project. Claude Code loads it when a task matches its description.

How do I install Defensive Writing Editor in Codex?

Run `npx skills add lennney/stop-that-shit --skill stss -a codex`. Or copy the skill folder (skills/stss in lennney/stop-that-shit) into .agents/skills/stss in your project. Codex loads it when a task matches its description.

Can I use Defensive Writing Editor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lennney/stop-that-shit --skill stss -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stss, .gemini/skills/stss, .github/skills/stss and .opencode/skills/stss in your project.

What does Defensive Writing Editor need to run?

SKILL.md names no scripts, command-line tools or credentials: Defensive Writing Editor is instructions for the agent only.

Does Defensive Writing Editor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Defensive Writing Editor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Defensive Writing Editor use?

Defensive Writing Editor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Defensive Writing Editor use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Defensive Writing Editor?

Skills that share tags, products or a category with Defensive Writing Editor: Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars), Chinese Technical Writing (leter/zh-tech-writing, 334 stars), Oil Tone Chinese Writing Style (oil-oil/oil-tone, 230 stars) and ISO 24495-1 Plain Language (GaZmagik/iso-24495, 189 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Defensive Writing Editor?

lennney (a GitHub user) maintains it in lennney/stop-that-shit, which has 2,506 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.

Source: lennney/stop-that-shit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.