Unslop File
sickn33/agentic-awesome-skills
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly.
Installs a set of rules into AGENTS.md that strips filler, hedging and padded closings from your agent's replies, in English and Chinese.
Install Talk Normal
$ npx skills add hexiecs/talk-normal --skill talk-normal -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hexiecs/talk-normal talk-normal --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hexiecs/talk-normal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill .claude/skills/talk-normal && rm -rf skills-srcUse ~/.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/
Install the "talk-normal" agent skill from https://github.com/hexiecs/talk-normal/tree/main/skill into .claude/skills/talk-normal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talk-normal", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hexiecs/talk-normal/tree/main/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hexiecs/talk-normal --skill talk-normal -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hexiecs/talk-normal talk-normal --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hexiecs/talk-normal.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill .agents/skills/talk-normal && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "talk-normal" agent skill from https://github.com/hexiecs/talk-normal/tree/main/skill into .agents/skills/talk-normal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talk-normal", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hexiecs/talk-normal --skill talk-normal -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hexiecs/talk-normal talk-normal --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hexiecs/talk-normal.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill .cursor/skills/talk-normal && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "talk-normal" agent skill from https://github.com/hexiecs/talk-normal/tree/main/skill into .cursor/skills/talk-normal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talk-normal", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hexiecs/talk-normal.git --path skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hexiecs/talk-normal --skill talk-normal -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hexiecs/talk-normal talk-normal --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hexiecs/talk-normal.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill .gemini/skills/talk-normal && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "talk-normal" agent skill from https://github.com/hexiecs/talk-normal/tree/main/skill into .gemini/skills/talk-normal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talk-normal", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hexiecs/talk-normal talk-normalInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hexiecs/talk-normal --skill talk-normal -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hexiecs/talk-normal.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill .github/skills/talk-normal && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "talk-normal" agent skill from https://github.com/hexiecs/talk-normal/tree/main/skill into .github/skills/talk-normal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talk-normal", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hexiecs/talk-normal --skill talk-normal -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hexiecs/talk-normal talk-normal --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hexiecs/talk-normal.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill .opencode/skills/talk-normal && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "talk-normal" agent skill from https://github.com/hexiecs/talk-normal/tree/main/skill into .opencode/skills/talk-normal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talk-normal", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
talk-normal- GitHub stars
- 1.9k
- Token cost
- ~931 tokens
- SKILL.md length
- 442 words
- Files
- 4
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Installs a set of rules into AGENTS.md that strips filler, hedging and padded closings from your agent's replies, in English and Chinese.
- Making an agent's answers shorter and less corporate in tone
- SKILL.md covers What this skill does, How to run, What gets installed and Updating to the latest rules, plus 4 more sections
- Runs Shell scripts from its folder; calls bash
- Removing stock openers and closers such as offers of further help
What it does
talk-normal is a one-time installer, not a per-turn workflow. Running `bash install.sh` copies the rules from prompt.md into the workspace's AGENTS.md between BEGIN and END markers, so every later reply from the agent follows them. Running the script again replaces the block in place, `bash install.sh --uninstall` removes it, and the rest of AGENTS.md is left alone.
The rules target common padding patterns: stock opening phrases and throat-clearing, burying the answer, summary closers and offers of further help, reject-then-correct phrasing, and balanced pros-and-cons essays where a short recommendation would do. They cover both English and Chinese. Updates come through ClawHub with clawhub update, followed by another run of the installer. The author reports 56 to 71 percent shorter output in their own tests.
When your agent uses it
- Making an agent's answers shorter and less corporate in tone
- Removing stock openers and closers such as offers of further help
- Setting an always-on style rule in a workspace's AGENTS.md
- Switching the rules off again with the uninstall option
Example prompts
- “Install talk-normal in this workspace.”
- “Our agent's replies are padded with filler, so add the talk-normal rules to AGENTS.md.”
- “Update talk-normal to the latest rules and re-run the installer.”
- “Uninstall talk-normal from our AGENTS.md.”
Requirements
- Bash to run install.sh
- A workspace AGENTS.md file the installer can edit
What it can do on your machine
Read from SKILL.md and the folder at commit d89cf32. 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
Ships script files (Shell), which the agent can run.
Shell commands in SKILL.md call:
bash
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
Talk Normal loads about 931 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 442 words of instructions outside code blocks.
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 hexiecs/talk-normal at commit d89cf32, republished under its MIT licence (© hexiecs). 442 words, ~931 tokens.
Download SKILL.mdSave it as
.claude/skills/talk-normal/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- talk-normal
- description
- Stop LLM slop. A curated system prompt that cuts verbose, corporate-sounding LLM output by 56-71% (measured) while preserving information. Works bilingually (English + Chinese). Installs into your AGENTS.md as an always-on behavior modifier.
- slug
- talk-normal
- version
- 0.6.2
- tags
- prompt, anti-slop, concise, system-prompt, chinese, bilingual, always-on
- homepage
- https://github.com/hexiecs/talk-normal
- license
- MIT
talk-normal
A curated system prompt that stops your LLM from writing like a LinkedIn post. Measured: 71% character reduction on GPT-4o-mini, 56% on GPT-5.4, across 10 prompts in English and Chinese, without losing information.
What this skill does
When invoked, this skill installs the talk-normal rules into your workspace's AGENTS.md file as an always-on behavior modifier. After install, every reply your OpenClaw agent produces follows the rules in prompt.md. The rules live between # --- talk-normal BEGIN --- and # --- talk-normal END --- markers so they do not conflict with your existing rules in AGENTS.md.
This is not a workflow skill you invoke per turn. It is a one-time installer that makes your agent permanently less verbose until you uninstall.
How to run
To install or update talk-normal in the current workspace:
bash install.shThe script is idempotent: running it again replaces the existing talk-normal block in place with the latest rules. Nothing else in your AGENTS.md is touched.
To remove:
bash install.sh --uninstallWhat gets installed
The contents of prompt.md get injected into your AGENTS.md. The rules target the specific slop patterns that make LLM output sound corporate and padded, grouped into a few categories:
- Filler and hedging — banned opening phrases ("Great question", "I'd be happy to", "让我们一起来看看"), no throat-clearing, no restating the question
- Structural discipline — lead with the answer, match depth to complexity, use bullets only when content is genuinely parallel, cap explanations for conceptual questions
- Closing patterns — no "In summary" / "Hope this helps" / "综上所述", no hypothetical follow-up offers, no conditional next-step menus ("If you want I can also...")
- Rhetorical tics — no "不是X，而是Y" / reject-then-correct framing in any variant, no plain-language restatements ("翻成人话", "in other words")
- Shape of comparisons — give a recommendation with brief reasoning, cap pros/cons lists, no balanced-essay posture
The exact rule list lives in prompt.md and evolves as new slop patterns get caught in the wild. Every commit to that file is a named slop pattern killed.
Show full SKILL.md (131 more words)Show less
Updating to the latest rules
clawhub update talk-normal
bash install.shThe first command pulls the latest skill bundle from ClawHub. The second command re-runs the idempotent installer, replacing the old rule block in AGENTS.md with the new one.
Compatibility
Works on any LLM that honors system prompts or custom instructions: GPT-5.4, GPT-4o-mini, Claude 4.6, Gemini 2.5, Grok 3, Qwen 3, DeepSeek V3, and others. OpenClaw integration is via AGENTS.md injection, which the agent reads on every turn.
Measured effect
Full benchmark data for 10 prompts across GPT-4o-mini and GPT-5.4 is in TEST_RESULTS.md in the upstream repository. Average reduction: 71% on GPT-4o-mini, 56% on GPT-5.4, while preserving the information content of the original response.
Upstream and issues
- Source: https://github.com/hexiecs/talk-normal
- Issues and rule suggestions: https://github.com/hexiecs/talk-normal/issues
- Contributing: see
CONTRIBUTING.mdin the upstream repo for the rule-submission format
License
MIT
© hexiecs, 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 3 other files in skill of hexiecs/talk-normal.
- SKILL.md
- README.md
- install.sh
- prompt.md
Open the folder on GitHubat commit d89cf32
Compare with similar skills
Talk Normal 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Talk Normal this skillhexiecs/talk-normal | 1.9k | — | ~931 | Automated safety check: Pass | MIT | |
| Unslop Filesickn33/agentic-awesome-skills | 47k | 1 repos | ~2.9k | Automated safety check: Warn | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| GPT-6 Astra Prompt Writergnipbao/gpt6-prompt-writer | 142 | — | ~662 | Automated safety check: Pass | MIT | |
| Directional Promptingkingbootoshi/directional-prompting | 143 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Init DeepAkaraChen/aghub | 272 | — | ~3.6k | Automated safety check: Pass | MIT |
Similar skills
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
GPT-6 Astra Prompt Writer
gnipbao/gpt6-prompt-writer
Writes, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes.
Directional Prompting
kingbootoshi/directional-prompting
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)…
Init Deep
AkaraChen/aghub
Generate hierarchical AGENTS.md and ensure paired CLAUDE.md files for codebases.
Unslop File
MohamedAbdallah-14/unslop
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly.
More from hexiecs/talk-normal
Talk Normal
hexiecs/talk-normal
Installs an always-on set of rules into your agent's workspace config that cuts filler, hedging and padded closings from its replies.
Related
Works with
Categories
Questions about Talk Normal
What does Talk Normal do?
Installs a set of rules into AGENTS.md that strips filler, hedging and padded closings from your agent's replies, in English and Chinese. talk-normal is a one-time installer, not a per-turn workflow.md between BEGIN and END markers, so every later reply from the agent follows them.
When should I use Talk Normal?
Talk Normal fits situations like: making an agent's answers shorter and less corporate in tone; removing stock openers and closers such as offers of further help; setting an always-on style rule in a workspace's AGENTS.md; switching the rules off again with the uninstall option.
How do I install Talk Normal in Claude Code?
Run `npx skills add hexiecs/talk-normal --skill talk-normal -a claude-code`. Or copy the skill folder (skill in hexiecs/talk-normal) into .claude/skills/talk-normal in your project. Claude Code loads it when a task matches its description.
How do I install Talk Normal in Codex?
Run `npx skills add hexiecs/talk-normal --skill talk-normal -a codex`. Or copy the skill folder (skill in hexiecs/talk-normal) into .agents/skills/talk-normal in your project. Codex loads it when a task matches its description.
Can I use Talk Normal 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 hexiecs/talk-normal --skill talk-normal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/talk-normal, .gemini/skills/talk-normal, .github/skills/talk-normal and .opencode/skills/talk-normal in your project.
What does Talk Normal need to run?
Going by SKILL.md and its folder, Talk Normal needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: Bash to run install.sh; A workspace AGENTS.md file the installer can edit.
Does Talk Normal 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 Talk Normal 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 Talk Normal use?
Talk Normal 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 Talk Normal use?
About 931 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Talk Normal?
Skills that share tags, products or a category with Talk Normal: Unslop File (sickn33/agentic-awesome-skills, 47k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), GPT-6 Astra Prompt Writer (gnipbao/gpt6-prompt-writer, 142 stars) and Directional Prompting (kingbootoshi/directional-prompting, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Talk Normal?
hexiecs (a GitHub user) maintains it in hexiecs/talk-normal, which has 1,858 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on April 22, 2026.
Source: hexiecs/talk-normal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.