Web Search
EXboys/skilllite
Web search and content extraction with Tavily and Exa via inference.sh CLI.
Improve chapter perplexity score by rewriting AI-suspect sentences.
Install Perplexity Improver
$ npx skills add ThomasHoussin/Claude-Book --skill perplexity-improver -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ThomasHoussin/Claude-Book perplexity-improver --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/ThomasHoussin/Claude-Book.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/perplexity-improver .claude/skills/perplexity-improver && 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 "perplexity-improver" agent skill from https://github.com/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improver into .claude/skills/perplexity-improver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perplexity-improver", 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/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improverType 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 ThomasHoussin/Claude-Book --skill perplexity-improver -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ThomasHoussin/Claude-Book perplexity-improver --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ThomasHoussin/Claude-Book.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/perplexity-improver .agents/skills/perplexity-improver && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "perplexity-improver" agent skill from https://github.com/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improver into .agents/skills/perplexity-improver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perplexity-improver", 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 ThomasHoussin/Claude-Book --skill perplexity-improver -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ThomasHoussin/Claude-Book perplexity-improver --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ThomasHoussin/Claude-Book.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/perplexity-improver .cursor/skills/perplexity-improver && 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 "perplexity-improver" agent skill from https://github.com/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improver into .cursor/skills/perplexity-improver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perplexity-improver", 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/ThomasHoussin/Claude-Book.git --path .claude/skills/perplexity-improver--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 ThomasHoussin/Claude-Book --skill perplexity-improver -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ThomasHoussin/Claude-Book perplexity-improver --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ThomasHoussin/Claude-Book.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/perplexity-improver .gemini/skills/perplexity-improver && 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 "perplexity-improver" agent skill from https://github.com/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improver into .gemini/skills/perplexity-improver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perplexity-improver", 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 ThomasHoussin/Claude-Book perplexity-improverInstalls 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 ThomasHoussin/Claude-Book --skill perplexity-improver -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ThomasHoussin/Claude-Book.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/perplexity-improver .github/skills/perplexity-improver && 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 "perplexity-improver" agent skill from https://github.com/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improver into .github/skills/perplexity-improver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perplexity-improver", 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 ThomasHoussin/Claude-Book --skill perplexity-improver -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ThomasHoussin/Claude-Book perplexity-improver --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ThomasHoussin/Claude-Book.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/perplexity-improver .opencode/skills/perplexity-improver && 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 "perplexity-improver" agent skill from https://github.com/ThomasHoussin/Claude-Book/tree/main/.claude/skills/perplexity-improver into .opencode/skills/perplexity-improver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perplexity-improver", 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
perplexity-improver- GitHub stars
- 120
- Token cost
- ~959 tokens
- SKILL.md length
- 392 words
- Files
- 3 (incl. references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Improve chapter perplexity score by rewriting AI-suspect sentences.
- Works in 5 steps: Analyze Chapter → Evaluate Need → Rewrite Sentences → …
- Tasks that involve Web search
- SKILL.md covers Quick Start, Performance Warning, When to Use and Supported Languages, plus 3 more sections
- Calls uv
What it does
Perplexity Improver is an agent skill from ThomasHoussin/Claude-Book. Improve chapter perplexity score by rewriting AI-suspect sentences. Use after writing a chapter to reduce detectable AI patterns.
Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/rewriting-techniques-en.md` and `references/rewriting-techniques-fr.md`).
It sits in Productivity & Automation, covering Web search. It works with Perplexity. The repository describes itself as: A Multi-Agent Framework for Writing Novels with Claude Code. The licence is MIT.
When your agent uses it
- Tasks that involve Web search
Example prompts
- “/perplexity-improver”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3fdebbb. 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
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Perplexity Improver loads about 959 tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 37 tokens; SKILL.md has 392 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 ThomasHoussin/Claude-Book at commit 3fdebbb, republished under its MIT licence (© ThomasHoussin). 392 words, ~959 tokens.
Download SKILL.mdSave it as
.claude/skills/perplexity-improver/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- perplexity-improver
- description
- Improve chapter perplexity score by rewriting AI-suspect sentences. Use after writing a chapter to reduce detectable AI patterns.
Perplexity Improver Skill
Reduce AI-detectable patterns in chapters by rewriting low-perplexity sentences while preserving narrative integrity.
Quick Start
/perplexity-improver story/chapters/chapitre-05.mdMultiple chapters can be analyzed in one run:
/perplexity-improver story/chapters/chapitre-01.md story/chapters/chapitre-02.mdPerformance Warning
⚠️ The analysis script is SLOW (several minutes for model loading and analysis).
- Accumulate several corrections before re-running
- Use at the end of a writing session, not after each edit
When to Use
- After writing a chapter, before final validation
- When perplexity analysis shows a warning (⚠️)
Supported Languages
| Code | Language | Techniques File |
|---|---|---|
fr | Français | references/rewriting-techniques-fr.md |
en | English | references/rewriting-techniques-en.md |
Workflow
Phase 1: Analyze Chapter
1. Detect language from chapter content (first 500 characters):
- Identify language code (
fr,en, etc.) - Load corresponding techniques file:
references/rewriting-techniques-{lang}.md - If language not supported → report error and exit
2. Run perplexity analysis from the script directory (required for uv to find dependencies):
cd scripts/detection && uv run python detection.py ../../<path/to/chapter.md>Important: The uv run command must be executed from scripts/detection/ where the pyproject.toml is located.
3. Extract from output:
- Median perplexity score
- Warning status (median below threshold)
- Suspect rate (percentage of suspect sentences)
- List of suspect sentences sorted by ascending perplexity
Phase 2: Evaluate Need
The script flags sentences using multiple criteria:
- low_perplexity: individually predictable sentence
- low_std: passage with uniform perplexity (no surprises)
- adjacent_low: extended stretch without friction
- low_ppl_density: cumulative boredom signal
- forbidden_word: AI-signal vocabulary
Decision tree:
- If no warning (⚠️) in output → PASS, report and exit
- If warning displayed (flagged rate > 25%) → proceed to Phase 3
Priority: Sentences with multiple flags (multi-flagged) should be rewritten first using techniques from references/rewriting-techniques-{lang}.md.
Show full SKILL.md (150 more words)Show less
Phase 3: Rewrite Sentences
Process sentences from lowest perplexity first (most predictable = most suspect).
For each suspect sentence:
- Locate in original chapter
- Rewrite using techniques from
references/rewriting-techniques-{lang}.md - Preserve exact meaning and narrative function
CRITICAL: Verify that meaning is preserved and rewrites integrate naturally.
Phase 4: Re-analyze
Run perplexity script on modified chapter.
Compare before/after:
- Median perplexity: target ≥ threshold (no warning)
- Suspect rate: target ≤ 20%
- Suspect sentence count: target reduction
If still warning:
- Iterate (max 3 loops)
- Try different rewriting techniques
- Focus on remaining lowest-perplexity sentences
Phase 5: Finalize
Generate reports in .work/:
perplexity-report.md: before/after stats, PASS/FAIL statusperplexity-changes.md: each rewritten sentence with technique used
Ask for validation before applying changes to chapter file.
Thresholds Reference
All thresholds are defined in scripts/detection/detection.py (constants at top of file).
Interaction Style
- Show progress after each phase
- Present before/after comparisons
- Explain technique choices
- Ask for validation before applying changes to file
© ThomasHoussin, 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 .claude/skills/perplexity-improver of ThomasHoussin/Claude-Book.
- SKILL.md
- references/rewriting-techniques-en.md
- references/rewriting-techniques-fr.md
Open the folder on GitHubat commit 3fdebbb
Compare with similar skills
Perplexity Improver 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 |
|---|---|---|---|---|---|---|
| Perplexity Improver this skillThomasHoussin/Claude-Book | 120 | — | ~959 | Automated safety check: Pass | MIT | |
| Web SearchEXboys/skilllite | 170 | 3 repos | ~1k | Automated safety check: Pass | MIT | |
| Keirouter Web Searchmydisha/keirouter | 147 | — | ~771 | Automated safety check: Pass | MIT | |
| Perplexity Researchinbrainfun/inbrain | 142 | — | ~1.7k | Automated safety check: Notes | Custom licence | |
| Perplexity Searchparcadei/Continuous-Claude-v3 | 3.9k | 2 repos | ~806 | Automated safety check: Notes | MIT | |
| Web Search PlusCraftOS-dev/CraftBot | 392 | 1 repos | ~2.4k | Automated safety check: Notes | MIT |
Similar skills
Keirouter Web Search
mydisha/keirouter
Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity.
Perplexity Research
inbrainfun/inbrain
Brain-augmented web research. An agent skill from inbrainfun/inbrain.
Perplexity Search
parcadei/Continuous-Claude-v3
AI-powered web search, research, and reasoning via Perplexity
Web Search Plus
CraftOS-dev/CraftBot
Unified search skill with Intelligent Auto-Routing. An agent skill from CraftOS-dev/CraftBot.
Perplexity
refly-ai/refly-skills
AI-powered search and chat with Perplexity. An agent skill from refly-ai/refly-skills.
More from ThomasHoussin/Claude-Book
Book Analyzer
ThomasHoussin/Claude-Book
Analyze source books to extract structured bible files (style, characters, structure, universe).
Story Ideator
ThomasHoussin/Claude-Book
Generate original storylines from any universe bible without plagiarizing source material.
Bible Merger
ThomasHoussin/Claude-Book
Merge multiple book analyses into a unified bible. An agent skill from ThomasHoussin/Claude-Book.
Related
Works with
Categories
Questions about Perplexity Improver
What does Perplexity Improver do?
Improve chapter perplexity score by rewriting AI-suspect sentences. Perplexity Improver is an agent skill from ThomasHoussin/Claude-Book. Improve chapter perplexity score by rewriting AI-suspect sentences.
When should I use Perplexity Improver?
Perplexity Improver fits situations like: tasks that involve Web search.
How do I install Perplexity Improver in Claude Code?
Run `npx skills add ThomasHoussin/Claude-Book --skill perplexity-improver -a claude-code`. Or copy the skill folder (.claude/skills/perplexity-improver in ThomasHoussin/Claude-Book) into .claude/skills/perplexity-improver in your project. Claude Code loads it when a task matches its description.
How do I install Perplexity Improver in Codex?
Run `npx skills add ThomasHoussin/Claude-Book --skill perplexity-improver -a codex`. Or copy the skill folder (.claude/skills/perplexity-improver in ThomasHoussin/Claude-Book) into .agents/skills/perplexity-improver in your project. Codex loads it when a task matches its description.
Can I use Perplexity Improver 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 ThomasHoussin/Claude-Book --skill perplexity-improver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/perplexity-improver, .gemini/skills/perplexity-improver, .github/skills/perplexity-improver and .opencode/skills/perplexity-improver in your project.
What does Perplexity Improver need to run?
Going by SKILL.md and its folder, Perplexity Improver needs the command-line tools its instructions call (uv). Our summary lists: Python 3.
Does Perplexity Improver access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Perplexity Improver 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 Perplexity Improver use?
Perplexity Improver is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Perplexity Improver use?
About 959 tokens (SKILL.md is roughly 3.8k 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 3.5k tokens, read only when the agent opens those files.
What are the alternatives to Perplexity Improver?
Skills that share tags, products or a category with Perplexity Improver: Web Search (EXboys/skilllite, 170 stars), Keirouter Web Search (mydisha/keirouter, 147 stars), Perplexity Research (inbrainfun/inbrain, 142 stars) and Perplexity Search (parcadei/Continuous-Claude-v3, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Perplexity Improver?
ThomasHoussin (a GitHub user) maintains it in ThomasHoussin/Claude-Book, which has 120 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on January 22, 2026.
Source: ThomasHoussin/Claude-Book on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.