text-stats
Compute word count, character count, or reading time for a piece of text using the in-bundle text-stats engine. Invoke whenever the user asks how long a passage is, how many words or characters it has, or how long it takes to read.
Install
npx skills add https://github.com/curie-eng/curie/tree/main/examples/text-stats-engine/skills/text-stats
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install curie-eng-curie@llmmart
git clone https://github.com/curie-eng/curie.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole curie-eng/curie collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Text statistics
When to run
The user asks how many words or characters a passage has, or how long it takes to read.
How to answer
- Take the text the user provided (or asks about).
- Call the in-bundle engine's tool for the metric requested:
word_countfor a word total.char_countfor a character total (passinclude_whitespace: falseto exclude spaces).reading_time_minutesfor an estimated read time at 200 wpm.
- Report the number plainly, naming the metric and the text it applies to.
Notes
The engine runs as an in-bundle stdio MCP server (scripts/engine_server.py,
declared in .mcp.json). The harness spawns it as a subprocess; there is no
network service and nothing to provision. See this bundle's README for when to
prefer this shape over a CLI subprocess.
Files (curie)
-
SKILL.md 1.1 KB
--- name: text-stats description: Compute word count, character count, or reading time for a piece of text using the in-bundle text-stats engine. Invoke whenever the user asks how long a passage is, how many words or characters it has, or how long it takes to read. allowed-tools: - text-stats-engine --- # Text statistics ## When to run The user asks how many words or characters a passage has, or how long it takes to read. ## How to answer 1. Take the text the user provided (or asks about). 2. Call the in-bundle engine's tool for the metric requested: - `word_count` for a word total. - `char_count` for a character total (pass `include_whitespace: false` to exclude spaces). - `reading_time_minutes` for an estimated read time at 200 wpm. 3. Report the number plainly, naming the metric and the text it applies to. ## Notes The engine runs as an in-bundle stdio MCP server (`scripts/engine_server.py`, declared in `.mcp.json`). The harness spawns it as a subprocess; there is no network service and nothing to provision. See this bundle's README for when to prefer this shape over a CLI subprocess.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.