# larashero3-dotcom/lieflat-gongwen

> A skill for AI agents that turns Chinese official-document (gongwen) style into measurable parameters derived from 1.02M characters of real corpora, helping reproduce 7 document genres.

- Magnitude: 1.2 out of 10 — Cooling
- Stars: 1,461 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2026-09-02 · Last push: 2026-09-05
- GitHub: https://github.com/larashero3-dotcom/lieflat-gongwen · Page: https://gitnova.dev/en/r/larashero3-dotcom/lieflat-gongwen

## Useful for

- Attach the skill to Codex or Claude Code so the agent drafts a work plan or research report with genre-specific parameters.
- Run a finished text through scripts/check_params.py to spot genre mismatches in heading structure.
- Compare a draft against the DNA documents and synthetic samples before submitting the material.

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- The repository is 40 days old and already has 1,461 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 200
- Issues and pull requests: 2
- Watchers: 3
- Average over the last week: 28 per day
- Usual pace: 18 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 12, 6, 8, 6, 7, 5, 21, 31, 97, 28, 11, 4, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-29 1.7, 09-30 1.5, 10-01 1.3, 10-02 1.2, 10-03 1.2, 10-04 1.2, 10-05 1.1, 10-06 1.4, 10-07 2.1, 10-08 2.5, 10-09 3.6, 10-10 2.4, 10-11 1.8, 10-12 1.2

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-12 00:23 UTC, updated every 30 minutes.