Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cxcscmu/SkillLearnBench --skill mandarin-rhyming-guidegit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cxcscmu/skilllearnbench/mandarin-rhyming-guide)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/mandarin-rhyming-guide"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/mandarin-rhyming-guide.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.01691 |
| Opus 5 | $0.00015 | $0.00846 |
| Sonnet 5 | $0.00006 | $0.00338 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
mandarin-rhyming-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandarin Rhyming for Classical Poetry
Modern Mandarin Pronunciation System
The Four Tones
1st Tone (ā): High and level
2nd Tone (á): Rising from middle to high
3rd Tone (ǎ): Falling then rising (dip)
4th Tone (à): Sharp fall from high to low
In regulated verse composition:
- Tones determine 平仄 patterns (1st & 2nd = 平, 3rd & 4th = 仄)
- Rhyming words must share the same final vowel sound + consonant pattern
- Tone marks can be different; only the vowel+consonant final must match
Pinyin Finals (Rhyme Sets)
Finals Ending in -an
- an (安/安): ān, án, ǎn, àn [pīnyīn: bān, pán, etc.]
- ian: xiān, miǎn, diàn
- uan: duān, guán, etc.
- üan: xuān, etc.
Common characters for 安 rhyme:
- 安 (ān) - peace/safety
- 山 (shān) - mountain
- 关 (guān) - gate/close
- 还 (huán) - return
- 间 (jiān) - space/between
- 坚 (jiān) - firm
- 颜 (yán) - face/color
- 年 (nián) - year
- 天 (tiān) - sky/heaven
- 千 (qiān) - thousand
Finals Ending in -ing
- ing: dīng, míng, píng, tíng
- uing: guīng, duīng
- iing: (not commonly used)
Common characters for -ing rhyme:
- 平 (píng) - flat/peace
- 鸣 (míng) - cry/sound
- 京 (jīng) - capital
- 情 (qíng) - emotion
- 生 (shēng) - life/birth
- 听 (tīng) - listen
- 云 (yún) - cloud
- 明 (míng) - bright
Finals Ending in -ang
- ang: bāng, fāng, gāng, cháng
- iang: jiāng, liáng, xiáng
- uang: zhuāng, chuáng, guāng
Common characters:
- 堂 (táng) - hall
- 乡 (xiāng) - village/countryside
- 光 (guāng) - light
- 伤 (shāng) - wound/harm
- 长 (cháng) - long
- 江 (jiāng) - river
Finals Ending in -en
- en: bēn, gēn, ōu
- ien: diēn, etc.
- uen: guēn, kūn
- ün: lǜn, jūn
Finals Ending in -er
- er: ér, hěr
- Most standalone rhyme (儿/女/者 style)
Identifying Rhyme Families
Method 1: Same Final Sound
Two characters rhyme if they share the same final vowel sound:
- 天 (tiān) + 年 (nián) = both end in "an" sound ✓
- 天 (tiān) + 名 (míng) = different finals ✗
Method 2: Checking Modern Pronunciation
- Write character's pinyin with tone marks
- Remove the tone mark
- Keep only the final vowel pattern
- Characters with identical finals rhyme
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 173 lines · 30 tokens per session scan A 49bb4f6bae99
mandarin-rhyming-guide is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,691 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
maven-plugin-configuration
Use when configuring Maven plugins, setting up common plugins like compiler, surefire, jar, or creating custom plugin executions.
erlang-otp-behaviors
Use when oTP behaviors including genserver for stateful processes, genstatem for state machines, supervisors for fault tolerance, genevent for event handling, and building robust, production-ready Erlang applications with proven patterns.
pcap-analysis
Guidance for analyzing network packet captures (PCAP files) and computing network statistics using Python, with tested utility functions.
maven-build-lifecycle
Use when working with Maven build phases, goals, profiles, or customizing the build process for Java projects.