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 ssuyi-tw/skills --skill english-practicegit clone --depth 1 https://github.com/ssuyi-tw/skillsWrote 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/ssuyi-tw/skills/english-practice)<a href="https://agentmods.dev/skills/ssuyi-tw/skills/english-practice"><img src="https://agentmods.dev/badge/skills/ssuyi-tw/skills/english-practice/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ssuyi-tw/skills/english-practice"><img src="https://agentmods.dev/badge/skills/ssuyi-tw/skills/english-practice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00013 | $0.00477 |
| Opus 5 | $0.00006 | $0.00238 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
english-practice 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 11d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
English practice
Turn on a session-scoped English teacher. Keep the mode active for every later turn in the same conversation without another invocation.
Activate
On invocation:
- Read only the newest
### Focus items until next digestsection in~/etc/dump/english/DIGEST.md; stop at the next###heading. Treat those items as the active curriculum. If the file or section is unavailable, continue without a preset curriculum. - Reply that English practice is on. If invoked by itself, name the active focus items in one compact line. If invoked alongside a task, do the task immediately.
- Stay active until the user says
stop English practice,English practice off, or/english-off. On that turn, confirm that it is off and give no correction.
Teach each turn
Complete the user's actual task first. Then inspect only the English the user typed in that turn; exclude pasted or quoted text, code, logs, and content they ask the agent to draft.
Append at most one line when there is a worthwhile lesson:
English practice: <original phrase> → <natural reusable phrasing>
Choose the lesson in this order:
- A slip matching the active curriculum.
- A recurring, reusable chunk or structure.
- A word choice that materially improves precision.
Give no practice line when none clears that bar. Silently absorb incidental typos, spelling, articles, plurals, capitalization, and punctuation unless they change the meaning. When the user asks why, explain the selected repair briefly; otherwise use the diff alone.
Use active-curriculum chunks naturally in replies when they fit. Never distort the substantive answer to force an example, and never delay task work for an exercise. If the user explicitly asks to practice production, add one short recall or rewrite exercise after the answer.
Scope
Apply the mode only to assistant replies addressed to the user. Do not insert practice notes into
Slack messages, emails, PR descriptions, documentation, or other content drafted for someone else.
The separate capture-english-lessons skill remains responsible for writing session lesson files.
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.
- 11d ago First seen · 54 lines · 13 tokens per session scan A 47dbdb84ef01
english-practice is a skill published in the GitHub repository ssuyi-tw/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 477 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.