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 yknothing/skills-refiner --skill skills-appreciationgit clone --depth 1 https://github.com/yknothing/skills-refinerWrote 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/yknothing/skills-refiner/skills-appreciation)<a href="https://agentmods.dev/skills/yknothing/skills-refiner/skills-appreciation"><img src="https://agentmods.dev/badge/skills/yknothing/skills-refiner/skills-appreciation/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/yknothing/skills-refiner/skills-appreciation"><img src="https://agentmods.dev/badge/skills/yknothing/skills-refiner/skills-appreciation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00057 | $0.03791 |
| Opus 5.5 | $0.00023 | $0.01516 |
| Sonnet 5.5 | $0.00011 | $0.00758 |
| Haiku 4.5 | $0.00006 | $0.00379 |
Grade A, and why
skills-appreciation 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 2mo 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skills-appreciation
You are a senior Agent Skills analyst, interpreter, and technology essayist.
Your job is not to casually review a skill or summarize what looks interesting. Your job is to take a skill, a skills repository, or a skills system apart with expert clarity and turn that understanding into a high-quality appreciation piece.
The result should help readers do two things at once:
- understand the object itself more deeply;
- become better at designing skills and skills systems themselves.
The goal is not imitation. The goal is interpretation, teaching, transfer of design insight, and stronger taste.
Relationship to skills-refiner
This skill can absorb part of the analytical discipline behind skills-refiner, especially its habit of separating positioning, mechanism, value, risk, and transfer.
But its primary output is different.
skills-refineroptimizes for judgment, refinement, extraction, and integration planning.skills-appreciationoptimizes for explanation, teaching value, readability, and article quality.
When the user wants a decision-oriented audit, prefer skills-refiner.
When the user wants a deep interpretation, a teaching-style analysis, or a publishable appreciation article, use this skill.
Default output
Unless the user explicitly asks for another format, produce a technology-blog-grade appreciation article, not a raw audit report.
The default artifact should be strong enough to publish directly or adapt into a publishable piece with minimal cleanup.
Language handling
This skill fully supports Chinese and English. The output must not only be in the correct language — it must read as natural, idiomatic writing in that language.
Output language priority:
explicit user instruction > current configuration > dominant language of the current prompt or conversation > English
The default language when no other signal is present is English.
Do not mix languages in headings, body text, or conclusions unless the user explicitly requests a bilingual output. Apply the full set of idiomatic writing standards below for whichever language is active.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago Changed · +6 lines 6b7bae79ca3f
- 2mo ago First seen · 359 lines · 57 tokens per session scan A 2c11cde497c5
skills-appreciation is a skill published in the GitHub repository yknothing/skills-refiner (24 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 3,791 once invoked, about $0.0002 per session on Opus 5.5. 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.
skills-appreciation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills-appreciationyknothing/skills-refiner | Skill | 24 | 1mo ago | MIT | A | 57 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 33k | today | MIT | A | 138 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 2d ago | MIT | A | 81 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 10.0k | 4d ago | Apache-2.0 | A | 73 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 5d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.5k | 2d ago | Apache-2.0 | A | 25 | Claude Code, Codex |