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 hanyuancheung/llm-skill --skill distillgit clone --depth 1 https://github.com/hanyuancheung/llm-skillWrote 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/hanyuancheung/llm-skill/distill)<a href="https://agentmods.dev/skills/hanyuancheung/llm-skill/distill"><img src="https://agentmods.dev/badge/skills/hanyuancheung/llm-skill/distill/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/hanyuancheung/llm-skill/distill"><img src="https://agentmods.dev/badge/skills/hanyuancheung/llm-skill/distill.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 | $0.00002 | $0.01147 |
| Opus 5 | $0.00001 | $0.00574 |
| Sonnet 5 | $0.00000 | $0.00229 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
distill 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
distill — Distillation Meta-Skill
What
Turn Raw-layer traces (conversation, pitfalls, best practices) into Wiki-layer skills, or CRUD existing ones, then notify guide to update the routing table.
When to use
- ✅
executereports a non-emptydistill-candidates. - ✅ User says "distill / remember / write it as a skill".
- ✅ Two skills overlap or conflict and need merging.
When NOT to use
- ❌ One-off incidents judged "won't recur".
- ❌ A tiny correction does not warrant a new skill (update the existing one).
How (SOP)
Phase 1: classify
For each candidate:
| Situation | Action |
|---|---|
| No routing hit + reusable | Create a new skill |
| Hit exists but record is inaccurate/incomplete | Update |
| Two skills overlap in responsibility | Merge, deprecate the loser |
| Not matched for 2 cycles | Deprecate |
| One-off, non-generalizable | Discard |
Phase 2: write/revise (follow Schema)
Adhere to AGENT.md §3 SKILL.md contract. Core requirements:
- Naming:
kebab-case, verb-domain or domain-action, e.g.review-go-pr,debug-cuda-oom. - Complete front-matter:
name/version/status/triggers/dependencies/owner/updated— all required. - Six required sections: What / When / How / Examples / Pitfalls / Changelog.
- Every Pitfall must come from a real trace, never fabricated.
- If > 500 lines, spill references into
references/.
Phase 3: version & status
- New:
version: 0.1.0,status: experimental. - Revision:
- Minor fix → patch (
0.1.0 → 0.1.1) - New How step → minor (
0.1.0 → 0.2.0) - Contract/trigger change → major (
0.1.0 → 1.0.0), document migration in Changelog.
- Minor fix → patch (
- After the 2nd independent reuse,
experimental → active.
Phase 4: notify Guide
After distillation, trigger guide to:
- Update
AGENT.md§2.2 registry. - Check dependency fan-in for ripple changes.
Distill Quality Bar
Before a candidate lands as a skill, self-check:
- Reusable: will a similar task genuinely reach for this again?
- Teachable: can
Howbe stated in ≤ 10 lines? - Falsifiable: can every Pitfall be stated as "if A then B"?
- Orthogonal: non-overlapping with existing skills?
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.
- 10d ago First seen · 128 lines · 2 tokens per session scan A 306c0a0062cb
distill is a skill published in the GitHub repository hanyuancheung/llm-skill (22 stars, last pushed 4mo ago), licensed MIT. It adds 2 tokens to every session and 1,147 once invoked, about $0.0000 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…