惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

云风的 BLOG
云风的 BLOG
M
MIT News - Artificial intelligence
博客园 - Franky
J
Java Code Geeks
V
Visual Studio Blog
G
Google Developers Blog
罗磊的独立博客
MongoDB | Blog
MongoDB | Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Recent Announcements
Recent Announcements
Last Week in AI
Last Week in AI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Stack Overflow Blog
Stack Overflow Blog
博客园 - 司徒正美
The GitHub Blog
The GitHub Blog
腾讯CDC
阮一峰的网络日志
阮一峰的网络日志
V
V2EX
博客园 - 【当耐特】
IT之家
IT之家
I
InfoQ
U
Unit 42
C
Check Point Blog
Martin Fowler
Martin Fowler

Hacker News

GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis Bonsai 1-bit WebGPU - a Hugging Face Space by webml-community Moving a large-scale metrics pipeline from StatsD to OpenTelemetry / Prometheus GitHub - Nightmare-Eclipse/RedSun: The Red Sun vulnerability repository GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - macOS26/Agent: Any AI, replaces Claude Code, Cursor, OpenClaw. Over 18 LLM providers (Claude, OpenAI, Gemini, Ollama, Zai, HF, Qwen) wired into a native Mac app that writes code, builds Xcode projects, bumps versions, manages git, automates Safari, use AppleScript, JS or Accessibility, extend Agent! w/ MCP Servers, run tasks from your iPhone via Messages. YouTube now lets you turn off Shorts I Made a Terminal Pager Burgers | マクドナルド公式 Commands — HackerNews CLI documentation ChatGPT for Excel PiCore - Raspberry Pi Port of Tiny Core Linux Live Nation illegally monopolized ticketing market, jury finds Google Broke Its Promise to Me. Now ICE Has My Data. Founding Engineer at Adaptional | Y Combinator CRISPR takes important step toward silencing Down syndrome’s extra chromosome GitHub - saffron-health/libretto: The AI toolkit for building reliable browser automations US v. Heppner (S.D.N.Y. 2026) no attorney-client privilege for AI chats [pdf] Retrofitting JIT Compilers into C Interpreters IPv6 – Google The Accursèd Alphabetical Clock Cybersecurity Looks Like Proof of Work Now Fragments: April 14 Cal.com Goes Closed Source: Why AI Security Is Forcing Our Decision | Cal.com - Scheduling Software for Online Bookings Laravel raised money and now injects ads directly into your agent When moving fast, talking is the first thing to break Too much Discussion of the XOR swap trick – Heather Cafe Introduction to Spherical Harmonics for Graphics Programmers The Grand Line
GitHub - Teaonly/SKILL.make: Specification and Tools for ...
teaonly · 2026-05-02 · via Hacker News

SKILL.make: Makefile Styled Skill file.

Specification and reference implementation for Makefile-styled Agent Skills.

What is this?

SKILL.make brings the declarative, dependency-driven paradigm of Makefiles to the Agent Skills format. It replaces fuzzy prose with structured logic, turning SKILL.md into a reproducible execution graph.

Why Makefile styled SKILL file?

  • Token Efficient: Optimized syntax reduces SKILL file size by ~15%, saving costs and context window space. With manual optimization, context size can be reduced by more than 30%.

  • Dependency Resolution: The harness resolves the DAG (Directed Acyclic Graph) automatically. No more relying on an LLM to "guess" the next logical step.Uses the Target: Dependency + Recipe model to ensure Agents follow a strict execution order without skipping steps.

  • Highly Composable: Modularize skills by calling targets across different files—just like a professional build system.

  • Auditability and evolution — Lays the groundwork for auditable and evolvable SKILL implementations.

Rule Definitions

Prefix Type Description
VAR = val Variable Define constants to reduce repetition.
@ cmd Shell Direct command-line instructions for execution.
$ tool Invocable Explicit calls to agent-defined tools/functions.
? prompt Reasoning Free-form prompts where the Agent decides the action.
ifeq Logic Conditional branching based on state or env vars.
multi-line string Code snippet Define code snippets using multi-line strings in Makefile syntax.

A Simple Example

Below is a typical code-review skill written in SKILL.make format:

---
name: code-review
description: A full code review workflow.
---

```makefile
# Variables
CODE_DIR = src/

# Target: review — run a full code review
review: lint test summary

lint:
	@ cd $(CODE_DIR) && eslint . --format json

test:
	@ cd $(CODE_DIR) && npm test

summary: lint test
	? Based on lint errors and test failures, write a review summary.
```

### Addtional info is also OK.

Format Comparison

We tested a complete SKILL collection (from the well-known "Skills for Real Engineers" — https://github.com/mattpocock/skills) using the Makefile format. It not only improves logical structure and readability, but more importantly, these SKILL.make files are well-suited for auditing (git tracking, invocation statistics) and lay a solid foundation for Evolution Engineering.

You can use convert.sh to reproduce this conversion. The comparison statistics are as follows:

File                                       SKILL.md SKILL.make   Change
---------------------------------------- ---------- ---------- --------
caveman                                        1916       1714     -10%
design-an-interface                            3366       2789     -17%
domain-model                                   3512       3376      -3%
edit-article                                    721        692      -4%
git-guardrails-claude-code                     2312       1861     -19%
github-triage                                 10089       8697     -13%
improve-codebase-architecture                  5509       4913     -10%
migrate-to-shoehorn                            2795       1328     -52%
obsidian-vault                                 1511       1233     -18%
qa                                             4965       4781      -3%
request-refactor-plan                          2711       2626      -3%
scaffold-exercises                             3589       2744     -23%
setup-pre-commit                               2261       1703     -24%
tdd                                            4211       3212     -23%
to-issues                                      2737       2027     -25%
to-prd                                         2460       2092     -14%
triage-issue                                   3783       3160     -16%
ubiquitous-language                            4890       4560      -6%
write-a-skill                                  3056       2879      -5%

TOTAL                                         66394      56387     -15%

Status

This is a proof-of-concept specification. This specification is designed to be compatible with most Agent Harness implementations.

License

MIT