New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Lua Eco

by zhaojh329 in zhaojh329/lua-eco

International lua-eco public API skill for writing, reviewing, explaining, and fixing Lua 5.4 code that runs on the eco runtime.

MITAuto-check passedBackend & APIs

Install Lua Eco

skills CLI
$ npx skills add zhaojh329/lua-eco --skill lua-eco -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zhaojh329/lua-eco lua-eco --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zhaojh329/lua-eco.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lua-eco .claude/skills/lua-eco && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lua-eco
GitHub stars
103
Token cost
~1.7k tokens
SKILL.md length
807 words
Files
25 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

International lua-eco public API skill for writing, reviewing, explaining, and fixing Lua 5.4 code that runs on the eco runtime.

  • Works in 10 steps: Read the runtime model when generating… → If the user is starting from zero and… → Identify capabilities first:… → …
  • Tasks mention lua-eco
  • SKILL.md covers Scope, Dual Workflow, Routing Guard and Evidence Priority, plus 3 more sections
  • Coroutine scheduling

What it does

Lua Eco is an agent skill from zhaojh329/lua-eco. International lua-eco public API skill for writing, reviewing, explaining, and fixing Lua 5.4 code that runs on the eco runtime. Use when tasks mention lua-eco, eco runtime, coroutine scheduling, async I/O, sockets, HTTP/WebSocket/MQTT, DNS, files, processes, timers, ubus/UCI, netlink, nl80211, termios, SSH, encoding, hashing, or code review for scheduler safety, API selection, timeouts, and cleanup.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 25 other files, including scripts and reference files (for example `references/00-activation-and-global-rules.md`, `references/00-runtime-model.md` and `references/01-core-and-concurrency.md`).

It sits in Backend & APIs, covering Realtime and WebSockets and Code review. It works with Lua. The repository describes itself as: Coroutine-first Lua 5.4 runtime for Linux: epoll-driven scheduler with synchronous-style, non-blocking APIs, plus built-in networking, TLS, HTTP/WebSocket, MQTT, DNS, and OpenWrt… The licence is MIT.

When your agent uses it

  • Tasks mention lua-eco
  • Coroutine scheduling
  • HTTP/WebSocket/MQTT
  • Code review for scheduler safety

Example prompts

  • “/lua-eco”

Requirements

  • Python 3
  • Node.js

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Read the runtime model when generating complete programs or reviewing scheduler behavior.
  2. If the user is starting from zero and asks for a complete program, apply the program skeleton.
  3. Identify capabilities first: concurrency, files, processes, networking, protocols, or platform integration.
  4. Select API candidates from the reference files, including primary and fallback module families.
  5. Run the Symbol Gate: verify every function, method, and constant against the public API manifest.
  6. Run the Shape Gate for covered high-risk modules: verify return values, object fields, and handler signatures against…
  7. Run the Signature Gate: use the API quick reference for call signatures, option names, summaries, and official documentation URLs.
  8. Run the Example Gate: inspect the closest runnable examples or tests for the selected module family before generating nontrivial call…
  9. Generate code with eco-scheduler-friendly patterns, timeouts, error handling, and resource cleanup.
  10. Run the Output Gate: reject invented fields, return shapes, or cross-ecosystem habits before answering.

What it can do on your machine

Read from SKILL.md and the folder at commit b392e65. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lua Eco loads about 1.7k tokens when it runs, and up to ~42k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 807 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~42k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from zhaojh329/lua-eco at commit b392e65, republished under its MIT licence (© zhaojh329). 807 words, ~1,707 tokens.

Download SKILL.mdSave it as .claude/skills/lua-eco/SKILL.md (or your agent's skills folder). This skill also uses 24 other files; get the full folder from GitHub.
name
lua-eco
description
International lua-eco public API skill for writing, reviewing, explaining, and fixing Lua 5.4 code that runs on the eco runtime. Use when tasks mention lua-eco, eco runtime, coroutine scheduling, async I/O, sockets, HTTP/WebSocket/MQTT, DNS, files, processes, timers, ubus/UCI, netlink, nl80211, termios, SSH, encoding, hashing, or code review for scheduler safety, API selection, timeouts, and cleanup.

lua-eco Public API Skill

Scope

Use this skill when the user asks to:

  • Write new lua-eco code, refactor existing code, fix bugs, or add tests.
  • Look up or use any public eco API.
  • Review code that is intended to run on lua-eco.

Trigger matching should use English public API names and domain terms. Activate this skill when the task mentions topics such as lua-eco, eco runtime, Lua 5.4, coroutine scheduler, async IO, network programming, socket, timeout, cleanup, code review, blocking misuse, or API selection.

This skill uses public APIs only by default and must not guide users toward direct dependencies on eco.internal modules.

Dual Workflow

Mode A: Code Generation
  1. Read the runtime model when generating complete programs or reviewing scheduler behavior.
  2. If the user is starting from zero and asks for a complete program, apply the program skeleton.
  3. Identify capabilities first: concurrency, files, processes, networking, protocols, or platform integration.
  4. Select API candidates from the reference files, including primary and fallback module families.
  5. Run the Symbol Gate: verify every function, method, and constant against the public API manifest.
  6. Run the Shape Gate for covered high-risk modules: verify return values, object fields, and handler signatures against references/95-high-risk-api-shapes.md.
  7. Run the Signature Gate: use the API quick reference for call signatures, option names, summaries, and official documentation URLs.
  8. Run the Example Gate: inspect the closest runnable examples or tests for the selected module family before generating nontrivial call shapes.
  9. Generate code with eco-scheduler-friendly patterns, timeouts, error handling, and resource cleanup.
  10. Run the Output Gate: reject invented fields, return shapes, or cross-ecosystem habits before answering.
Mode B: Code Review
  1. Start with findings ordered by severity: Critical, High, Medium, Low.
  2. Each finding must include trigger conditions, risk, recommended fix, and whether tests are needed.
  3. Review these dimensions first:
  • Whether API selection matches the task capability.
  • Whether field names, return tuples, and handler signatures match documented lua-eco shapes.
  • Whether blocking interfaces are misused in a way that breaks eco scheduling.
  • Whether timeout handling and nil, err checks are missing.
  • Whether sockets, files, processes, timers, or connection contexts can leak.
  • Whether boundary inputs and error paths are covered by tests.

Routing Guard

This skill does not rely on hard-coded one-off function choices. It uses a general routing mechanism:

  1. Capability matrix: map the task to one or more capabilities before selecting APIs.
  2. Primary and secondary strategy: each capability defines primary and secondary API families.
  3. Anti-pattern constraints: each capability defines common misuse cases.
  4. Symbol gate: do not output calls to functions missing from the public API manifest.
  5. Shape gate: do not output fields, return tuples, or handler signatures that are not documented for lua-eco.
  6. Signature gate: use the API quick reference before emitting calls with nontrivial arguments.
  7. Example gate: prefer the closest runnable examples or tests for covered high-risk modules before trusting generic intuition.
  8. Fallback rewrite: if the selected API does not match the capability, backtrack and rewrite before answering.

Detailed rules: references/10-capability-matrix-and-routing-guards.md.

Show full SKILL.md (303 more words)Show less

Evidence Priority

When sources disagree or generic intuition conflicts with lua-eco, resolve facts in this order:

  1. Public symbol existence: references/90-public-api-manifest.md
  2. High-risk object shapes and return conventions: references/95-high-risk-api-shapes.md
  3. Runnable examples and tests in the lua-eco repo
  4. API signatures and option names: references/91-api-quick-reference.md
  5. Source inspection as a tie-breaker only when earlier layers do not settle the answer

Never infer field names or return structures from Python requests, Fetch, Node.js streams, Go net/http, or other ecosystems when lua-eco evidence is available.

Runtime and Syntax Constraints

  • Run programs with eco by default, not lua.
  • Use luac5.4 -p for syntax checks.
  • If luac5.4 is unavailable, first check whether plain luac exists and reports Lua 5.4; use it only in that case.
  • If no Lua 5.4 compiler is available, try to install one with the system package manager instead of failing immediately.
  • If installation requires network access or elevated permissions, request user approval and then proceed with the install attempt.
  • Prefer coroutine-scheduler-friendly APIs.
  • Avoid long blocking calls on primary coroutine paths.

Reference Entry Points

  • Activation and global rules: references/00-activation-and-global-rules.md
  • Runtime model: references/00-runtime-model.md
  • Core and concurrency: references/01-core-and-concurrency.md
  • Files, processes, and system IO: references/02-files-processes-system.md
  • Networking and transport: references/03-networking-and-transport.md
  • HTTP, WebSocket, and MQTT: references/04-http-websocket-mqtt.md
  • Platform integration and devices: references/05-platform-integration-and-devices.md
  • Netlink family: references/06-netlink-family.md
  • Encoding and digests: references/07-encoding-and-digests.md
  • API coverage checklist: references/08-api-coverage-checklist.md
  • Code review template: references/09-code-review-template.md
  • Capability matrix and routing guards: references/10-capability-matrix-and-routing-guards.md
  • Regression prompts: references/11-regression-prompts.md
  • Public API manifest: references/90-public-api-manifest.md
  • API quick reference: references/91-api-quick-reference.md
  • High-risk API shapes: references/95-high-risk-api-shapes.md
  • Usage patterns: references/92-usage-patterns.md
  • Common mistakes: references/93-common-mistakes.md
  • Program skeleton: references/94-program-skeleton.md

Minimum Delivery Standard

  • Generated code must be runnable, readable, maintainable, and include error handling plus resource cleanup.
  • Code reviews must be finding-first, evidence-based, and actionable.
  • API selection must match the required capability and avoid nonexistent or unsuitable functions.
  • Covered high-risk modules must use the documented lua-eco field names, return tuples, and handler signatures.

© zhaojh329, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 24 other files (scripts, references) in skills/lua-eco of zhaojh329/lua-eco.

  • SKILL.md
  • references/00-activation-and-global-rules.md
  • references/00-runtime-model.md
  • references/01-core-and-concurrency.md
  • references/02-files-processes-system.md
  • references/03-networking-and-transport.md
  • references/04-http-websocket-mqtt.md
  • references/05-platform-integration-and-devices.md
  • references/06-netlink-family.md
  • references/07-encoding-and-digests.md
  • references/08-api-coverage-checklist.md
  • references/09-code-review-template.md
  • references/10-capability-matrix-and-routing-guards.md
  • references/11-regression-prompts.md
  • references/90-public-api-manifest.md
  • references/91-api-quick-reference.md
  • references/92-usage-patterns.md
  • references/93-common-mistakes.md
  • references/94-program-skeleton.md
  • references/95-high-risk-api-shapes.md
  • … and 5 more

Open the folder on GitHubat commit b392e65

Compare with similar skills

Lua Eco next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lua Eco compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lua Eco this skillzhaojh329/lua-eco103—~1.7kAutomated safety check: PassMIT
Classcadawv-informatik/classcad-ai122—~12kAutomated safety check: PassMIT
Dev Rulesrust-dd/tako162—~810Automated safety check: PassMIT
System Bridge Go Backendtimmo001/system-bridge356—~841Automated safety check: PassApache-2.0
REST API Contract Reviewdecebals/claude-code-java751—~2.8kAutomated safety check: PassMIT
Debug Logsadam-s/intercept189—~1.1kAutomated safety check: PassMIT

Similar skills

  • Classcad

    awv-informatik/classcad-ai

    Structured API reference for the ClassCAD headless parametric CAD engine (v1 JSON/WebSocket API).

    122 GitHub stars~12k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Dev Rules

    rust-dd/tako

    General coding-style rules to apply to every project. An agent skill from rust-dd/tako.

    162 GitHub stars~810 tokensUpdated 8 days ago
    Backend & APIsAuto-check passed

  • System Bridge Go Backend

    timmo001/system-bridge

    System Bridge Go backend conventions - error wrapping, graceful degradation for data modules, nil-pointer safety, context-aware Module.Update, structured slog logging, and errcheck-clean deferred…

    356 GitHub stars~841 tokensUpdated today
    Backend & APIsAuto-check passed

  • REST API Contract Review

    decebals/claude-code-java

    Reviews REST API design for correct HTTP verbs, versioning, DTO use, consistent responses and backward compatibility before an API change ships.

    751 GitHub stars~2.8k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Debug Logs

    adam-s/intercept

    Iterative debugging with targeted logs. An agent skill from adam-s/intercept.

    189 GitHub stars~1.1k tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed

  • tRPC Release Compatibility Check

    superset-sh/superset

    Checks whether a tRPC procedure change is safe for released desktop, mobile, CLI and SDK builds, picks a compatible pattern and decides when a deprecated procedure can go.

    15k GitHub stars~1.7k tokensUpdated today
    Backend & APIsAuto-check passed

Works with

Categories

Questions about Lua Eco

What does Lua Eco do?

International lua-eco public API skill for writing, reviewing, explaining, and fixing Lua 5.4 code that runs on the eco runtime. Lua Eco is an agent skill from zhaojh329/lua-eco.4 code that runs on the eco runtime.

When should I use Lua Eco?

Lua Eco fits situations like: tasks mention lua-eco; coroutine scheduling; HTTP/WebSocket/MQTT; code review for scheduler safety.

How do I install Lua Eco in Claude Code?

Run `npx skills add zhaojh329/lua-eco --skill lua-eco -a claude-code`. Or copy the skill folder (skills/lua-eco in zhaojh329/lua-eco) into .claude/skills/lua-eco in your project. Claude Code loads it when a task matches its description.

How do I install Lua Eco in Codex?

Run `npx skills add zhaojh329/lua-eco --skill lua-eco -a codex`. Or copy the skill folder (skills/lua-eco in zhaojh329/lua-eco) into .agents/skills/lua-eco in your project. Codex loads it when a task matches its description.

Can I use Lua Eco in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zhaojh329/lua-eco --skill lua-eco -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lua-eco, .gemini/skills/lua-eco, .github/skills/lua-eco and .opencode/skills/lua-eco in your project.

What does Lua Eco need to run?

SKILL.md names no scripts, command-line tools or credentials: Lua Eco is instructions for the agent only. Our summary lists: Python 3; Node.js.

Does Lua Eco access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Lua Eco safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Lua Eco use?

Lua Eco is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lua Eco use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 40k tokens, read only when the agent opens those files.

What are the alternatives to Lua Eco?

Skills that share tags, products or a category with Lua Eco: Classcad (awv-informatik/classcad-ai, 122 stars), Dev Rules (rust-dd/tako, 162 stars), System Bridge Go Backend (timmo001/system-bridge, 356 stars) and REST API Contract Review (decebals/claude-code-java, 751 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lua Eco?

zhaojh329 (a GitHub user) maintains it in zhaojh329/lua-eco, which has 103 GitHub stars. The repository was last updated on September 30, 2026.

Source: zhaojh329/lua-eco on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.