Agent skill

Update Libs

by tingly-dev in tingly-dev/tingly-box

Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests.

MPL-2.0Auto-check passedAI & LLM Engineering

Install Update Libs

skills CLI
$ npx skills add tingly-dev/tingly-box --skill update-libs -a claude-code

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

GitHub CLI
$ gh skill install tingly-dev/tingly-box update-libs --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/tingly-dev/tingly-box.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/update-libs .claude/skills/update-libs && 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
update-libs
GitHub stars
351
Token cost
~830 tokens
SKILL.md length
322 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MPL-2.0

At a glance

Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests.

  • Works in 7 steps: Declare the target versions: edit the… → Network fallback if git fetch over HTTPS… → Review the fork patches. The… → …
  • Asked to bump/update SDK submodules
  • SKILL.md covers Wiring and Procedure
  • Calls git and go; reaches github.com

What it does

Update Libs is an agent skill from tingly-dev/tingly-box. Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests. Use when asked to bump/update SDK submodules, sync libs to new tingly-dev/upstream tags, or fix breakage after a submodule bump.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering LLM API integration. It works with Anthropic API, OpenAI and Go. The repository describes itself as: Your Intelligence, Orchestrated. Every builder. Every team. Every agent. For Everyone. The licence is MPL-2.0.

When your agent uses it

  • Asked to bump/update SDK submodules
  • Sync libs to new tingly-dev/upstream tags
  • Fix breakage after a submodule bump

Example prompts

  • “/update-libs”

Workflow steps

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

  1. Declare the target versions: edit the three vars in Taskfile.yml,
  2. Network fallback if git fetch over HTTPS fails (SSH usually works)
  3. Review the fork patches. The tingly-dev-* branches carry a small set
  4. Build-fix loop
  5. Verify
  6. Evaluate behavior changes — do NOT blindly conform. When a test fails
  7. Commit in stages (never one big commit; the user's preferred order)

What it can do on your machine

Read from SKILL.md and the folder at commit 2d935b7. 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

    Shell commands in SKILL.md call:

    • git
    • go

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

Update Libs loads about 830 tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~830

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from tingly-dev/tingly-box at commit 2d935b7, republished under its MPL-2.0 licence (© tingly-dev). 322 words, ~830 tokens.

Download SKILL.mdSave it as .claude/skills/update-libs/SKILL.md (or your agent's skills folder).
name
update-libs
description
Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests. Use when asked to bump/update SDK submodules, sync libs to new tingly-dev/upstream tags, or fix breakage after a submodule bump.

Update libs/ SDK submodules

Wiring

  • Submodules: libs/openai-go, libs/anthropic-sdk-go, libs/go-genai, wired into go.mod via replace.
  • Version source of truth: OPENAI_GO_VERSION / ANTHROPIC_SDK_GO_VERSION / GO_GENAI_VERSION at the top of Taskfile.yml (branch or tag names).
  • task submodule:update checks out those refs and rewrites branch = in .gitmodules to match — never hand-edit .gitmodules.

Procedure

  1. Declare the target versions: edit the three vars in Taskfile.yml, then run:

    bash
    task submodule:update
  2. Network fallback if git fetch over HTTPS fails (SSH usually works):

    bash
    for d in libs/openai-go libs/anthropic-sdk-go libs/go-genai; do
      git -C $d config url."git@github.com:".insteadOf "https://github.com/"
    done

    Set it per-submodule — submodule repos don't inherit superproject config.

  3. Review the fork patches. The tingly-dev-* branches carry a small set of deliberate patches over upstream. Verify each still exists and still makes sense; a patch may have been deleted on purpose:

    bash
    git -C libs/<sdk> fetch origin
    git -C libs/<sdk> log --oneline origin/<upstream-ref>..<tingly-dev-ref>
    git -C libs/<sdk> diff --stat origin/<upstream-ref>..<tingly-dev-ref>

    Fork patch commits are prefixed tingly-dev and explain their intent in the commit body — read it before deciding anything.

  4. Build-fix loop:

    bash
    go build ./...

    Typical SDK breakage: plain fields become param.Opt[T] (packages/param). Write with param.NewOpt(x), read with x.Value (Opt[T] is a value struct; absent → zero value, no nil deref). Note that identically-named fields on different structs may differ — one may stay plain while another became Opt — so check the struct, not the field name.

  5. Verify:

    bash
    go vet ./internal/... ./cli/... ./ai/... ./imbot/...
    go test ./internal/protocol/...

    For any failure, first attribute it: SDK-related or environment? (Failing on network fetches, temp-HOME layout, etc. is unrelated to the bump.) Do not claim verification passed on failures you didn't triage.

  6. Evaluate behavior changes — do NOT blindly conform. When a test fails on changed semantics (not just types):

    • Read the fork/upstream commit that changed the behavior and its stated intent.
    • Search tingly-box for production call sites relying on the old behavior.
    • Adapt our code/tests only if the product does not depend on the old behavior; otherwise surface the conflict to the user before changing anything.
  7. Commit in stages (never one big commit; the user's preferred order):

    1. chore(taskfile): Taskfile.yml version vars only.
    2. chore(libs): submodule pointers + .gitmodules (follows the Taskfile).
    3. refactor/fix: API adaptation code + tests (always last).
    4. Optional: doc updates.

© tingly-dev, MPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/update-libs of tingly-dev/tingly-box.

Open the folder on GitHubat commit 2d935b7

Compare with similar skills

Update Libs 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.

Update Libs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Libs this skilltingly-dev/tingly-box351—~830Automated safety check: PassMPL-2.0
ModLens Image Vision Bridgeliustack/modlens4.1k—~1.3kAutomated safety check: NotesMIT
Claude APIKocoro-lab/Kocoro4148 repos~4.5kAutomated safety check: PassApache-2.0
Using Ccproxy Inspectorstarbaser/ccproxy348—~2.7kAutomated safety check: PassCustom licence
Using Ccproxy APIstarbaser/ccproxy348—~4kAutomated safety check: PassCustom licence
Get API Docssudomakes/backroad162—~1kAutomated safety check: PassMIT

Similar skills

  • Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.

    4.1k GitHub stars~1.3k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes
  • Claude API

    Kocoro-lab/Kocoro

    Build apps with the Claude API or Anthropic SDK. An agent skill from Kocoro-lab/Kocoro.

    414 GitHub starsUsed in 8 repos~4.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Using Ccproxy Inspector

    starbaser/ccproxy

    Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic.

    348 GitHub stars~2.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Using Ccproxy API

    starbaser/ccproxy

    Guides users through ccproxy as an OpenAI-compatible and Anthropic-compatible LLM API server with SDK integration, OAuth authentication, sentinel key substitution, model routing, and troubleshooting.

    348 GitHub stars~4k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Get API Docs

    sudomakes/backroad

    A skill your agent uses when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, "use the OpenAI API", "call the Stripe API", "use the…

    162 GitHub stars~1k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed
  • Wire encrypted credentials to environment variables using the credential: convention.

    440 GitHub stars~930 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

More from tingly-dev/tingly-box

  • UI Preview

    tingly-dev/tingly-box

    Capture headless-Chrome screenshots of the tingly-box frontend (running locally in mock mode) so frontend changes can be visually verified in environments without a real browser.

    351 GitHub stars~2k tokensUpdated today
    Auto-check: notes

Questions about Update Libs

What does Update Libs do?

Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests. Update Libs is an agent skill from tingly-dev/tingly-box. Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests.

When should I use Update Libs?

Update Libs fits situations like: asked to bump/update SDK submodules; sync libs to new tingly-dev/upstream tags; fix breakage after a submodule bump.

How do I install Update Libs in Claude Code?

Run `npx skills add tingly-dev/tingly-box --skill update-libs -a claude-code`. Or copy the skill folder (.claude/skills/update-libs in tingly-dev/tingly-box) into .claude/skills/update-libs in your project. Claude Code loads it when a task matches its description.

How do I install Update Libs in Codex?

Run `npx skills add tingly-dev/tingly-box --skill update-libs -a codex`. Or copy the skill folder (.claude/skills/update-libs in tingly-dev/tingly-box) into .agents/skills/update-libs in your project. Codex loads it when a task matches its description.

Can I use Update Libs 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 tingly-dev/tingly-box --skill update-libs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-libs, .gemini/skills/update-libs, .github/skills/update-libs and .opencode/skills/update-libs in your project.

What does Update Libs need to run?

Going by SKILL.md and its folder, Update Libs needs the command-line tools its instructions call (git and go).

Does Update Libs access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Update Libs 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. Review the folder before installing.

What licence does Update Libs use?

Update Libs is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Libs use?

About 830 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Update Libs?

Skills that share tags, products or a category with Update Libs: ModLens Image Vision Bridge (liustack/modlens, 4.1k stars), Claude API (Kocoro-lab/Kocoro, 414 stars), Using Ccproxy Inspector (starbaser/ccproxy, 348 stars) and Using Ccproxy API (starbaser/ccproxy, 348 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Libs?

tingly-dev (a GitHub organization) maintains it in tingly-dev/tingly-box, which has 351 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.

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