Agent skill

CI Validate

by tetherto in tetherto/qvac

Trigger a CI workflow for a package, wait for completion, and report results

Apache-2.0Auto-check passedAI & LLM Engineering

Install CI Validate

skills CLI
$ npx skills add tetherto/qvac --skill ci-validate -a claude-code

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

GitHub CLI
$ gh skill install tetherto/qvac ci-validate --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/tetherto/qvac.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/ocr-ggml/.agent/skills/ci-validate .claude/skills/ci-validate && 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
ci-validate
GitHub stars
681
Token cost
~731 tokens
SKILL.md length
409 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
Apache-2.0

At a glance

Trigger a CI workflow for a package, wait for completion, and report results

  • Works in 5 steps: Validate and push → Trigger the workflow → Monitor the run → …
  • A CI workflow for a package
  • SKILL.md covers Argument and Steps
  • Calls gh and git

What it does

CI Validate is an agent skill from tetherto/qvac. Trigger a CI workflow for a package, wait for completion, and report results

Its SKILL.md is about 730 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. The repository describes itself as: Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more… The licence is Apache-2.0.

When your agent uses it

  • A CI workflow for a package
  • Wait for completion

Example prompts

  • “/ci-validate”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Validate and push
  2. Trigger the workflow
  3. Monitor the run
  4. Report results
  5. Retry loop (if called by an agent, not interactively)

What it can do on your machine

Read from SKILL.md and the folder at commit c3a6030. 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:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    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

CI Validate loads about 731 tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 409 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~731

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 tetherto/qvac at commit c3a6030, republished under its Apache-2.0 licence (© tetherto). 409 words, ~731 tokens.

Download SKILL.mdSave it as .claude/skills/ci-validate/SKILL.md (or your agent's skills folder).
name
ci-validate
description
Trigger a CI workflow for a package, wait for completion, and report results
argument-hint
<package-short-name>
disable-model-invocation
true

CI Validate — Cross-Platform Workflow Runner

Trigger a CI workflow for a package, wait for it to complete, and report results.

Argument

The argument $ARGUMENTS is the package short name. See the CI Package Mapping table in .agent/knowledge/ci-validation.md for valid short names and their corresponding package directories.

The workflow name is: On PR Trigger (<short-name>) where <short-name> is the argument.

Steps

Step 1: Validate and push
  1. Confirm $ARGUMENTS matches one of the valid package names above. If not, show the list and stop.
  2. Make sure all changes are committed. If there are uncommitted changes, warn and stop.
  3. Push the current branch to origin: git push origin HEAD
Step 2: Trigger the workflow

Run: gh workflow run "On PR Trigger ($ARGUMENTS)" --repo tetherto/qvac --ref $(git branch --show-current)

If the trigger fails, show the error and stop.

Wait 5 seconds for the run to register, then find the run ID: gh run list --repo tetherto/qvac --workflow "On PR Trigger ($ARGUMENTS)" --branch $(git branch --show-current) --limit 1 --json databaseId,status,conclusion,createdAt

Step 3: Monitor the run

Wait for the run to complete: gh run watch <run-id> --repo tetherto/qvac

Show full SKILL.md (224 more words)Show less
Step 4: Report results

After the run completes, get the result: gh run view <run-id> --repo tetherto/qvac

  • If all jobs passed: Report success with a summary of platforms/jobs that passed.
  • If any job failed:
    1. Get failed logs: gh run view <run-id> --repo tetherto/qvac --log-failed
    2. Show the user which jobs/platforms failed and the relevant error logs
    3. Ask if they want you to investigate and fix the issue

For failure analysis, platform details, and troubleshooting: see .agent/knowledge/ci-validation.md.

Important: Only attempt to fix infra/CI failures (environment, config, workflow issues). If the failure is a code logic error (compilation error, test assertion, lint violation, type error), report the failure back to the user with the relevant logs — do not attempt to fix application code.

Step 5: Retry loop (if called by an agent, not interactively)

If running as part of an automated pipeline (not interactive):

  1. Analyze the failure logs using the classification guide in .agent/knowledge/ci-validation.md
  2. If infra failure: fix the CI/config issue, commit and push, re-trigger (go to Step 2)
  3. If code logic failure: stop and report back with the error logs, affected platforms, and which source files need attention
  4. If the same infra failure persists more than 5 times after fixes: document on the Asana task with full error logs, what was tried, and which platforms are affected — then STOP

© tetherto, Apache-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 packages/ocr-ggml/.agent/skills/ci-validate of tetherto/qvac.

Open the folder on GitHubat commit c3a6030

Compare with similar skills

CI Validate 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.

CI Validate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI Validate this skilltetherto/qvac681—~731Automated safety check: PassApache-2.0
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
Peft Fine TuningOrchestra-Research/AI-Research-SKILLs13k9 repos~3.1kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k9 repos~3.3kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.8k15 repos~656Automated safety check: PassApache-2.0

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed
  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Peft Fine Tuning

    Orchestra-Research/AI-Research-SKILLs

    Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.

    13k GitHub starsUsed in 9 repos~3.1k tokens
    AI & LLM EngineeringAuto-check passed
  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 9 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed
  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.8k GitHub starsUsed in 15 repos~656 tokens
    AI & LLM EngineeringAuto-check passed
  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 8 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

More from tetherto/qvac

All 50 skills in this repo
  • Creates a Solutions page in the QVAC documentation website from a real use case, generalizing the case into reusable guidance and registering the page in the site navigation.

    681 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Qv Docs Update

    tetherto/qvac

    Updates the docs website after a change to the SDK or CLI. An agent skill from tetherto/qvac.

    681 GitHub stars~11k tokensUpdated today
    Auto-check passed
  • Qv Agent Stack Sync

    tetherto/qvac

    Plan and prepare the QVAC agent-stack release cascade across @qvac/inference, @qvac/sdk, @qvac/cli, @qvac/ai-sdk-provider, @qvac/opencode-plugin, and @qvac/openclaw-plugin.

    681 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Run the deterministic code-quality audit, turn related findings into contextual remediation groups, prepare approval-gated Asana proposals, reconcile recurring runs, or configure twice-monthly…

    681 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Review C++ changes for string parameter and call-site efficiency conventions (std::stringview, std::string&&, const std::string&, const char, and TransparentStringMap lookup).

    681 GitHub stars~702 tokensUpdated today
    Auto-check passed
  • Qv Addon Changelog

    tetherto/qvac

    Generate changelog entries for a target add-on package. An agent skill from tetherto/qvac.

    681 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Questions about CI Validate

What does CI Validate do?

Trigger a CI workflow for a package, wait for completion, and report results. CI Validate is an agent skill from tetherto/qvac.

When should I use CI Validate?

CI Validate fits situations like: A CI workflow for a package; wait for completion.

How do I install CI Validate in Claude Code?

Run `npx skills add tetherto/qvac --skill ci-validate -a claude-code`. Or copy the skill folder (packages/ocr-ggml/.agent/skills/ci-validate in tetherto/qvac) into .claude/skills/ci-validate in your project. Claude Code loads it when a task matches its description.

How do I install CI Validate in Codex?

Run `npx skills add tetherto/qvac --skill ci-validate -a codex`. Or copy the skill folder (packages/ocr-ggml/.agent/skills/ci-validate in tetherto/qvac) into .agents/skills/ci-validate in your project. Codex loads it when a task matches its description.

Can I use CI Validate 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 tetherto/qvac --skill ci-validate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ci-validate, .gemini/skills/ci-validate, .github/skills/ci-validate and .opencode/skills/ci-validate in your project.

What does CI Validate need to run?

Going by SKILL.md and its folder, CI Validate needs the command-line tools its instructions call (gh and git).

Does CI Validate access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is CI Validate 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 CI Validate use?

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

How many tokens does CI Validate use?

About 731 tokens (SKILL.md is roughly 2.9k 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 CI Validate?

Skills that share tags, products or a category with CI Validate: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI Validate?

tetherto (a GitHub organization) maintains it in tetherto/qvac, which has 681 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 7, 2026.

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