Javdb Cli Ci logo

Javdb Cli Ci

Community
FlanChanXwO
javdb-cli-ci

Diagnose javdb-cli quality, platform, PR-verification, and publication workflows using exact run and commit evidence. Use for failed or stalled checks, PR readiness, and authorized rerun/cancel/recovery actions; read-only investigation is the default.

Overview

PublisherFlanChanXwO
Repositoryjavdb-cli
Skill namejavdb-cli-ci
Stars
76
Forks
15
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by FlanChanXwO on GitHub. Read the source before you install it.

Installation

Install the Javdb Cli Ci AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/FlanChanXwO/javdb-cli/tree/main/.agents/skills/javdb-cli-ci
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/FlanChanXwO/javdb-cli.git /tmp/javdb-cli
mkdir -p .claude/skills
cp -r /tmp/javdb-cli/.agents/skills/javdb-cli-ci .claude/skills/javdb-cli-ci
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Javdb Cli Ci in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Javdb Cli Ci on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Javdb Cli Ci is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Diagnose javdb-cli CI

Read AGENTS.md, the exact workflow, its tool/script, and the current change classifier. ci/platforms.json and tools/platformmatrix own shared targets; keep workflow conditions, permissions, and executable behavior authoritative rather than copying job counts into policy documents.

Resolve repository, PR, head SHA, workflow, run ID/attempt, event, failing job/step, and first causal error through the available GitHub connector or installed gh:

bash
gh pr checks PR_NUMBER
gh run view RUN_ID --json name,event,headBranch,headSha,status,conclusion,jobs,url
gh run view RUN_ID --log-failed
gh run view --job JOB_ID --log

Replace placeholders with verified IDs. Redact credentials and private URLs. Distinguish tool/API access errors, environment gaps, deterministic regressions, upstream failures, cancellation, and infrastructure flakiness. Slow execution alone is not a failed job.

Use javdb-cli-test to reproduce the smallest relevant failure. Run safely independent downstream phases that fail-fast hides; do not repeatedly rerun unchanged deterministic failures. Honor the actual docs-only classifier and required aggregate gates rather than adding skip conditions.

ci.yml owns the read-only Quality check: scope classification uses trusted base-branch policy, while the Quality job executes the pull request result. Trusted pr-metadata.yml validates template/command declarations, and trusted pr-smoke-gates.yml classifies smoke scope and dispatches base-ref Platform/Container workers. Only worker matrix jobs execute the exact PR head with read-only permissions. Preserve this fork-safe boundary.

Inspect the exact PR SHA: Quality gate, Platform smoke gate, and Container smoke gate are GitHub Actions jobs; PR template gate / PR commands gate are commit statuses. An unnecessary Quality or smoke gate must display Skipped, not synthetic success. Smoke worker runs use the trusted base ref, so filtering workflow runs only by PR head can miss them; follow the smoke gate and worker runs. Ordinary branch/main pushes do not run CI; stable tag pushes run Release only, because Release already repeats the release-critical test/build verification.

PR verification treats body/commands as untrusted data. Trusted metadata/aggregation jobs must not execute PR-controlled source with write credentials; preserve the exact head and artifact identity checks. /test can perform real API work and requires an authorized target scope. A reaction or submitted comment is not proof that verification succeeded.

Release boundaries

Unlike Pixiv, JavDB release.yml accepts both a matching tag push and an explicit release_tag dispatch. The existing source verifier still binds the immutable tag to the default branch. Do not transplant another repository's recovery procedure or infer a release tag from a run title.

Native archives and verified container artifacts are prepared before the single release-approval gate; publication consumes that identity. Homebrew, ClawHub, and publish-dockerhub.yml are independent downstream publishers. The latter publishes both GHCR and Docker Hub from the verified images. Their manual recovery accepts the original release_run_id, not a replacement tag/current-main source. Stable latest promotion follows the actual publisher policy.

Rerun, cancel, dispatch, push, merge, tag, or secret access requires authorization for the specific action. Do not move tags, resign/rebuild different assets, bypass review, or add retries/timeouts merely to conceal a failure. Read javdb-cli-release-notes for release preparation and history synchronization.

Report exact run/attempt/head, cause, observed checks, and unresolved blockers. Keep pending/skipped/failed distinct from passed; workflow files alone do not prove live protection settings or platform acceptance.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Javdb Cli Ci AI skill do?

Diagnose javdb-cli quality, platform, PR-verification, and publication workflows using exact run and commit evidence. Use for failed or stalled checks, PR readiness, and authorized rerun/cancel/recovery actions; read-only investigation is the default.

Why use Javdb Cli Ci on TypingMind?

Because you install it once and use it with any model. Javdb Cli Ci is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Javdb Cli Ci in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FlanChanXwO/javdb-cli/tree/main/.agents/skills/javdb-cli-ci. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Javdb Cli Ci?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Javdb Cli Ci?

As many as you like. As long as a model supports skills, you can use Javdb Cli Ci with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Javdb Cli Ci AI skill free?

Yes. It is published on GitHub by FlanChanXwO under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇