Run Github Project logo

Run Github Project

CommunityPopular
chrisbanes
run-github-project

Use when asked to set up, review, or operate a repository's GitHub Project workflow, including ready claims, role-labelled human work, unknown remote mutation outcomes, Todo triage, epics, checkpoints, next-issue execution, or an authorized drain.

Overview

Publisherchrisbanes
Repositoryskills
Skill namerun-github-project
Stars
1.1K
Forks
53
Bundled files
20
LicenseApache-2.0
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.

  • 20 bundled files

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

  • Open source

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

Installation

Install the Run Github Project 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/chrisbanes/skills/tree/main/skills/run-github-project
  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/chrisbanes/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/run-github-project .claude/skills/run-github-project
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Run Github Project 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 Run Github Project 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 Run Github Project 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.

Run GitHub Project

Core principle

Use Backlog → Todo → Ready to implement → In progress → Done as the default board lanes. Todo queues planning. Resolve lane names in this procedure and its references through the trusted binding's verified names and option IDs; preserve existing configured names. Current column membership supplies ticket authorization; never inspect column transition history for permission, plan freshness, or a Ready handoff. Backlog is read-only: never claim, plan, triage, close epics, resume cleanup, or promote its items. Only humans move items out of Backlog. Continue automatic work only in Todo and later applicable columns, subject to ownership, dependencies, plan integrity, and the current run's operation-specific grants.

A verified ticket handoff covers in-scope local implementation, tests and repairs. The ticket lead may work solo or delegate when justified; retain one independent integrated-candidate review and reuse valid evidence under deliver-spec.

The Project is the live control plane. Apply these invariants throughout:

  1. Live authority: claims, selection, and finish decisions require complete, fresh GitHub and Project state; cache and partial reads are hints only.
  2. Controller ownership: only the controller claims, assigns, mutates shared Project state, merges, closes issues, and reconciles. A ticket agent owns its worktree, branch, and non-merge PR mutations only.
  3. Unknown outcomes: reconcile a failed or timed-out remote mutation before retrying or reporting success.
  4. Preservation: retain blocked, dependency-gated, and role-labelled human work in its authoritative frontier or partial-drain report; never change state merely to make the queue appear empty.

Preserve verified plan state through contract-preserving replans, return true human work to a decision pause, and in drain pair occupied slots with warm worktrees and persistent ticket agents. Park verified authority pauses and qualifying terminal required-CI claims outside capacity before refreshing the control plane.

Before dispatch, apply the execution controller's unattended readiness pass. Preserve required qualification and bounded grants while independent runnable work continues.

Select the mode

  • review: inspect or explain only; finish under the review contract.
  • setup: configure or validate the binding only; finish under the setup contract. Neither mode dispatches Project work or requires execution dependencies.
  • next: default execution; process at most one selected issue.
  • drain: only on explicit drain/run-all/repeat/until-empty request; no skill-defined ticket cap. A merge pause remains resumable work.

A named Wayfinder child remains next; it grants neither drain authority nor a claim bypass. Before any mode-specific action, read the matching mandatory lane:

ModeMandatory reference
review or setupReview and setup
next or drainReview and setup for binding validation, then execution controller and ticket lifecycle

For execution, read workflow providers before preconditions; it is authoritative on required, conditional, optional providers, sources, installation commands, and lane-specific fallback. Never install a provider implicitly. Read all providers and specialist contracts required by the execution-controller lane before their relevant action. Read run authority and ticket pauses. Use next --auto-merge or drain --auto-merge to grant merge authority for this invocation. Without it, deliver to ready PRs and pause only their merges while the board continues. When the trusted configuration enables agent profiles, read agent routing before assigning a planner, ticket agent, or helper. For drain, read drain scheduler completely before drain queue work. For next or drain, read review contracts completely before acceptance work.

Final report

Use the selected lane's terminal state and report contract. Lead an execution report with the outcome, completed tickets, work still moving, exact blockers, and the user's next action, if any. Link to durable issue, PR, and checkpoint evidence instead of repeating unchanged queries or no-op events. Keep mode, capacity, configuration digest, live-query and authority evidence, routing ledger, frontiers, parked/triage/reconciliation outcomes, and per-ticket selection, lease/plan, branch/commit/PR, verification/review, reconciled mutation/merge, and preserved or cleaned state available in a concise appendix when needed to audit a decision or resume work. Include changed unattended readiness blockers, complete-refresh/invalidation reasons, and observed planning/implementation/repair/review/CI intervals and capacity/resource waits under the timing procedure. Distinguish overlapping phase durations, total wall time and unknown timing; link repeated-cycle diagnosis and the bounded next action without claiming unmeasured savings.

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 Run Github Project AI skill do?

Use when asked to set up, review, or operate a repository's GitHub Project workflow, including ready claims, role-labelled human work, unknown remote mutation outcomes, Todo triage, epics, checkpoints, next-issue execution, or an authorized drain.

Why use Run Github Project on TypingMind?

Because you install it once and use it with any model. Run Github Project 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 Run Github Project in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chrisbanes/skills/tree/main/skills/run-github-project. 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 Run Github Project?

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 Run Github Project?

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

Is the Run Github Project AI skill free?

Yes. It is published on GitHub by chrisbanes under the Apache-2.0 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 👇