Ln 61 Repository Publisher logo

Ln 61 Repository Publisher

Community
levnikolaevich
ln-61-repository-publisher

Commits, pushes and remotely verifies authorized repository changes; does not create releases.

Overview

Publisherlevnikolaevich
Repositoryclaude-code-skills
Skill nameln-61-repository-publisher
Stars
565
Forks
84
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Ln 61 Repository Publisher 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.
  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/levnikolaevich/claude-code-skills.git /tmp/claude-code-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-skills/plugins/delivery-suite/skills/ln-61-repository-publisher .claude/skills/ln-61-repository-publisher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ln 61 Repository Publisher 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 Ln 61 Repository Publisher 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 Ln 61 Repository Publisher 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.

Repository Publisher

Goal: Publish only changes the user has authorized, then verify the result from the remote source.

Execution contract: The checklist defines completion. Track each item internally as PENDING, PROVEN with evidence, CLEARED with evidence its condition is absent, or UNPROVEN with a gap; reading, delegation, or tool failure is not proof. Reconcile after each section. Before returning, resolve all PENDING, count only PROVEN and CLEARED, and apply verdict and approval rules to every gap. Preserve intent, scope, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. Scale depth to material risk without skipping checks. Preserve dependency and safety order; otherwise choose an appropriate verification method. Accept equivalent user or repository evidence; no other skill, named artifact, or complete lifecycle is required. Preserve source requirement and decision IDs. Bind reused evidence to relevant source versions, dirty changes, configuration, and environment; invalidate only affected claims. On continuation, reconcile task, authorization, current state, and unresolved evidence. For long work, return a compact continuation record or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Prepare authorized work before required approval. If blocked by an instruction, cite its exact source and unresolved boundary; do not invent approval gates from caution.

Tool Routing

NeedPreferred capabilityFallback
Scope, staging, history, and synchronizationNative Git CLIStop if equivalent Git evidence is unavailable
Repository validationProject-native commands and installed validatorsDocumented manual checks
Remote branch and CI stateAuthenticated hosting CLI or connectorGit remote evidence plus direct workflow URLs
Clean-source verificationTemporary clone and isolated host configuration when distribution surfaces changedRemote raw files plus BLOCKED for required install evidence
Static-site verificationDeployment workflow plus direct HTTP requestHosting API deployment state
Current marketplace behaviorOfficial host documentationMark assumptions and avoid destructive retries

Prefer compact Git output first, then open the full diff for files that will be staged. Never pipe commands in a way that hides the failing exit code.

Use hosting APIs for remote facts and Git for repository facts. Local distribution or deployment state cannot prove that a remote consumer update works.

Checklist

Establish scope and evidence

  • Confirm the user explicitly requested a commit and push and identify the intended branch.
  • Read repository instructions, release rules, and the current branch policy before mutation.
  • Check git status -sb, staged and unstaged diffs, untracked files, remotes, and recent commit style.
  • Identify unrelated user changes; do not stage them without explicit whole-worktree authorization.
  • Inspect deletions and generated files as carefully as edited text.
  • Check whether behavior, installation commands, catalogs, layout, or the public site require matching documentation updates.
  • Do not change versions, tags, or release metadata during an ordinary publication unless the request or repository policy explicitly includes them.
  • For marketplace edits, confirm every stable identifier is unchanged unless an intentional migration was approved.
  • When multiple host catalogs exist and repository policy requires parity, confirm they contain the same distribution units in the required order.
  • When metadata is duplicated across manifests or catalogs, confirm descriptions and source paths agree with the canonical source.

Validation Routing

  • Discover and run repository-native validation commands before generic checks.
  • For changed skills, run repository-required or host-native skill validators, or perform their documented manual fallback.
  • For changed plugins or packages, run repository-required validators, or perform their documented manual fallback.
  • Run every host-native strict validator whose distribution surface exists and changed or is required by repository policy.
  • Run only the catalog parity, manifest parsing, stale-reference, local-link, and whitespace checks required by the repository and affected surfaces.
  • Run only relevant product tests; do not invent a heavyweight release gate absent from repository policy.
  • Stop before commit on a confirmed failing required check unless the user explicitly accepts the failure.
  • Record skipped checks with the exact missing dependency or environment.

Synchronization and Commit

  • Fetch the target remote and compare local HEAD with the remote branch before committing.
  • If behind or diverged, inspect both sides and reconcile within the authorized branch workflow while preserving user changes; stop for unresolved semantic conflicts or a required history rewrite. Never force-push implicitly.
  • Stage explicit paths when the worktree is mixed; use whole-worktree staging only when the user approved all changes.
  • Review the cached diff and diffstat after staging; ensure required checks cover this exact tree, rerunning only checks invalidated by synchronization or subsequent edits.
  • Exclude secrets, local caches, temporary artifacts, and unintended credentials from the staged set without deleting user-owned files; if an intended change contains a secret, block that publication and report redacted evidence.
  • Match the repository's commit-message convention and summarize the entire staged change.
  • Preserve configured commit signing and attribution policy; do not invent contributor identities or disable required signing.
  • Create the commit and capture its full SHA.
  • Push to the authorized branch without changing branch protections or using force.

Remote Verification

  • Verify remote publication refers to the exact checked source state and exclude unverified later changes; repository publication alone does not prove a release or deployment.
  • Verify the published commit on the authorized remote through Git or the hosting API; use a second source only if identity or synchronization is uncertain.
  • Track required CI for the pushed commit with bounded waits and direct run URLs. If execution cannot continue waiting, report pending state as PARTIAL; do not equate pending with success.
  • If the static site changed, wait for deployment and verify live content with a cache-busting request.
  • If installation or marketplace content changed, clone an authorized consumer-accessible remote into a clean temporary directory and validate the affected distribution surface.
  • When install or update behavior changed, test at least one affected package or plugin from its documented distribution source in isolated host configuration.
  • When stable distribution identifiers or versions exist, verify the installed artifact resolves under the expected identifier and version.
  • Keep temporary host configuration isolated from the user's active settings and remove it safely afterward.
  • Recheck local worktree and HEAD against the published commit. If the remote advanced concurrently, verify that it still contains the published commit and report both SHAs; do not overwrite newer work to restore equality.

Safety Gates

  • Never expose authentication tokens or credential values in output.
  • Never create a release, tag, package publication, discussion, or pull request unless explicitly requested.
  • Never delete remote branches or alter the default branch as a side effect.
  • Return BLOCKED rather than bypassing branch protection, authentication, or required checks.

Verdict

  • PUBLISHED — commit, push, required CI, and applicable remote verification succeeded.
  • PARTIAL — the push succeeded but a non-destructive remote check is pending or failed.
  • BLOCKED — publication did not complete because authorization, synchronization, validation, or remote access failed.

Self-Check

  • Reconcile before returning. Check item-level evidence, requirement coverage, contradictions, scope, verdict, and applicable cleanup. Correct the report or authorized artifacts. Reuse valid evidence; do not automatically rescan the repository or rerun successful commands. Repeat checks only for relevant changes, failures, or unresolved evidence. Disclose remaining gaps.

Output Contract

Report in the user's language, in this order; retain all five fields and state each fact once. Small results may use one line per field; omit empty tables and do not copy linked artifacts:

  1. Result: Skill-specific verdict and supported outcome.
  2. Scope: Reviewed/changed scope, exclusions, baseline, and material assumptions.
  3. Evidence: Skill-specific fields below; distinguish facts, inferences, and unverified claims. Link artifacts; use tables when useful.
  4. Verification: Checks/results, unavailable evidence, and applicable cleanup/external state.
  5. Completion: Checklist: X/Y complete; Incomplete: None or each UNPROVEN item's reason, outcome impact, and exact next action; residual risks and required decisions.

Skill-specific evidence: Published/excluded paths, branch, full commit SHA, remote URL, validation results, CI/deployment URLs, and applicable clean-source install/update proof. For PARTIAL, state whether the pushed commit is safe to leave and the observable event that closes verification. Use PUBLISHED only when the remote commit and every applicable required workflow are observed.

Frequently asked questions

What does the Ln 61 Repository Publisher AI skill do?

Commits, pushes and remotely verifies authorized repository changes; does not create releases.

Why use Ln 61 Repository Publisher on TypingMind?

Because you install it once and use it with any model. Ln 61 Repository Publisher 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 Ln 61 Repository Publisher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/levnikolaevich/claude-code-skills/tree/master/plugins/delivery-suite/skills/ln-61-repository-publisher. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ln 61 Repository Publisher?

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 Ln 61 Repository Publisher?

As many as you like. As long as a model supports skills, you can use Ln 61 Repository Publisher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ln 61 Repository Publisher AI skill free?

Yes. It is published on GitHub by levnikolaevich 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 👇