Agent skill

Ln 62 Release Publisher

by levnikolaevich in levnikolaevich/claude-code-skills

Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.

MITAuto-check passedDevelopment

Install Ln 62 Release Publisher

skills CLI
$ npx skills add levnikolaevich/claude-code-skills --skill ln-62-release-publisher -a claude-code

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

GitHub CLI
$ gh skill install levnikolaevich/claude-code-skills ln-62-release-publisher --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/levnikolaevich/claude-code-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/delivery-suite/skills/ln-62-release-publisher .claude/skills/ln-62-release-publisher && 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
ln-62-release-publisher
GitHub stars
574
Token cost
~2.9k tokens
SKILL.md length
1,532 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.

  • Works in 5 steps: Result: The exact skill-specific verdict… → Scope: Reviewed/changed scope,… → Evidence: Skill-specific fields below;… → …
  • Development work in your project
  • SKILL.md covers Tool Routing, Checklist, Verdict and Self-Check, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ln 62 Release Publisher is an agent skill from levnikolaevich/claude-code-skills. Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.

Its SKILL.md is about 2.9k 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 Development. It works with GitHub. The repository describes itself as: Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified. For Claude Code and Codex. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “Use the ln-62-release-publisher skill to prepare and publishes an explicitly requested tagged GitHub release; does not deploy applications”
  • “/ln-62-release-publisher”

Workflow steps

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

  1. Result: The exact skill-specific verdict token first, then the 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…

What it can do on your machine

Read from SKILL.md and the folder at commit 0ce8796. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Ln 62 Release Publisher loads about 2.9k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 1,532 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 levnikolaevich/claude-code-skills at commit 0ce8796, republished under its MIT licence (© levnikolaevich). 1,532 words, ~2,887 tokens.

Download SKILL.mdSave it as .claude/skills/ln-62-release-publisher/SKILL.md (or your agent's skills folder).
name
ln-62-release-publisher
description
Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.

Release Publisher

Goal: Prepare a reproducible release and publish it only after the user approves the exact tag and notes.

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, tool failure, a zero exit status, or a self-reported success is not proof; only the observed outcome is. 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. When no one can answer during the run, state the exact question and apply the skill's verdict for the remaining gap instead of waiting or guessing. 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
Release boundary and commit evidenceGit history, tags, and diffsHosting API commit comparison
Existing release style and stateAuthenticated GitHub CLI or connectorPublic GitHub API for read-only evidence
Release identity and version scopeRepository policy, prior tags, and canonical version files when presentStop only when the release identity remains ambiguous
Release validationRepository-native gates and clean checkoutManual structural checks with reduced confidence
Tag and GitHub Release creationGit plus an authenticated GitHub release capabilityBLOCKED; do not emulate release state in files
Installation verificationIsolated environment against the documented distribution sourceClean source validation without install proof

When publishing through a shell, use a temporary notes file so Markdown, quotes, and code blocks are not reinterpreted. Keep credentials in the host credential store and never echo them.

Do not browse for generic release advice when repository policy and previous comparable releases answer the question. Use official host documentation only for current API or CLI behavior.

Checklist

Establish scope and evidence
  • Confirm the user explicitly requested a release and identify the repository, release target, and intended audience.
  • Read repository release rules before selecting a version, tag shape, files, or publication sequence.
  • Verify an authenticated GitHub release capability, repository access, and permission to create releases.
  • Require a clean worktree or explicitly exclude unrelated changes before release preparation.
  • Fetch tags and the target branch; confirm local HEAD is synchronized with the remote release branch.
  • Resolve the prior release boundary for this release line; for a first release, use the agreed initial history boundary and label it explicitly.
  • Inspect commits and full commit bodies from the previous release boundary to the proposed release commit.
  • Read the affected manifests, authoritative documentation, installation instructions, configured catalogs, and user-facing migration notes when present.
  • Treat commits and source diffs as evidence; use existing release notes only as secondary context.
Version and Scope
  • Use the repository's declared versioning policy; do not impose CalVer, SemVer, or a shared catalog version when none is specified.
  • If the release target or tag is ambiguous, stop and ask instead of inventing a convention.
  • Check the proposed tag locally and remotely. For a resumed approved release, verify its exact target and existing release state before continuing; otherwise treat a collision as a blocker, never overwrite it.
  • Prepare version changes only in canonical fields identified by repository instructions; keep them local and reviewable until proposal approval.
  • Update only packages, plugins, or components included in the release; do not bump unrelated manifests for visual consistency.
  • Keep a new distribution unit at its approved initial version unless this release explicitly advances it.
  • Ensure the tag, release title, and notes describe the same release unit; require manifest-version alignment only for versioned manifests included in that unit.
  • Document breaking installation or behavior changes in the repository's required migration surface.
Release Notes
  • Read the most recent comparable releases and preserve useful house style without copying stale structure.
  • Group changes by user outcome, not by file list or internal implementation chronology.
  • Lead with why the release matters, then state the concrete behavior users receive.
  • Include exact install or update commands only after verifying them against the current authoritative documentation and applicable distribution metadata.
  • Include migration steps for every confirmed breaking change, with old and new behavior clearly separated.
  • Mention removed behavior plainly; do not disguise removal as simplification.
  • Credit external contributors by verified handle and omit a contributors section for solo work.
  • Link to canonical documentation and repository paths that exist at the release commit.
  • Exclude claims about adoption, performance, compatibility, or counts that cannot be reproduced.
  • Distinguish measured facts from interpretation and future intent.
Show full SKILL.md (673 more words)Show less
Validation and Approval
  • Run every repository release gate and the relevant product, package, plugin, skill, or marketplace checks for surfaces that exist.
  • When multiple host catalogs exist and repository policy requires parity, confirm they remain aligned; preserve every stable distribution identifier unless migration was approved.
  • When installation surfaces change, validate an isolated snapshot of the exact proposed tree before approval and identify its baseline and patch; after committing, verify that the release commit contains that validated tree.
  • Record commands, versions, exit codes, and skipped checks without exposing secrets.
  • Present the exact version changes, tag, title, full notes, validation evidence, and planned commands.
  • Wait for explicit user approval of that exact proposal before committing version changes, tagging, or publishing.
  • Reuse approval while version changes, target, tag, title, and notes remain exactly as approved; present changed publication content for renewed approval before publishing.
Publication
  • Reconcile prepared metadata and documentation with the approved proposal; apply any outstanding approved edits and exclude unrelated changes.
  • Confirm required release gates cover the final approved tree; rerun only checks invalidated by final edits or unresolved failures.
  • Commit and push the release commit using the authorized branch workflow.
  • Confirm required CI succeeds on the release commit before creating the tag.
  • Create an annotated or repository-standard tag pointing at the verified commit and push it without force.
  • Create the GitHub Release from a file containing the approved notes to preserve Markdown and shell safety.
  • Bind the published release to the checked commit, exact tag, and approved notes; do not infer application deployment or operational health from a GitHub Release.
  • Verify the published tag, target commit, title, body, and release URL through the hosting API.
  • Test documented installation or update from the repository's documented release or distribution source when the release changes an installation surface.
  • Do not publish npm, PyPI, NuGet, container, or other packages unless separately authorized.
  • Do not create a community announcement as an implicit side effect.
Failure Handling
  • Before public tagging, diagnose failures and correct bounded preparation defects within scope; reuse approval only if the proposal is unchanged. Stop on unresolved prerequisites and preserve the exact state.
  • If tag publication or release creation returns an uncertain result, inspect remote tag and release identity before retrying. Report partial state and resume only the missing approved operation; never create a duplicate or overwrite conflicting content.
  • Never delete or move a published tag without explicit approval.
  • Never overwrite an existing release or use force to conceal a bad release commit.

Verdict

  • RELEASED — tag and GitHub Release point to the verified commit and remote checks pass.
  • PREPARED — proposal and evidence are complete but publication awaits approval.
  • PARTIAL — externally visible release state exists but verification or a later step failed.
  • BLOCKED — release cannot proceed safely.

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; label all five fields and state each fact once. Use controlled plain language: one fact per sentence, usually under 20 words, active voice, and one term per concept, with no synonyms for verdicts, IDs, or states. Small results may use one line per field; omit empty tables and do not copy linked artifacts:

  1. Result: The exact skill-specific verdict token first, then the 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: Release scope, canonical version changes, tag/commit, title, full proposed notes before approval or release URL afterward, validation evidence, and publication state. For PARTIAL, enumerate every externally visible object and the approval needed before deleting, moving, or replacing it.

© levnikolaevich, MIT. 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 plugins/delivery-suite/skills/ln-62-release-publisher of levnikolaevich/claude-code-skills.

Open the folder on GitHubat commit 0ce8796

Compare with similar skills

Ln 62 Release Publisher 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.

Ln 62 Release Publisher compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ln 62 Release Publisher this skilllevnikolaevich/claude-code-skills574—~2.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Setup Matt Pocock Skillsbestofjs/bestofjs3.1k20 repos~1.7kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Setup Matt Pocock Skills

    bestofjs/bestofjs

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout.

    3.1k GitHub starsUsed in 20 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

More from levnikolaevich/claude-code-skills

All 31 skills in this repo
  • Ln 53 Documentation Auditor

    levnikolaevich/claude-code-skills

    Audits documentation and comments for trust, coverage, consistency and freshness; read-only.

    574 GitHub stars~3.8k tokensUpdated 6 days ago
    Auto-check passed
  • Ln 81 Skill Reviewer

    levnikolaevich/claude-code-skills

    Reviews skill instructions, trigger boundaries and distribution contracts; not product code.

    574 GitHub stars~3.5k tokensUpdated 6 days ago
    Auto-check passed
  • Ln 11 Opportunity Evaluator

    levnikolaevich/claude-code-skills

    Evaluates new product opportunities through demand, channels and economics before committing to build.

    574 GitHub stars~3k tokensUpdated 6 days ago
    Auto-check passed
  • Ln 12 Product Requirements Builder

    levnikolaevich/claude-code-skills

    Defines product requirements, business rules and acceptance criteria for a committed intent; edits product docs only.

    574 GitHub stars~1.9k tokensUpdated 6 days ago
    Auto-check passed
  • Ln 13 Interaction Design Builder

    levnikolaevich/claude-code-skills

    Designs user flows, interaction states and mockups for a defined product scope; does not implement UI code.

    574 GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed
  • Ln 21 System Design Baseline Builder

    levnikolaevich/claude-code-skills

    Defines measurable architecture drivers and constraints before system design; edits architecture docs only.

    574 GitHub stars~2.5k tokensUpdated 6 days ago
    Auto-check passed

Works with

Categories

Questions about Ln 62 Release Publisher

What does Ln 62 Release Publisher do?

Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications. Ln 62 Release Publisher is an agent skill from levnikolaevich/claude-code-skills. Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.

When should I use Ln 62 Release Publisher?

Ln 62 Release Publisher fits situations like: development work in your project.

How do I install Ln 62 Release Publisher in Claude Code?

Run `npx skills add levnikolaevich/claude-code-skills --skill ln-62-release-publisher -a claude-code`. Or copy the skill folder (plugins/delivery-suite/skills/ln-62-release-publisher in levnikolaevich/claude-code-skills) into .claude/skills/ln-62-release-publisher in your project. Claude Code loads it when a task matches its description.

How do I install Ln 62 Release Publisher in Codex?

Run `npx skills add levnikolaevich/claude-code-skills --skill ln-62-release-publisher -a codex`. Or copy the skill folder (plugins/delivery-suite/skills/ln-62-release-publisher in levnikolaevich/claude-code-skills) into .agents/skills/ln-62-release-publisher in your project. Codex loads it when a task matches its description.

Can I use Ln 62 Release Publisher 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 levnikolaevich/claude-code-skills --skill ln-62-release-publisher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ln-62-release-publisher, .gemini/skills/ln-62-release-publisher, .github/skills/ln-62-release-publisher and .opencode/skills/ln-62-release-publisher in your project.

What does Ln 62 Release Publisher need to run?

SKILL.md names no scripts, command-line tools or credentials: Ln 62 Release Publisher is instructions for the agent only.

Does Ln 62 Release Publisher access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ln 62 Release Publisher 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 Ln 62 Release Publisher use?

Ln 62 Release Publisher is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ln 62 Release Publisher use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Ln 62 Release Publisher?

Skills that share tags, products or a category with Ln 62 Release Publisher: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Setup Matt Pocock Skills (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ln 62 Release Publisher?

levnikolaevich (a GitHub user) maintains it in levnikolaevich/claude-code-skills, which has 574 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 5, 2026.

Source: levnikolaevich/claude-code-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.