ln-61-repository-publisher SKILL.md skillA

ln-61-repository-publisher from levnikolaevich/claude-code-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add levnikolaevich/claude-code-skills/ln-61-repository-publisher@git:20261018.9ab066b

Pins git:20261018.9ab066b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
levnikolaevich/claude-code-skills
Path
plugins/delivery-suite/skills/ln-61-repository-publisher/SKILL.md
Versions recorded
6
Latest version
git:20261018.9ab066b, committed Oct 18, 2026
First version recorded
Sep 12, 2026
Size
11,979 bytes
Repository stars
589
License
MIT

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

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Repository Publisher

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

**Execution contract:** Track every checklist item as `PENDING`, `PROVEN` with observed outcome evidence, `CLEARED` with evidence its condition is absent, or `UNPROVEN` with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are 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, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add levnikolaevich/claude-code-skills/ln-61-repository-publisher@sha256:cb77d20da512a69c

The line at the top of this page pins the label git:20261018.9ab066b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lngxwbnsvcf3ddex.svg)](https://markdownregistry.com/a/art_lngxwbnsvcf3ddex)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Sep 12, 2026 and Oct 18, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261018.9ab066b latest2026-10-18 9ab066b 11,979 BA view · diff
git:20261012.161af7f2026-10-12 161af7f 11,401 BA view · diff
git:20261012.2a77c732026-10-12 2a77c73 11,600 BA view · diff
git:20261002.a5d6eab2026-10-02 a5d6eab 10,462 BA view · diff
git:20260916.dded6882026-09-16 dded688 10,047 BA view · diff
git:20260912.16a43822026-09-12 16a4382 10,163 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11979 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

levnikolaevich/claude-code-skills · 589 stars · license MIT · pushed 2026-11-05 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_lngxwbnsvcf3ddex
GET https://markdownregistry.com/api/v1/resolve?ref=levnikolaevich/claude-code-skills/ln-61-repository-publisher
GET https://markdownregistry.com/api/v1/blob/cb77d20da512a69cd6b44a41071c214a5cfc0d110f9a7e06cd313819ec38d064

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from levnikolaevich/claude-code-skills

AGENTS.md AGENTS.md file
levnikolaevich/claude-code-skills · AGENTS.md
git:20261018.9ab066b · audit A · 589 stars
CLAUDE.md CLAUDE.md file
levnikolaevich/claude-code-skills · CLAUDE.md
git:20260711.8a861bf · audit B · 589 stars
ln-21-system-design-baseline-builder SKILL.md skill
levnikolaevich/claude-code-skills · plugins/architecture-suite/skills/ln-21-system-design-baseline-builder/SKILL.md · Defines measurable architecture drivers and constraints before system design; edits architecture docs only.
git:20261018.9ab066b · audit A · 589 stars
ln-22-current-architecture-documenter SKILL.md skill
levnikolaevich/claude-code-skills · plugins/architecture-suite/skills/ln-22-current-architecture-documenter/SKILL.md · Documents current architecture from implementation evidence; does not propose a target or audit fitness.
git:20261018.9ab066b · audit A · 589 stars
ln-23-system-design-proposal-builder SKILL.md skill
levnikolaevich/claude-code-skills · plugins/architecture-suite/skills/ln-23-system-design-proposal-builder/SKILL.md · Designs target system boundaries, contracts and tradeoffs from requirements; does not plan tasks or implement.
git:20261026.bb2f0cb · audit A · 589 stars
ln-24-architecture-decision-recorder SKILL.md skill
levnikolaevich/claude-code-skills · plugins/architecture-suite/skills/ln-24-architecture-decision-recorder/SKILL.md · Records one architecture decision with alternatives, consequences and status; does not design the whole system.
git:20261026.bb2f0cb · audit A · 589 stars
ln-25-architecture-diagram-builder SKILL.md skill
levnikolaevich/claude-code-skills · plugins/architecture-suite/skills/ln-25-architecture-diagram-builder/SKILL.md · Creates evidence-backed current or target architecture diagrams; not UI design.
git:20261026.bb2f0cb · audit A · 589 stars
ln-26-architecture-migration-planner SKILL.md skill
levnikolaevich/claude-code-skills · plugins/architecture-suite/skills/ln-26-architecture-migration-planner/SKILL.md · Plans architecture migrations with compatibility, data safety, rollout and recovery; does not execute them.
git:20261026.bb2f0cb · audit A · 589 stars
ln-31-delivery-plan-builder SKILL.md skill
levnikolaevich/claude-code-skills · plugins/delivery-planning-suite/skills/ln-31-delivery-plan-builder/SKILL.md · Builds dependency-ordered delivery plans from requirements and repository evidence; read-only.
git:20261018.9ab066b · audit A · 589 stars
ln-32-test-strategy-planner SKILL.md skill
levnikolaevich/claude-code-skills · plugins/delivery-planning-suite/skills/ln-32-test-strategy-planner/SKILL.md · Plans risk-based test portfolios and acceptance evidence; does not write or execute tests.
git:20261026.bb2f0cb · audit A · 589 stars
ln-33-plan-reviewer SKILL.md skill
levnikolaevich/claude-code-skills · plugins/delivery-planning-suite/skills/ln-33-plan-reviewer/SKILL.md · Reviews a concrete implementation plan for missing decisions, feasibility and risk before execution; read-only.
git:20261026.bb2f0cb · audit A · 589 stars
ln-62-release-publisher SKILL.md skill
levnikolaevich/claude-code-skills · plugins/delivery-suite/skills/ln-62-release-publisher/SKILL.md · Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.
git:20261018.9ab066b · audit A · 589 stars

Every file in levnikolaevich/claude-code-skills

Browse by kind, by grade A, or by owner.