Skip to content
Development
Skill

/ln-64-community-announcer

Drafts or publishes authorized, fact-checked GitHub Discussions announcements; does not create releases.

From plugin
claude-code-skills
56631 skills
Install
$ npx -y skills add levnikolaevich/claude-code-skills --skill ln-64-community-announcer --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/ln-64-community-announcer

Context preview

The summary Claude sees to decide when to auto-load this skill.

Drafts or publishes authorized, fact-checked GitHub Discussions announcements; does not create releases.

SKILL.md

ln-64-community-announcer.SKILL.md
name: ln-64-community-announcer
description: "Drafts or publishes authorized, fact-checked GitHub Discussions announcements; does not create releases."

Community Announcer

**Goal:** Create a source-backed announcement and publish it only after the user approves the full draft.

**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

| Need | Preferred capability | Fallback | |---|---|---| | Repository identity and permissions | Authenticated GitHub CLI or connector | Public GitHub API for read-only discovery | | Discussion categories and publication | GitHub GraphQL API | Continue a draft with destination limitations; publication is `BLOCKED` without this capability | | Shipped-change evidence | Remote Git history, releases, and canonical files | Clean remote clone | | Commands, paths, names, and counts | Focused repository search and direct reads | Hosting API content reads | | Current external claims | Primary dated sources | Omit the claim when it cannot be verified | | Draft publication | Temporary Markdown file passed to the API | Safely escaped API input with read-back verification |

Prefer the hosting API over scraping rendered pages. Use the browser only to inspect presentation or a page the API cannot expose.

Do not expose repository tokens, category node IDs, or other credentials in the announcement. IDs may be used for the mutation but are not audience content.

Checklist

Establish scope and evidence

  • [ ] Resolve the target repository from the request or hosting client and determine whether the task is draft-only or includes publication.
  • [ ] Read the default branch and source evidence. Discover Discussions availability and a suitable category when accessible; missing publication access does not prevent a fact-checked draft.
  • [ ] For draft-only work, report destination limitations and continue. Before publication, require write access, repository/category IDs, and a suitable enabled Discussions category; do not silently publish elsewhere.
  • [ ] Identify the announcement subject from the user's request, a release, or a bounded commit range.
  • [ ] Read repository communication guidance when present, but do not require a community strategy file.
  • [ ] Read the current authoritative documentation, installation instructions, affected manifests, release notes, and relevant source diffs when present.
  • [ ] Inspect recent commits and up to three available comparable announcements for cadence, repeated claims, and house style; do not require prior announcements in a new or low-volume repository.
  • [ ] Pin shipped claims to the target remote commit or release, including release lines behind the default branch; never present an unpushed local diff as available.
  • [ ] Separate what shipped, what changed for users, migration needs, and future intent.

Classification and Style

  • [ ] Classify the announcement as release, breaking change, feature update, architecture change, or community news.
  • [ ] Choose the shortest style that explains the user outcome and its significance.
  • [ ] Match the project's voice while keeping claims understandable without internal repository context.

Draft

  • [ ] Write a specific title that names the outcome rather than saying only "update" or "announcement".
  • [ ] Open with the user problem or the most important shipped outcome.
  • [ ] Explain why the change was made using evidence from commits, docs, or release notes.
  • [ ] Summarize highlights in outcome language and name exact products, packages, plugins, skills, or components where useful.
  • [ ] Include verified installation or update commands when the reader must act.
  • [ ] Make breaking changes prominent and provide clear before-and-after migration steps; follow repository format rather than requiring a particular callout label.
  • [ ] Link to canonical documentation at the default branch or immutable release tag as appropriate.
  • [ ] Include a short "What's next" section only for committed or clearly labelled tentative work.
  • [ ] Thank verified external contributors by handle; omit the section for solo work.
  • [ ] End with one genuine, answerable feedback question when community input would be useful.

Fact Check

  • [ ] Verify claims about availability and measured effects against the actual release, deployment, or outcome evidence; distinguish announced plans from available capabilities.
  • [ ] Verify every command against current authoritative documentation and any stable package, plugin, or marketplace identifier it uses.
  • [ ] Verify every named product, package,
Read more
Ships withclaude-code-skills

Give your AI agent a clear finish line. You ask for a fix and get a new abstraction. A review lists generic advice. The agent says “done,” but you still have to work out what it checked.

Get the whole plugin

Other skills on claude-code-skills.