xonika9/agent-skills / .claude/skills/release
release
VerifiedUse for this repository when the maintainer asks to prepare or publish a release — «подготовь релиз», «выпусти релиз», "prepare a release", "publish the release". Do not use for ordinary changelog edits, package validation, commits, pushes, or pull requests that are not explicitly a release.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.5 KB |
| references/checks.md | markdown | 2.8 KB |
| references/version-confirmation.md | markdown | 1.4 KB |
| scripts/check_global_files.py | script | 2.3 KB |
| scripts/check_skill_links.py | script | 4.7 KB |
references/version-confirmation.md
View on GitHub# Calendar versioning
Use `YY.M.D.N`, for example `26.11.3.1`. The year has two digits; month and
day have no leading zeros; together they represent a valid date in 2000–2099.
`N` is a positive integer without leading zeros, starts at 1 each day, and increases for further releases that day.
The date is determined in `Europe/Moscow`; GitHub tags retain the `v` prefix.
After fetching public tags, `python3 scripts/prepare_release.py --next-version`
selects today's next number. Historical semantic-version releases remain
immutable and do not participate in the daily sequence. Do not ask the owner
to classify the change or confirm the computed version.
An explicit owner-supplied version takes precedence when it has a valid date,
is newer than the latest public release, and has no public tag or GitHub Release.
Do not silently replace an invalid or already published number: report the
conflict and resolve only that decision. If midnight passes before publication,
keep an explicitly selected date; for an automatically selected version,
recompute it before committing and align the changelog date.
The number identifies a release date and sequence, not compatibility. Describe
incompatible behavior and migration steps under Breaking changes and Install /
update. Both plugin manifests, the changelog heading, and the release tag use
the same calendar number. Never change an existing published version or tag.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |