跳到正文
cccskills
免费在 GitHub 公开

hs-release

Prepare and publish a core Hindsight release, then open a pull request for its changelog and announcement blog post. Covers version updates, package publication checks, and synchronization of the accompanying documentation references.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

集成工具GitHub
查看安装方法

适用场景

  • Publishing a new core Hindsight version
  • Preparing a release changelog and announcement
  • Checking release tags and publication workflows
  • Synchronizing documentation references after a release

包含的文件(1)

  • SKILL.md5.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Hindsight Release

Cut a core Hindsight release and open the accompanying changelog/blog PR. This is for the core product version (API, clients, CLI, control plane, Helm). Integrations are versioned independently — use scripts/release-integration.sh for those, not this skill.

The release is irreversible and outward-facing: it tags a version and pushes it straight to main, which triggers CI that publishes packages to PyPI / npm / Helm. Confirm the version number and that the intended fixes are already merged to main before you start.

Step 0 — Pre-flight

  1. Decide the base. A release is cut from the latest origin/main, never from a feature branch. git fetch origin --tags first. Confirm the "couple of fixes" the user means are actually merged to main (git log v<prev>..origin/main --oneline).
  2. Find where main is checked out. main is often already checked out in a sibling worktree (git worktree list). You cannot check out main in a second worktree — run the release in the worktree that already holds it. If that worktree is dirty with throwaway cruft (.next-* tsconfig paths, screenshots), git stash push -u, fast-forward to origin/main, run the release, then git stash pop.
  3. Pitfall: never pipe the checkout in an && chain like git checkout main 2>&1 | tail && git reset --hard ... — the pipe's exit status is tail's (always 0), so a failed checkout won't stop the chain and the reset fires on the wrong branch. Check out as its own command and verify git branch --show-current before resetting.

Step 1 — Cut the release

Run from the worktree on a clean main:

./scripts/release.sh <version>     # e.g. 0.8.1  (no leading v)

release.sh bumps the version in every component, regenerates the OpenAPI spec + all client SDKs, updates docs versioning, commits Release v<version>, tags v<version>, and pushes the commit and tag directly to main. The push triggers the Release GitHub Actions workflow that builds and publishes the packages. It is not a PR.

Verify after: gh run list --limit 5 should show the Release v<version> workflow running, and git ls-remote --tags origin v<version> should return the tag.

Step 2 — Changelog + blog PR (separate)

Done after the tag exists, as its own PR (precedent: v0.8.0 = #2053, v0.8.1 = #2080). Work on a branch off the new main:

git checkout -b docs-changelog-<version> origin/main

Only spin up a separate worktree (git worktree add ../hindsight-changelog-<version> -b docs-changelog-<version> origin/main) if you can't get a clean checkout otherwise — e.g. main is held in another worktree and the current one has work you don't want to disturb.

Branch naming: use the docs- (hyphen) convention, e.g. docs-changelog-0.8.1. A remote branch literally named docs exists, so any docs/... branch is rejected on push with directory file conflict.

Changelog

uv run --directory hindsight-dev generate-changelog <version>

LLM-summarizes the commits between the previous tag and v<version> and prepends an entry to hindsight-docs/src/pages/changelog/index.md.

The entry ends with a Database Migrations section listing every Alembic migration added in the range, each linking to the PR that introduced it. That section is enumerated deterministically from git (--diff-filter=A over hindsight_api/alembic/versions/), not by the LLM — don't hand-edit it, and if a migration is missing, check that its commit actually added the file in the tag range. Requires OPENAI_API_KEY (already in the repo .env). It excludes hindsight-integrations/ source, but new integrations whose commits also touched docs will still appear — that matches precedent, leave them in the changelog.

Blog post

Hand-write hindsight-docs/blog/YYYY-MM-DD-version-X-Y-Z.md (mirror an existing one; patch releases are short — see 2026-06-02-version-0-7-2.md). Guidance:

  • Explain user impact, not internals/mechanism. Lead with what the user can now do and what to set. Config/env-var names are fine (developer-facing), code symbols and internals are not.
  • Do not list integrations in the release blog. The core blog covers core engine / API / ops changes; each integration ships its own changelog. (Integrations may still appear in the generated changelog/index.md — that's fine; just keep them out of the blog.)
  • Call out an upgrade recommendation when there are operational/data-integrity fixes.
  • Validate formatting: npx prettier --check <blog file>.

Sync the docs skill

./scripts/generate-docs-skill.sh

Refreshes skills/hindsight-docs/references/changelog/index.md. It will also bump skills/hindsight-docs/references/openapi.json by one version — release.sh regenerates the skill before bumping OpenAPI, so the skill copy lags a version in the release commit; this step syncs it. Expect a one-line version diff there; keep it.

Commit, push, PR

git add -A
git commit --no-verify -m "docs: changelog and blog post for v<version>"
git push -u origin docs-changelog-<version>
gh pr create --base main --title "docs: changelog and blog post for v<version>" --body "..."

Expected files in the PR: the changelog entry, the new blog post, the regenerated skill changelog mirror, and the skill openapi.json version sync.

Cleanup

If you created a temporary worktree, remove it once the PR is up (git worktree remove ../hindsight-changelog-<version>; the branch stays on origin). Restore any stash you popped in Step 0.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Record task handoffs between Bots in shared Hindsight memory, including progress, remaining work, sources, and caveats. Other Bots can retrieve the record later, continue unfinished work, and report the outcome back through shared memory.

中文简介正在准备中。当前显示英语简介。

  • Handing unfinished work to another Bot
  • Resuming a task started by another Bot
  • Sharing findings with Bots outside the current conversation
vectorize-io/hindsight5.2万2026年10月19日 更新

Review changed code against project rules and report missing tests, unused code, typing problems, and style violations. It also checks API design and data isolation, helping developers identify issues after implementation.

中文简介正在准备中。当前显示英语简介。

  • Reviewing changes after implementation
  • Finding missing tests and unused code
  • Checking Python types and API design
vectorize-io/hindsight5.2万2026年10月19日 更新

Create a specialized Claude Code subagent with Hindsight long-term memory. Start with an empty agent or import prepared documents, then equip it with knowledge pages and memory search to reuse information across sessions.

中文简介正在准备中。当前显示英语简介。

  • Create a specialized agent that remembers across sessions
  • Build an agent from prepared reference documents
  • Start an empty agent and add knowledge over time
vectorize-io/hindsight5.2万2026年10月19日 更新

figure

免费

Create an animated diagram showing request flows, background jobs, or feature changes. The result is a single SVG image for README files, pull requests, issues, or blog posts, with support for light and dark themes.

中文简介正在准备中。当前显示英语简介。

  • Explaining request and data flows
  • Illustrating how a background job works
  • Showing feature changes in a pull request
vectorize-io/hindsight5.2万2026年10月19日 更新

Plan how an AI application should use Hindsight memory. Identify useful information to retain, define user-scoping tags and memory bank settings, and specify how retrieved facts and synthesized knowledge should reach the model.

中文简介正在准备中。当前显示英语简介。

  • Plan memory that carries conversation context across sessions
  • Design tags that separate each user's memories
  • Plan summaries of customer preferences and recurring issues
vectorize-io/hindsight5.2万2026年10月19日 更新

Store project conventions, task outcomes, and troubleshooting lessons in a shared Hindsight Cloud memory bank. Retrieve relevant context before new work, or synthesize past experience to guide decisions and help teammates reuse what has been learned.

中文简介正在准备中。当前显示英语简介。

  • Save project coding and testing conventions
  • Share failure causes, fixes, and workarounds
  • Retrieve related lessons before starting a task
vectorize-io/hindsight5.2万2026年10月19日 更新

查看 vectorize-io 的全部技能

报告此技能的问题