ghe-checkpoint
Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
Best use case
ghe-checkpoint is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "ghe-checkpoint" skill to help with this workflow task. Context: Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ghe-checkpoint/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ghe-checkpoint Compares
| Feature / Agent | ghe-checkpoint | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
## IRON LAW: User Specifications Are Sacred **THIS LAW IS ABSOLUTE AND ADMITS NO EXCEPTIONS.** 1. **Every word the user says is a specification** - follow verbatim, no errors, no exceptions 2. **Never modify user specs without explicit discussion** - if you identify a potential issue, STOP and discuss with the user FIRST 3. **Never take initiative to change specifications** - your role is to implement, not to reinterpret 4. **If you see an error in the spec**, you MUST: - Stop immediately - Explain the potential issue clearly - Wait for user guidance before proceeding 5. **No silent "improvements"** - what seems like an improvement to you may break the user's intent **Violation of this law invalidates all work produced.** ## Background Agent Boundaries When running as a background agent, you may ONLY write to: - The project directory and its subdirectories - The parent directory (for sub-git projects) - ~/.claude (for plugin/settings fixes) - /tmp Do NOT write outside these locations. --- ## GHE_REPORTS Rule (MANDATORY) **ALL reports MUST be posted to BOTH locations:** 1. **GitHub Issue Thread** - Full report text (NOT just a link!) 2. **GHE_REPORTS/** - Same full report text (FLAT structure, no subfolders!) **Report naming:** `<TIMESTAMP>_<title or description>_(<AGENT>).md` **Timestamp format:** `YYYYMMDDHHMMSSTimezone` **ALL 11 agents write here:** Athena, Hephaestus, Artemis, Hera, Themis, Mnemosyne, Hermes, Ares, Chronos, Argos Panoptes, Cerberus **REQUIREMENTS/** is SEPARATE - permanent design documents, never deleted. **Deletion Policy:** DELETE ONLY when user EXPLICITLY orders deletion due to space constraints. --- ## Settings Awareness Respects `.claude/ghe.local.md`: - `enabled`: If false, skip checkpoint - `serena_sync`: If false, skip SERENA memory bank update - `checkpoint_interval_minutes`: Used for reminder logic --- # GitHub Elements Checkpoint **Purpose**: Save current work state to active thread. Does NOT change phases. ## Precondition - Must have an active (claimed, in-progress) thread - If no active thread, use `ghe-claim` first ## When to Use - Save progress during work - Document milestones - Record blockers - Before ending session - At meaningful state changes ## How to Execute ### Step 1: Find active thread Check for issues assigned to @me with "in-progress" label. If no active thread found: - Inform user - Suggest using `ghe-claim` to start work ### Step 2: Gather current state Collect: - Work log (what was done since last checkpoint) - Completed tasks - In-progress tasks - Pending tasks - Files changed - Commits made - Current branch - Blockers (if any) - Next action ### Step 3: Post checkpoint Spawn appropriate thread manager based on thread type: - `dev` → **dev-thread-manager** - `test` → **test-thread-manager** - `review` → **review-thread-manager** The thread manager will post formatted checkpoint to issue. ### Step 4: Sync memory Spawn **memory-sync** agent to update activeContext.md. ## Checkpoint Format ```markdown ## [<TYPE> Session N] DATE TIME UTC - @me ### Work Log - [HH:MM] Action 1 - [HH:MM] Action 2 ### State Snapshot #### Thread Type <dev | test | review> #### Completed - [x] Task 1 #### In Progress - [ ] Task 2 (N% complete) #### Pending - [ ] Task 3 #### Files Changed | File | Changes | #### Commits | Hash | Message | #### Branch `feature/branch-name` #### Blockers [None | List] #### Next Action [Specific next step] ### Scope Reminder [Phase-specific abilities and limits] ``` ## Output Confirmation that: - Checkpoint posted to issue - Memory bank updated ## Key Differentiator This skill SAVES progress without changing phases. To COMPLETE current phase and MOVE to next, use `ghe-transition` instead.
Related Skills
checkpoint
Save current progress to memory-keeper to prevent work loss.
epistemic-checkpoint
Force verification before answering questions involving versions, dates, status, or "current" state. Prevents hallucinations at the REASONING level by checking assertions.yaml and WebSearch before forming beliefs. Triggers on software versions, release status, dates, and package versions.
azure-quotas
Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".
raindrop-io
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
zlibrary-to-notebooklm
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。
discover-skills
当你发现当前可用的技能都不够合适(或用户明确要求你寻找技能)时使用。本技能会基于任务目标和约束,给出一份精简的候选技能清单,帮助你选出最适配当前任务的技能。
web-performance-seo
Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.
project-to-obsidian
将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则(默认到 00_Inbox/AI/、追加式、统一 Schema) 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】: - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建(先到 00_Inbox/AI/) - 禁止自作主张决定输出位置
obsidian-helper
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩(00_Inbox/AI/、追加式、白名单字段) 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤,不要自作主张 【禁止行为】: - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记(除非用户明确指定)
internationalizing-websites
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.
google-official-seo-guide
Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation
github-release-assistant
Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.