@xiaotianxt/skills 0.1.0

package/skills/gh-review-workflow/references/workflow.md

@@ -0,0 +1,48 @@
+# Review Workflow Reference
+
+## Tool split
+
+- Use GitHub metadata tools for:
+  - latest PR lookup
+  - PR title, state, branch mapping
+  - top-level PR comments
+- Use `gh api graphql` for:
+  - inline review threads
+  - `isResolved`
+  - `isOutdated`
+  - thread file and line anchors
+  - resolving review threads
+
+## Minimal workflow
+
+1. Resolve the PR:
+   - explicit repo plus PR number if provided
+   - otherwise current branch PR through `gh pr view`
+2. Fetch review state:
+   - `python3 ~/.codex/skills/gh-review-workflow/scripts/fetch_review_state.py`
+3. Read these sections in order:
+   - `review_threads`
+   - `reviews`
+   - `conversation_comments`
+4. Collapse duplicates:
+   - many inline comments may represent one shared design concern
+5. After code changes:
+   - verify locally
+   - push
+   - resolve the addressed threads if the user asked
+
+## Response shape
+
+- Start with actionable findings.
+- Mention file or behavior area.
+- State which threads are already outdated.
+- Distinguish:
+  - must fix
+  - reasonable suggestion
+  - explanation only
+
+## Common pitfalls
+
+- Looking only at top-level PR comments misses most real review feedback.
+- `get_pull_request_reviews` style data may be incomplete for thread state; always verify with GraphQL thread reads.
+- Resolving threads before pushing verified fixes makes the PR history confusing.

package/skills/gh-review-workflow/scripts/fetch_review_state.py

@@ -0,0 +1,222 @@
+#!/usr/bin/env python3
+"""Fetch PR comments, reviews, and inline review threads from GitHub."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import subprocess
+import sys
+from typing import Any
+
+QUERY = """\
+query(
+  $owner: String!,
+  $repo: String!,
+  $number: Int!,
+  $commentsCursor: String,
+  $reviewsCursor: String,
+  $threadsCursor: String
+) {
+  repository(owner: $owner, name: $repo) {
+    pullRequest(number: $number) {
+      number
+      url
+      title
+      state
+      comments(first: 100, after: $commentsCursor) {
+        pageInfo { hasNextPage endCursor }
+        nodes {
+          id
+          body
+          createdAt
+          updatedAt
+          author { login }
+        }
+      }
+      reviews(first: 100, after: $reviewsCursor) {
+        pageInfo { hasNextPage endCursor }
+        nodes {
+          id
+          state
+          body
+          submittedAt
+          author { login }
+        }
+      }
+      reviewThreads(first: 100, after: $threadsCursor) {
+        pageInfo { hasNextPage endCursor }
+        nodes {
+          id
+          isResolved
+          isOutdated
+          path
+          line
+          diffSide
+          startLine
+          startDiffSide
+          originalLine
+          originalStartLine
+          resolvedBy { login }
+          comments(first: 100) {
+            nodes {
+              id
+              body
+              createdAt
+              updatedAt
+              author { login }
+            }
+          }
+        }
+      }
+    }
+  }
+}
+"""
+
+
+def _run(cmd: list[str], stdin: str | None = None) -> str:
+    proc = subprocess.run(cmd, input=stdin, capture_output=True, text=True)
+    if proc.returncode != 0:
+        raise RuntimeError(proc.stderr.strip() or "command failed")
+    return proc.stdout
+
+
+def _run_json(cmd: list[str], stdin: str | None = None) -> dict[str, Any]:
+    return json.loads(_run(cmd, stdin=stdin))
+
+
+def _ensure_auth() -> None:
+    try:
+        _run(["gh", "auth", "status"])
+    except RuntimeError as exc:
+        raise RuntimeError("gh auth is required; run `gh auth status` / `gh auth login`") from exc
+
+
+def _current_branch_pr() -> tuple[str, str, int]:
+    pr = _run_json(
+        [
+            "gh",
+            "pr",
+            "view",
+            "--json",
+            "number,headRepositoryOwner,headRepository",
+        ]
+    )
+    owner = pr["headRepositoryOwner"]["login"]
+    repo = pr["headRepository"]["name"]
+    number = int(pr["number"])
+    return owner, repo, number
+
+
+def _fetch_page(
+    owner: str,
+    repo: str,
+    number: int,
+    comments_cursor: str | None,
+    reviews_cursor: str | None,
+    threads_cursor: str | None,
+) -> dict[str, Any]:
+    cmd = [
+        "gh",
+        "api",
+        "graphql",
+        "-F",
+        "query=@-",
+        "-F",
+        f"owner={owner}",
+        "-F",
+        f"repo={repo}",
+        "-F",
+        f"number={number}",
+    ]
+    if comments_cursor:
+        cmd += ["-F", f"commentsCursor={comments_cursor}"]
+    if reviews_cursor:
+        cmd += ["-F", f"reviewsCursor={reviews_cursor}"]
+    if threads_cursor:
+        cmd += ["-F", f"threadsCursor={threads_cursor}"]
+    return _run_json(cmd, stdin=QUERY)
+
+
+def _fetch_all(owner: str, repo: str, number: int) -> dict[str, Any]:
+    conversation_comments: list[dict[str, Any]] = []
+    reviews: list[dict[str, Any]] = []
+    review_threads: list[dict[str, Any]] = []
+    comments_cursor = None
+    reviews_cursor = None
+    threads_cursor = None
+    pull_request = None
+
+    while True:
+        payload = _fetch_page(
+            owner,
+            repo,
+            number,
+            comments_cursor,
+            reviews_cursor,
+            threads_cursor,
+        )
+        errors = payload.get("errors")
+        if errors:
+            raise RuntimeError(json.dumps(errors, indent=2))
+
+        pr = payload["data"]["repository"]["pullRequest"]
+        if pull_request is None:
+            pull_request = {
+                "number": pr["number"],
+                "url": pr["url"],
+                "title": pr["title"],
+                "state": pr["state"],
+                "owner": owner,
+                "repo": repo,
+            }
+
+        comments = pr["comments"]
+        review_list = pr["reviews"]
+        threads = pr["reviewThreads"]
+        conversation_comments.extend(comments.get("nodes") or [])
+        reviews.extend(review_list.get("nodes") or [])
+        review_threads.extend(threads.get("nodes") or [])
+
+        comments_cursor = comments["pageInfo"]["endCursor"] if comments["pageInfo"]["hasNextPage"] else None
+        reviews_cursor = review_list["pageInfo"]["endCursor"] if review_list["pageInfo"]["hasNextPage"] else None
+        threads_cursor = threads["pageInfo"]["endCursor"] if threads["pageInfo"]["hasNextPage"] else None
+        if not (comments_cursor or reviews_cursor or threads_cursor):
+            break
+
+    return {
+        "pull_request": pull_request,
+        "conversation_comments": conversation_comments,
+        "reviews": reviews,
+        "review_threads": review_threads,
+    }
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--owner")
+    parser.add_argument("--repo")
+    parser.add_argument("--number", type=int)
+    args = parser.parse_args()
+
+    _ensure_auth()
+    if args.owner or args.repo or args.number:
+        if not (args.owner and args.repo and args.number):
+            raise RuntimeError("pass --owner, --repo, and --number together")
+        owner, repo, number = args.owner, args.repo, args.number
+    else:
+        owner, repo, number = _current_branch_pr()
+
+    result = _fetch_all(owner, repo, number)
+    json.dump(result, sys.stdout, indent=2)
+    sys.stdout.write("\n")
+    return 0
+
+
+if __name__ == "__main__":
+    try:
+        raise SystemExit(main())
+    except RuntimeError as exc:
+        print(str(exc), file=sys.stderr)
+        raise SystemExit(1)

package/skills/gh-review-workflow/scripts/resolve_review_threads.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Resolve GitHub PR review threads by id or from a saved review-state JSON dump."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+MUTATION = """\
+mutation($threadId: ID!) {
+  resolveReviewThread(input: {threadId: $threadId}) {
+    thread {
+      id
+      isResolved
+    }
+  }
+}
+"""
+
+
+def _run(cmd: list[str], stdin: str | None = None) -> str:
+    proc = subprocess.run(cmd, input=stdin, capture_output=True, text=True)
+    if proc.returncode != 0:
+        raise RuntimeError(proc.stderr.strip() or "command failed")
+    return proc.stdout
+
+
+def _thread_ids_from_json(path: Path) -> list[str]:
+    data = json.loads(path.read_text())
+    ids = []
+    for thread in data.get("review_threads", []):
+        if not thread.get("isResolved"):
+            ids.append(thread["id"])
+    return ids
+
+
+def _resolve(thread_id: str) -> dict[str, object]:
+    payload = _run(
+        [
+            "gh",
+            "api",
+            "graphql",
+            "-f",
+            f"query={MUTATION}",
+            "-F",
+            f"threadId={thread_id}",
+        ]
+    )
+    return json.loads(payload)
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("thread_ids", nargs="*")
+    parser.add_argument("--from-json", type=Path)
+    args = parser.parse_args()
+
+    thread_ids = list(args.thread_ids)
+    if args.from_json is not None:
+        thread_ids.extend(_thread_ids_from_json(args.from_json))
+    if not thread_ids:
+        raise RuntimeError("provide thread ids or --from-json")
+
+    seen = set()
+    for thread_id in thread_ids:
+        if thread_id in seen:
+            continue
+        seen.add(thread_id)
+        result = _resolve(thread_id)
+        json.dump(result, sys.stdout)
+        sys.stdout.write("\n")
+    return 0
+
+
+if __name__ == "__main__":
+    try:
+        raise SystemExit(main())
+    except RuntimeError as exc:
+        print(str(exc), file=sys.stderr)
+        raise SystemExit(1)

package/skills/github/SKILL.md

@@ -0,0 +1,74 @@
+---
+name: github
+description: Triage and orient GitHub repository, pull request, and issue work through local GitHub MCP tools and the `gh` CLI. Use when the user asks for general GitHub help, wants PR or issue summaries, or needs repository context before choosing a more specific GitHub workflow.
+---
+
+# GitHub
+
+## Overview
+
+Use this skill as the umbrella entrypoint for general GitHub work. It should decide whether the task stays in repo and PR triage or should be handed off to a more specific review, CI, or publish workflow.
+
+This workflow is intentionally hybrid:
+
+- Prefer local GitHub MCP tools for repository, issue, pull request, comment, label, reaction, and PR creation workflows.
+- Use local `git` and `gh` only when the connector does not cover the job well, especially for current-branch PR discovery, branch creation, commit and push, `gh auth status`, and GitHub Actions log inspection.
+- Keep connector state and local checkout context aligned. If the request is about the current branch, resolve the local repo and branch before acting.
+
+Once the intent is clear, route to the specialist skill immediately and do not keep broad GitHub triage in scope longer than needed.
+
+## Connector-First Responsibilities
+
+Handle these directly in this skill when the request does not need a narrower specialist workflow:
+
+- repository orientation once the repo, PR, issue, or local checkout is identified
+- recent PR or issue triage
+- PR metadata summaries
+- PR patch inspection
+- PR comments, labels, and reactions
+- issue lookup and summarization
+- PR creation after a branch is already pushed
+
+Prefer GitHub MCP tools for those flows because they provide structured PR, issue, and review-adjacent data without depending on a local checkout. If the repository is not already identifiable from the user request or local git context, ask for the repo instead of pretending there is a repo-search flow that may not exist.
+
+## Routing Rules
+
+1. Resolve the operating context first:
+   - If the user provides a repository, PR number, issue number, or URL, use that.
+   - If the request is about "this branch" or "the current PR", resolve local git context and use `gh` only as needed to discover the branch PR.
+   - If the repository is still ambiguous after local inspection, ask for the repo identifier.
+2. Classify the request before taking action:
+   - `repo or PR triage`: summarize PRs, issues, patches, comments, labels, reactions, or repository state
+   - `review follow-up`: unresolved review threads, requested changes, or inline review feedback
+   - `CI debugging`: failing checks, Actions logs, or CI root-cause analysis
+   - `publish changes`: create or switch branches, stage changes, commit, push, and open a draft PR
+3. Route to the specialist skill as soon as the category is clear:
+   - Review comments and requested changes: `../gh-review-workflow/SKILL.md`
+   - Failing GitHub Actions checks: `../gh-fix-ci/SKILL.md`
+   - Commit, push, and open PR: `../yeet/SKILL.md`
+4. Keep the hybrid model consistent after routing:
+   - GitHub MCP first for PR and issue data
+   - local `git` and `gh` only for the specific gaps the connector does not cover
+
+## Default Workflow
+
+1. Resolve repository and item scope.
+2. Gather structured PR or issue context through GitHub MCP tools.
+3. Decide whether the task stays in connector-backed triage or needs a specialist skill.
+4. Route immediately when the work becomes review follow-up, CI debugging, or publish workflow.
+5. End with a clear summary of what was inspected, what changed, and what remains.
+
+## Output Expectations
+
+- For triage requests, return a concise summary of the repository, PR, or issue state and the next likely action.
+- For mixed requests, tell the user which specialist path you are taking and why.
+- For GitHub MCP write actions, restate the exact PR, issue, label, or reaction target before applying the change.
+- Never imply that GitHub Actions logs are available through GitHub MCP alone. That remains a `gh` workflow.
+
+## Examples
+
+- "Use GitHub to summarize the open PRs in this repo and tell me what needs attention."
+- "Help with this PR."
+- "Review the latest comments on PR 482 and tell me what is actionable."
+- "Debug the failing checks on this branch."
+- "Commit these changes, push them, and open a draft PR."

package/skills/github/agents/openai.yaml

@@ -0,0 +1,6 @@
+interface:
+  display_name: "GitHub"
+  short_description: "Inspect PRs, issues, CI, and publish flows"
+  icon_small: "./assets/github-small.svg"
+  icon_large: "./assets/github.png"
+  default_prompt: "Use $github to inspect pull requests and issues, orient the repository context, and choose the right GitHub workflow."

package/skills/github/assets/github-small.svg

@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" viewBox="0 0 16 16">
+  <path fill="currentColor" d="M8 1.3a6.665 6.665 0 0 1 5.413 10.56 6.677 6.677 0 0 1-3.288 2.432c-.333.067-.458-.142-.458-.316 0-.226.008-.942.008-1.834 0-.625-.208-1.025-.45-1.233 1.483-.167 3.042-.734 3.042-3.292a2.58 2.58 0 0 0-.684-1.792c.067-.166.3-.85-.066-1.766 0 0-.559-.184-1.834.683a6.186 6.186 0 0 0-1.666-.225c-.567 0-1.134.075-1.667.225-1.275-.858-1.833-.683-1.833-.683-.367.916-.134 1.6-.067 1.766a2.594 2.594 0 0 0-.683 1.792c0 2.55 1.55 3.125 3.033 3.292-.192.166-.367.458-.425.891-.383.175-1.342.459-1.942-.55-.125-.2-.5-.691-1.025-.683-.558.008-.225.317.009.442.283.158.608.75.683.941.133.376.567 1.092 2.242.784 0 .558.008 1.083.008 1.242 0 .174-.125.374-.458.316a6.662 6.662 0 0 1-4.559-6.325A6.665 6.665 0 0 1 8 1.3Z"/>
+</svg>

package/skills/gws-calendar/SKILL.md

@@ -0,0 +1,126 @@
+---
+name: gws-calendar
+description: "Google Calendar: Manage calendars and events."
+metadata:
+  openclaw:
+    category: "productivity"
+    requires:
+      bins: ["gws"]
+    cliHelp: "gws calendar --help"
+---
+
+# calendar (v3)
+
+> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it.
+
+```bash
+gws calendar <resource> <method> [flags]
+```
+
+## User Calendar Policy
+
+- Treat Google Calendar as the durable source of truth for user events.
+- For this user's current setup, prefer `tianyupeiandy@gmail.com` as the default personal write calendar when the user does not specify another calendar.
+- Verify the active account before writes:
+
+```bash
+gws auth status
+```
+
+- List calendar IDs before cleanup, migration, or writes in multi-account contexts:
+
+```bash
+gws calendar calendarList list --params '{"showHidden":true,"maxResults":250}'
+```
+
+- Use stable calendar IDs, not display names, when names may be duplicated. Apple Calendar can show multiple calendars with the same name from different stores.
+- Treat school calendars such as `yupeit@andrew.cmu.edu` as transition sources unless the user explicitly asks to write there.
+- Do not fall back to Apple Calendar for writes unless the user explicitly asks for Apple Calendar.
+
+## Helper Commands
+
+| Command | Description |
+|---------|-------------|
+| [`+insert`](../gws-calendar-insert/SKILL.md) | create a new event |
+| [`+agenda`](../gws-calendar-agenda/SKILL.md) | Show upcoming events across all calendars |
+
+## API Resources
+
+### acl
+
+  - `delete` — Deletes an access control rule.
+  - `get` — Returns an access control rule.
+  - `insert` — Creates an access control rule.
+  - `list` — Returns the rules in the access control list for the calendar.
+  - `patch` — Updates an access control rule. This method supports patch semantics.
+  - `update` — Updates an access control rule.
+  - `watch` — Watch for changes to ACL resources.
+
+### calendarList
+
+  - `delete` — Removes a calendar from the user's calendar list.
+  - `get` — Returns a calendar from the user's calendar list.
+  - `insert` — Inserts an existing calendar into the user's calendar list.
+  - `list` — Returns the calendars on the user's calendar list.
+  - `patch` — Updates an existing calendar on the user's calendar list. This method supports patch semantics.
+  - `update` — Updates an existing calendar on the user's calendar list.
+  - `watch` — Watch for changes to CalendarList resources.
+
+### calendars
+
+  - `clear` — Clears a primary calendar. This operation deletes all events associated with the primary calendar of an account.
+  - `delete` — Deletes a secondary calendar. Use calendars.clear for clearing all events on primary calendars.
+  - `get` — Returns metadata for a calendar.
+  - `insert` — Creates a secondary calendar.
+The authenticated user for the request is made the data owner of the new calendar.
+
+Note: We recommend to authenticate as the intended data owner of the calendar. You can use domain-wide delegation of authority to allow applications to act on behalf of a specific user. Don't use a service account for authentication. If you use a service account for authentication, the service account is the data owner, which can lead to unexpected behavior.
+  - `patch` — Updates metadata for a calendar. This method supports patch semantics.
+  - `update` — Updates metadata for a calendar.
+
+### channels
+
+  - `stop` — Stop watching resources through this channel
+
+### colors
+
+  - `get` — Returns the color definitions for calendars and events.
+
+### events
+
+  - `delete` — Deletes an event.
+  - `get` — Returns an event based on its Google Calendar ID. To retrieve an event using its iCalendar ID, call the events.list method using the iCalUID parameter.
+  - `import` — Imports an event. This operation is used to add a private copy of an existing event to a calendar. Only events with an eventType of default may be imported.
+Deprecated behavior: If a non-default event is imported, its type will be changed to default and any event-type-specific properties it may have will be dropped.
+  - `insert` — Creates an event.
+  - `instances` — Returns instances of the specified recurring event.
+  - `list` — Returns events on the specified calendar.
+  - `move` — Moves an event to another calendar, i.e. changes an event's organizer. Note that only default events can be moved; birthday, focusTime, fromGmail, outOfOffice and workingLocation events cannot be moved.
+  - `patch` — Updates an event. This method supports patch semantics.
+  - `quickAdd` — Creates an event based on a simple text string.
+  - `update` — Updates an event.
+  - `watch` — Watch for changes to Events resources.
+
+### freebusy
+
+  - `query` — Returns free/busy information for a set of calendars.
+
+### settings
+
+  - `get` — Returns a single user setting.
+  - `list` — Returns all user settings for the authenticated user.
+  - `watch` — Watch for changes to Settings resources.
+
+## Discovering Commands
+
+Before calling any API method, inspect it:
+
+```bash
+# Browse resources and methods
+gws calendar --help
+
+# Inspect a method's required params, types, and defaults
+gws schema calendar.<resource>.<method>
+```
+
+Use `gws schema` output to build your `--params` and `--json` flags.

package/skills/gws-calendar-agenda/SKILL.md

@@ -0,0 +1,52 @@
+---
+name: gws-calendar-agenda
+version: 1.0.0
+description: "Google Calendar: Show upcoming events across all calendars."
+metadata:
+  openclaw:
+    category: "productivity"
+    requires:
+      bins: ["gws"]
+    cliHelp: "gws calendar +agenda --help"
+---
+
+# calendar +agenda
+
+> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it.
+
+Show upcoming events across all calendars
+
+## Usage
+
+```bash
+gws calendar +agenda
+```
+
+## Flags
+
+| Flag | Required | Default | Description |
+|------|----------|---------|-------------|
+| `--today` | — | — | Show today's events |
+| `--tomorrow` | — | — | Show tomorrow's events |
+| `--week` | — | — | Show this week's events |
+| `--days` | — | — | Number of days ahead to show |
+| `--calendar` | — | — | Filter to specific calendar name or ID |
+
+## Examples
+
+```bash
+gws calendar +agenda
+gws calendar +agenda --today
+gws calendar +agenda --week --format table
+gws calendar +agenda --days 3 --calendar 'Work'
+```
+
+## Tips
+
+- Read-only — never modifies events.
+- Queries all calendars by default; use --calendar to filter.
+
+## See Also
+
+- [gws-shared](../gws-shared/SKILL.md) — Global flags and auth
+- [gws-calendar](../gws-calendar/SKILL.md) — All manage calendars and events commands

package/skills/gws-calendar-insert/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: gws-calendar-insert
+description: "Google Calendar: Create a new event."
+metadata:
+  openclaw:
+    category: "productivity"
+    requires:
+      bins: ["gws"]
+    cliHelp: "gws calendar +insert --help"
+---
+
+# calendar +insert
+
+> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it.
+
+create a new event
+
+## Usage
+
+```bash
+gws calendar +insert --summary <TEXT> --start <TIME> --end <TIME>
+```
+
+## Target Calendar Rules
+
+- Always state the active Google account and target calendar before writing.
+- In multi-account setups, prefer an explicit `--calendar <calendarId>` instead of relying on `primary`.
+- For this user's current setup, when the user says "my calendar" or gives no target, use `--calendar tianyupeiandy@gmail.com` after `gws auth status` confirms the active user is `tianyupeiandy@gmail.com`.
+- Do not write durable events to Apple Calendar, iCloud, or school calendars as a fallback.
+- If multiple calendars share the same display name, list calendars and use the ID:
+
+```bash
+gws calendar calendarList list --params '{"showHidden":true,"maxResults":250}'
+```
+
+## Flags
+
+| Flag | Required | Default | Description |
+|------|----------|---------|-------------|
+| `--calendar` | — | primary | Calendar ID (default: primary) |
+| `--summary` | ✓ | — | Event summary/title |
+| `--start` | ✓ | — | Start time (ISO 8601, e.g., 2024-01-01T10:00:00Z) |
+| `--end` | ✓ | — | End time (ISO 8601) |
+| `--location` | — | — | Event location |
+| `--description` | — | — | Event description/body |
+| `--attendee` | — | — | Attendee email (can be used multiple times) |
+
+## Examples
+
+```bash
+gws calendar +insert --summary 'Standup' --start '2026-06-17T09:00:00-07:00' --end '2026-06-17T09:30:00-07:00'
+gws calendar +insert --summary 'Review' --start ... --end ... --attendee alice@example.com
+```
+
+## Tips
+
+- Use RFC3339 format for times (e.g. 2026-06-17T09:00:00-07:00).
+- For recurring events or conference links, use the raw API instead.
+
+> [!CAUTION]
+> This is a **write** command — confirm with the user before executing.
+
+## See Also
+
+- [gws-shared](../gws-shared/SKILL.md) — Global flags and auth
+- [gws-calendar](../gws-calendar/SKILL.md) — All manage calendars and events commands