4K skills · sorted by relevance
Investigate a specific OpenShell problem or feature need and create a structured GitHub issue. Record observed behavior, technical findings, alternatives, and missing evidence so a human can decide what to accept and pursue.
INTERNAL/HELPER skill — do NOT invoke directly from a user query. This is the shared formatter/poster used by create-issue, create-issue-from-issue-number, and update-issue. It formats an implementation-ready GitHub Issue body, runs the pre-posting checklist, executes `gh issue create` or `gh issue edit`, and optionally posts a 確認事項 follow-up comment. Invoke this skill ONLY from one of the three parent skills via the Skill tool, after the parent has completed analysis. If a user asks to 'format an issue body' or similar, route them to the appropriate parent skill (/create-issue, /create-issue-from-issue-number, or /update-issue) rather than invoking this one directly.
The English summary is being prepared. Showing the original description.
雑な要件や思考メモからGitHub Issueを生成するスキル。 「Issueを作成して」「Issueを作って」「Issue起票して」「これをIssueにして」などのリクエストで発動。 テキスト入力や添付ファイルから要件を抽出し、構造化されたIssueを作成する。 記載されていない仕様は推測せず、不明点はユーザーに質問する。
The English summary is being prepared. Showing the original description.
依頼された内容（自然言語の説明、または既存のIssue番号）を要件とTODOに分解し、タスクごとにGitHub Issueを作成するスキル。タスクの整理・分解、複数Issueの一括作成、依存関係の明示が必要な場合に使用する。「この機能をIssueに分けて」「タスクを洗い出してIssueにして」「PRDのIssue #123 を分解して」といったリクエストで発動する。
The English summary is being prepared. Showing the original description.
Sentry の Issue 一覧 URL（例 `https://<org>.sentry.io/issues/?project=<id>&environment=<env>`）を受け取り、未解決（unresolved）の Issue を列挙して1件ずつサブエージェントで並列調査する。コード上で既に解消済みと確認できたものは Sentry 側を resolved にし、未解消のものは `create-issue` スキルで GitHub Issue を作成する。「Sentryのissueをトリアージして」「Sentryの未解決エラーをチケット化して」といった依頼で使用する。
The English summary is being prepared. Showing the original description.
INTERNAL/HELPER skill — do NOT invoke directly from a user query. This is the shared formatter/poster used by create-issue, create-issue-from-issue-number, and update-issue. It formats an implementation-ready GitHub Issue body, runs the pre-posting checklist, executes `gh issue create` or `gh issue edit`, and optionally posts a 確認事項 follow-up comment. Invoke this skill ONLY from one of the three parent skills via the Skill tool, after the parent has completed analysis. If a user asks to 'format an issue body' or similar, route them to the appropriate parent skill (/create-issue, /create-issue-from-issue-number, or /update-issue) rather than invoking this one directly.
The English summary is being prepared. Showing the original description.
repo の root に issues/ を作り、dotfiles の issues/README.md を持ち込んで issue 運用を始める。commit するかはユーザーに聞く。「issue運用を始めて」「issuesディレクトリを作って」「start-issues-ops」で発火。
The English summary is being prepared. Showing the original description.
Manage GitHub repository operations with the gh command-line tool. Classify issues, check pull request readiness, investigate failed automated checks, prepare releases and changelogs, and review dependency or exposed-secret security alerts.
Work with Jira issues through Orca's command-line interface. Search issues, move them through workflow states, create follow-up issues, and record completion with a PR or MR link and a comment using guidance matched to the installed Orca version.
Review GitHub issues and pull requests together to find duplicate work, security findings without fixes, and critical bugs without linked changes. Produce action tables and a dated report to support backlog reviews and sprint planning.
Organize GitHub issues using parent and child relationships and links showing which tasks must finish first. Use gh CLI to create, change, remove, and inspect relationships, including links across repositories.
Create GitHub issues that follow the current repository's templates. The skill selects the appropriate report format, collects required information, and prepares the title, body, labels, and issue type for review before submission.
Manage coding work from issue intake through implementation, review, deployment, and acceptance checks. Track each completion requirement against fresh evidence, with defined retry limits and explicit escalation when progress needs human input.
Fix bugs reported in GitHub issues through a reproduce-first process. The workflow guides code changes, build checks, verification, regression tests that check for recurring failures, and review before considering the fix complete.
Create a GitHub tracking issue from a merged Kilo v1 pull request, documenting behavior, edge cases, and acceptance criteria so an agent can verify or rebuild the same behavior in opencode v2.
Review OpenShell issues, pull requests, and failed main-branch checks, then build a local Markdown report with linked evidence and ranked recommendations. Saved progress helps resume an unfinished triage pass without changing GitHub.
Investigate Bifrost GitHub issues by examining reports, related code, and library documentation. Produce an implementation plan with impact analysis and regression tests, including a demonstrated failing test for bugs before requesting approval to fix them.
Turn feature requirements into a PRD, a document defining what to build, then organize development plans and GitHub Issues. Coordinate parallel agents and track progress, blockers, and next priorities through delivery.
Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, manage repository labels, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "create a label", "rename a label", "list repo labels", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.
The English summary is being prepared. Showing the original description.
Replicate and validate a GitHub issue by spinning up Archon, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Archon, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /archon or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).
The English summary is being prepared. Showing the original description.
Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.
The English summary is being prepared. Showing the original description.
Investigate duplicate OpenClaw pull requests and issues using local history and current GitHub evidence. Organize confirmed or suspected duplicates in prtags, recording the decision, confidence, and reasons for maintainers.
Turn a vague request into a precise specification through five phases and file it as a GitHub issue. Optionally start a Claude Code agent in a separate working directory to begin implementation.
Organize GitHub issues and pull requests found during quality assurance testing. Apply release tracking labels, classify bugs by four severity levels, and label multiple findings while keeping documentation issues and feature requests outside the severity scheme.