plan-to-tickets
Turn a large approved plan into small, independently verifiable agent-ready tickets with concrete acceptance criteria, verification evidence, blockers, and vertical tracer-bullet slices.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- plan-to-tickets
- license
- MIT
- version
- 0.1.0
- metadata
- { "hermes_config_kit": { "adapter": "hermes-agent-config-kit", "conversion": "adapted", "source_path": "skills/plan-to-tickets/SKILL.md", "source_repo": "AnastasiyaW/claude-code-config" } }
- description
- Turn a large approved plan into small, independently verifiable agent-ready tickets with concrete acceptance criteria, verification evidence, blockers, and vertical tracer-bullet slices.
03 SKILL.md 正文
Plan To Tickets
Source: AnastasiyaW/claude-code-config/skills/plan-to-tickets/SKILL.md.
This module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.
Plan To Tickets
Use this module when a large approved plan, PRD, feature, refactor, research plan, or multi-step coding task must be decomposed into small agent-ready tickets. Each ticket should have concrete acceptance criteria, verification evidence, explicit blockers, and a narrow vertical tracer-bullet slice. Do not use it for a small task that should be implemented directly, a single bug fix, or a chat-only summary.
This module complements the builtin plan and writing-plans modules. Those establish an implementation plan; this module turns an already understood plan into independently executable ticket contracts. It does not create tickets, publish tracker issues, run a validator, dispatch agents, or authorise implementation.
Output location
When the operator or project has not selected an issue tracker, propose local ticket files under the project-relative path:
<project>/.agent/tickets/<YYYY-MM-DD>-<slug>/
Use one Markdown file per ticket, for example:
TICKET-001-short-slug.md
Creating ticket files or publishing external issues remains subject to the project’s normal write and operator-confirmation policy.
Required ticket shape
Each ticket contains these headings:
## Status## Parent## What To Build## Acceptance Criteria## Verification## Blocked By## Notes
Mark a ticket ready-for-agent only when every acceptance criterion and verification step is concrete. Acceptance criteria use observable checklist items. Verification names at least one relevant test, command, artefact inspection, or explicit manual-review gate.
Slicing rules
- Prefer vertical tracer bullets: a narrow, complete path through the necessary layers rather than separate broad backend, UI, and test tickets.
- Make every ticket independently verifiable.
- Put preparatory refactoring first only when it makes a later slice materially smaller or safer.
- Record dependencies in
## Blocked By; useNoneonly when work can start immediately. - Avoid stale-prone paths unless current codebase evidence establishes them as a stable contract.
- Do not publish external tracker issues unless the operator selected that tracker.
Planning protocol
- Read the approved plan and the smallest current project context needed to avoid invented tickets.
- Identify the independently testable outcome and dependency boundary for each vertical slice.
- Draft tickets in dependency order with concrete acceptance criteria, evidence-producing verification, scope exclusions, and blockers.
- Review the set for overlap, hidden ordering, horizontal-only work, and tickets that cannot be verified alone.
- Before declaring the split ready, run the project’s applicable checks or perform the stated manual-review gate. If no suitable check exists, report that evidence gap rather than claiming validation.
- Report the proposed ticket directory, ready-ticket count, blocked tickets, verification evidence, and any operator decision still required.
Avoid
- Horizontal tickets that leave integration or verification to an unspecified later agent.
- "Implement feature" as an acceptance criterion.
- "Run tests" without naming the relevant check or observable artefact.
- Ticketization used to postpone a task small enough to complete directly.
- Treating ticket status as proof that implementation or verification has occurred.
04 同仓库更多 Skills
owner-voice
暂无简介
humanize-russian
Редактировать русский текст для ясности и естественного звучания, сохраняя факты, термины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст живее, отредактировать русский черновик или статью перед публикацией. Не определяет авторство и не обещает обход детекторов. Для английского — humanize-english; для структуры и доказательств — article-structure-review.
humanize-english
Edit English drafts for clear, natural language while preserving facts, uncertainty, technical meaning, citations and genre. Use when: humanize this text, remove AI-style filler, improve English prose, or edit an English article before publication. Not an authorship detector or a promise to bypass one. For Russian use humanize-russian; for thesis/evidence and structure use article-structure-review.
caveman
Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse "caveman" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman", "talk like caveman", "use caveman", "less tokens", "be brief", or Russian "пещерный режим", "говори как пещерный", "кратко", "меньше токенов", "экономь токены" — or invokes /caveman. Preserves the user's language (Russian in → Russian caveman out). Off only: "stop caveman" / "normal mode" / "обычный режим". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.
article-structure-review
Проверить структуру технической статьи после черновика: задача читателя, жанр, опора значимых утверждений на доказательства и честные ограничения. Use after the first draft, before publication. Исправлять структуру, когда это входит в запрос; не создавать обязательный конвейер из других навыков. Для локальной языковой редактуры — humanize-english или humanize-russian.
video-post-production
Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames/scenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.