dart-plan-update
GitHub用于讨论或更新DART动态计划的工作流。支持需求分类、基于证据的审查、计划修订及任务拆解,维护文档状态与优先级,确保规划与实际进展一致。
Trigger Scenarios
Install
npx skills add dartsim/dart --skill dart-plan-update -g -y
SKILL.md
Frontmatter
{
"name": "dart-plan-update",
"description": "DART Plan Update: discuss or update DART living plans"
}
dart-plan-update
Use this skill in Codex to run the DART dart-plan-update workflow. The editable
workflow source lives in .claude/commands/; this file is its generated adapter
in the shared .agents/skills/ catalog.
Invocation
- Claude Code/OpenCode:
/dart-plan-update <arguments> - Codex:
$dart-plan-update <arguments>
Treat the text after the skill name as $ARGUMENTS. When the workflow
references $1, $2, etc., map those to the positional values supplied by the
user.
Command Body
Discuss or update DART living plans: $ARGUMENTS
Required Reading
@AGENTS.md @docs/ai/principles.md @docs/ai/north-star.md @docs/plans/README.md @docs/plans/dashboard.md @docs/plans/north-star-roadmap.md @docs/ai/verification.md
Workflow
- Classify the request:
- discussion-only: compare options, priority, scope, or sequencing;
- plan edit: revise
docs/plans/**or related indexes; - task derivation: turn a plan item into a bounded implementation or docs task.
- Inspect current evidence before changing plan state. Use repo docs, code,
tests, CI evidence, issue/PR state, benchmark data, or explicit maintainer
direction.
- For solver/paper implementation plans, hold the plan to
docs/ai/verification.md§ "Research Paper Implementation Evidence", record the completed slice and the next missing paper-parity gap, and keep the corpus matrix (tests,py-demos, visual artifacts, benchmark JSON, CPU reference comparisons, GPU parity) explicit about missing rows.
- For solver/paper implementation plans, hold the plan to
- Keep the plan manageable:
- revise an existing initiative before adding a duplicate;
- use stable initiative IDs when renaming, splitting, consolidating, or parking work;
- keep
docs/plans/dashboard.mdas the single source of truth for priority, status, horizon, dimension, next step, and gate. - when deriving packets or dev-task work, include the DART specification
intake from
docs/ai/orchestration.md: value, scope, non-goals, assumptions/open decisions, acceptance evidence, gates, and dependencies. Use owner-localDecision neededblocks for consequential ambiguity instead of silent defaults.
- For discussion-only requests, present the tradeoff and proposed plan delta; do not edit unless the user asks for an edit or the request already implies one.
- For plan edits, update
docs/plans/dashboard.mdfor operating state, the detailed numbered initiative file or external owner document for rationale and workstreams, anddocs/plans/north-star-roadmap.mdonly for strategic framing. - If the plan item becomes implementation work, route to
/dart-new-taskin Claude/OpenCode or$dart-new-taskin Codex, and usedocs/dev_tasks/README.mdwhen it is multi-session or needs design tracking. - Verify with
docs/ai/verification.md: use the docs-only gate for plan-only docs, and the AI docs/adapters gate set when AI docs, workflow sources, or generated adapters change. - Do not perform GitHub or remote mutations without explicit maintainer/user approval.
Output
- Request classification (discussion, plan edit, or task derivation)
- Plan files changed and the operating-state updates made
- Verification gate run
- Any routed follow-up task or
Decision neededblock recorded
Version History
-
bcd584e
Current 2026-09-02 23:40
将Claude Code路由通道更新至Fable 5.1并刷新AI工具链。
- b9fbefc 2026-07-19 11:30


