AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
中文简介正在准备中。当前显示原文说明。
Create or update implementation plans in the repo's SIMPLE or COMPLEX format. Use when turning an idea, PRD, or approved direction into a saved plan artifact.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Output style: write the plan answer-first with tables/bullets and a one-line TL;DR per the canonical rule —
process/development-protocols/communication-standards.md.
Use this skill to produce the authoritative implementation plan artifact set for the project's work.
This skill is the canonical planning contract for the repo. Planning discipline previously spread across vc-plan now belongs here plus the plan-agent prompt.
Normal output is one plan file.
For large multi-phase programs, this skill instead defines how to create an umbrella plan plus
phase-plan set under one feature folder. See process/development-protocols/phase-programs.md.
Optional input: a feature idea plus simple or complex when the user already knows the intended depth.
references/generate-plan.md for the full plan contract.date +%d-%m-%y before choosing the filename.SIMPLE or COMPLEX.process/general-plans/active/{slug}_{date}/{slug}_PLAN_{date}.md (or process/features/{feature}/active/{slug}_{date}/{slug}_PLAN_{date}.md). Create the {slug}_{date}/ subfolder first. Per task-folder artefact colocation, every artefact this plan produces — the plan, any {slug}_SPEC_{date}.md, reports, and references — lives INSIDE this same task folder; never write to the deprecated sibling reports/ or references/ dirs.process/context/all-context.md when present to choose relevant context docs..claude/skills/vc-generate-plan/references/example-complex-prd.md before writing.process/context/tests/all-tests.md.*_PLAN_*.md plans, include explicit sections for Touchpoints, Public Contracts, Blast Radius, Verification Evidence, Test Infra Improvement Notes, and Resume and Execution Handoff.node .claude/skills/vc-generate-plan/scripts/validate-plan-artifact.mjs <plan-path>
process/features/{feature}/active/{slug}_{date}/ task folder when the topic maps to an existing feature folder.CODE DONE, not VERIFIED.For new or newly touched direct *_PLAN_*.md files, include all of the following sections:
Touchpoints — files, packages, or services that will be changed or readPublic Contracts — interfaces, APIs, schemas, or behaviors visible to other packages or callersBlast Radius — the scope of change: how many files, which packages, and what risk classVerification Evidence — table with columns | Gate / Scenario | Strategy | Proves SPEC criterion |; each row maps a test gate to the SPEC acceptance criterion it proves and the strategy (Fully-Automated / Hybrid / Agent-Probe)Test Infra Improvement Notes — placeholder at plan-write time ("(none identified yet)"); updated with test infrastructure gaps found during vc-test-coverage-plan and EVLResume and Execution Handoff — required sub-fields:
Validate Contract — written by vc-validate-agent after VALIDATE runs; leave a placeholder
heading during PLAN (## Validate Contract\n\n(placeholder — vc-validate-agent writes this section before EXECUTE))Use Markdown-structured sections, not a second machine-only schema. Markdown sections are stable across all agents (Claude, Codex, future systems) without requiring a parser.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
中文简介正在准备中。当前显示原文说明。
Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.
中文简介正在准备中。当前显示原文说明。
Audit project context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.
中文简介正在准备中。当前显示原文说明。
Audit active project plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.
中文简介正在准备中。当前显示原文说明。
Audit agent harness health: Claude/Codex agent parity, skill registry consistency, README.md sync, and protocol file wiring. Use when agents, skills, README.md, or development-protocol files move, split, or drift.
中文简介正在准备中。当前显示原文说明。
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
中文简介正在准备中。当前显示原文说明。