skills/new-chat-ready/SKILL.md
Prepare seamless new-chat handoff packs when a user wants to start a fresh chat, continue elsewhere, pause a long task, recover from context decay, recover a lost conversation from local Codex or Claude Code logs, preserve reusable project knowledge in Markdown, or hand work to another agent. Generates a durable handoff document, optional project-level Markdown updates such as AGENTS.md/README.md/PROJECT_SPEC.md/PROJECT_MEMORY.md, and a paste-ready next-chat prompt grounded in current task state, local conversation records, source files, specs, codemaps, validation evidence, open risks, and constraints.
npx skillsauth add huisezhiyin/sdd-riper new-chat-readyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill turns an active or recoverable past conversation into an execution handoff and a chance to preserve durable project knowledge.
It is not a generic chat summary. It should preserve the next agent's operating context: the current goal, latest recap checkpoint, workspace, decisions, files, validation evidence, risks, constraints, and the exact next action.
Use it as a cross-cutting handoff layer with SDD-RIPER, CodeMap, expcap, ordinary coding tasks, local conversation recovery, and project-level Markdown sync. SDD skills may route to this skill, but the handoff, recovery, and project sync format lives here.
Project-level sync is part of the core job, not an optional afterthought. When a project exposes long-lived knowledge files such as root PROJECT_KNOWLEDGE.md, PROJECT_MEMORY.md, PROJECT_SPEC.md, or equivalents indexed from AGENTS.md, prefer those files for stable project truth and reusable memory. Use AGENTS.md for routing, boundaries, validation expectations, and safety rules.
Use this skill when the user asks for or implies:
new chat, fresh chat, 换对话, 开新会话, 另开一轮handoff, resume pack, 交接, 接着做, 无缝续接上下文快满, 压缩上下文, 总结给下个 chat对话丢了, 恢复对话, 找回上次对话, 从 Codex/Claude 日志恢复沉淀到项目文档, 更新 AGENTS/README, 避免反复踩坑, 把经验写进项目 memoryIf the user only asks whether this capability is a good idea, answer the design question first. Create a handoff only after the user asks to do it, or when a running task clearly needs a pause/resume artifact.
For detailed trigger boundaries, read references/trigger-policy.md.
AGENTS.md;git status and touched files when in a repo;Recovery Mode:
references/recovery-from-local-logs.md;Resume / Handoff area and optionally create a separate handoff file.mydocs/handoff/YYYY-MM-DD_hh-mm_<task>_new-chat.md when the user wants a durable artifact and the workspace is writable.references/handoff-template.md.Project MD Sync Scan before finishing a handoff:
references/project-md-sync.md to classify reusable project knowledge from this conversation, recovered logs, spec, codemap, validation, and diff;AGENTS.md and existing root project knowledge files (PROJECT_KNOWLEDGE.md, PROJECT_MEMORY.md, PROJECT_SPEC.md) to find the local source of truth;Synced, Candidates not synced, and Skipped even when no files are updated;Project MD Sync Candidates before editing durable project docs unless the user explicitly asked to update them or current approval includes reverse sync;references/new-chat-prompt-template.md.Confirmed, Inferred, and Unknown facts when continuity depends on them.confirmed from logs, inferred from logs, or unknown..env contents.references/trigger-policy.md: when to proactively offer or create a new-chat handoff.references/recovery-from-local-logs.md: how to recover a lost or stale conversation from local Codex / Claude Code records.references/project-md-sync.md: how to update project-level Markdown so future chats avoid repeated learning and repeated correction.references/handoff-template.md: durable handoff document shape.references/new-chat-prompt-template.md: paste-ready prompt for the next chat.development
将 SDD-RIPER 方法论落地为严格可执行流程的重型 Harness 技能。用于辅助用户澄清最终目标、生成 codemap/context、拆分最小混沌单元、维护完整 spec、执行 RIPER 阶段门禁、阻塞高风险动作和沉淀可 new chat 恢复的本地任务轨迹。
testing
面向 GPT-5.4 等强模型和熟练用户的轻量 AI Agent Harness / checkpoint-driven coding skill。默认用户已经把任务切到基本可执行的最小混沌单元;模型自行分解、探索与推进,人类通过最终目标、最小 spec、复述、checkpoint、证据验证与回写来低干扰控盘。
development
Generate, update, or drift-check agent-facing CodeMaps as progressive code terrain indexes for projects, features, capabilities, functions, modules, or bug chains. Use when Codex needs to inspect an unfamiliar codebase, map a feature/capability from entry to effect, create or update `mydocs/codemap/*`, answer `create_codemap`, `MAP`, `PROJECT MAP`, code terrain, impact-map, "where should the agent look first", check whether existing CodeMaps are stale after a diff, or prepare SDD-RIPER Research without loading the whole repository into context.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.