← all publishers

keli-wen

@keli-wen source repo

Report this profile Claim this profile

• 20 skills
• 0 followers
• 15 hours ago last updated

1. ▌
   Ctx Grill 2 · keli-wen

   用一场带上下文的追问把方案、决策或想法拷问到位。适用于 /ctx-grill、「拷问这个方案」「帮我把方案过一遍问题」「压测一下我的思路」，或用户希望在动手前压测自己思路的场景。先读持久 contexts（已回答的绝不再问），按「答案会不会改变方向」逐个提问并附推荐答案，边际收益递减即停，敲定的决策写回归档。仅限交互场景——CI、循环等无人值守运行中绝不可调用。
   0
   installs
2. ▌
   Ctx Research 2 · keli-wen

   基于项目持久 context 体系的深度调研。适用于 /ctx-research，触发语：「基于 context 调研 X」「结合我们的 contexts 做深度研究」。先读已有 contexts，把问题磨到真正的知识缺口上，再多智能体展开调研，关键论断做对抗验证，结论写回去。
   0
   installs
3. ▌
   Long Horizon 2 · keli-wen

   用一次长程自主运行执行一个定稿的目标——数小时的 agent 工作推完整个验收台账，人只出现在两道闸：运行前的 spec、运行后的 review。适用于 /long-horizon、「长程执行这个任务」「跑一个长程目标」，或在已有 `.long-horizon/` 工作区的仓库中恢复工作时。入口交互式反复迭代；运行由 fan-out 驱动、副作用被授权信封约束；进展只认证据；实时 report.html 以 DAG 呈现台账。
   0
   installs
4. ▌
   To Ctx 2 · keli-wen

   把当前对话的结论写成一份规范的 context 文档，放进项目 context 体系的正确位置。触发语：/to-ctx、「写进 contexts」「落个 context」「把这个结论归档」。先查放置规则（如 CONTEXT_MAP.md），按项目的既有风格写，最后汇报路径。
   0
   installs
5. ▌
   Fan Out 2 · keli-wen bundle

   把当前任务派发给多个 subagent——但先检查这次拆分到底值不值。适用于 /fan-out，触发语：「用多智能体做」「派发出去」「拆给多个 agent 并行」，或任务能拆成真正独立的子任务时。按上下文耦合度拆解，spawn prompt 用 handoff 的纪律写成任务契约。
   0
   installs
6. ▌
   Handoff 2 · keli-wen

   当另一个 agent 或 session 要接管任务或继续未完成工作时，生成最小充分交接。触发语：/handoff、「把任务交给下一个 agent」「生成 handoff」「让另一个 session 继续」、session 转移、任务所有权转移，或当前上下文退化时重开一个干净 session（交接给未来的自己）。持久 artifact 用引用不用复制，输出前抹掉 secrets。
   0
   installs
7. ▌
   Lowband 2 · keli-wen

   低带宽协作模式：用户注意力或脑力耗尽时的响应协议。当用户调用 /lowband 或 $lowband，或说「低带宽」「省脑」「脑子不够用了」「太累了，简短点」时启用；每轮持续生效，直到用户说「恢复正常」或带 off 参数再次调用。工作能力不降级，只压缩呈现、过滤决策。
   0
   installs
8. ▌
   Readout 2 · keli-wen bundle

   写出别人一遍就能读懂的回复和工作汇报：一句话只说一件事，动作放在动词里，不确定性绑在它所属的那条结论上。当用户说 /readout、「你的汇报太难读了」「说人话」「别写得像 AI」，或者需要修正某次运行的汇报风格时使用。下面的正文独立成篇：整段贴进 AGENTS.md 或 CLAUDE.md，就能每轮生效，不必调用。
   0
   installs
9. ▌
   Just Ask 2 · keli-wen

   一次性「只回答」回合——用户是在问问题，不是在派活。用 /just-ask 加问题调用（如「/just-ask 这个测试为什么会偶发失败」）。仅该回合内：只读调查、给出经过分析的回答；不改文件、不跑会改状态的命令、不写计划、不动手修。下一条消息恢复正常。以显式调用为主；用户说「只问一下，别动手」「你就解释，不用修」时同样适用。
   0
   installs
10. ▌
    Agentic Harness Patterns · keli-wen bundle

    Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
    0
    installs
11. ▌
    Agentic Harness Patterns Zh · keli-wen bundle

    AI Agent Harness 设计模式 — 记忆、权限、上下文工程、委派、技能、 Hook、Bootstrap。中文版。
    0
    installs
12. ▌
    To Ctx · keli-wen

    Turn the current conversation's conclusions into a well-formed context document filed in the project's context system. Use for /to-ctx, "file this into contexts", "turn this conclusion into a context doc". Finds the placement rules (e.g. CONTEXT_MAP.md), writes in the project's house style, and reports the path.
    0
    installs
13. ▌
    Fan Out · keli-wen bundle

    Dispatch the current task to multiple subagents — after checking that fan-out is actually justified. Use for /fan-out, when the user says "multi-agent this" or "fan out", or when a task decomposes into genuinely independent subtasks. Decomposes along context coupling, uses handoff discipline for spawn contracts.
    0
    installs
14. ▌
    Handoff · keli-wen

    Generate a minimal-sufficient handoff when another agent or session will take ownership of a task or continue unfinished work. Use for /handoff, "hand this to the next agent", "let another session continue", session transfer, task ownership transfer, or restarting in a fresh context when the current session has degraded (a handoff to your future self). Reuses durable artifacts by reference instead of copying them, and redacts secrets.
    0
    installs
15. ▌
    Lowband · keli-wen

    Low-bandwidth collaboration mode — response protocol for when the user's attention or mental capacity is depleted. Activate on /lowband or $lowband, or when the user says "too tired, keep it short", "brain is fried", "low bandwidth". Stays active every turn until the user says "back to normal" (or the equivalent in their language) or invokes with off. Work capability is not degraded; only presentation is compressed and decisions are filtered.
    0
    installs
16. ▌
    Readout · keli-wen bundle

    Write replies and work reports a person can take in on one read — one claim per sentence, action in the verb, uncertainty attached to the claim it belongs to. Use for /readout, "make your reports readable", "your output is hard to read", "stop writing like an AI", or when a run's reporting style needs fixing. The body below is standalone prose — paste it into AGENTS.md or CLAUDE.md to apply it every turn instead of on invocation.
    0
    installs
17. ▌
    Just Ask · keli-wen

    One-shot answer-only turn — the user is asking a question, not assigning work. Invoked as /just-ask with the question attached (e.g. "/just-ask why does this test flake"). For that turn only, investigate read-only and reply with an analyzed answer; do not edit files, run state-changing commands, write a plan, or start a fix. The next message returns to normal. Meant for explicit invocation; also applies when the user says "just answer, don't do anything", "just explain, don't fix it".
    0
    installs
18. ▌
    Ctx Grill · keli-wen

    Stress-test a plan, decision, or idea with a context-aware interview. Use for /ctx-grill, "grill this plan", "stress-test this plan", or when the user wants their thinking stress-tested before committing. Reads durable contexts first (never asks what they answer), asks direction-changing questions one at a time with a recommended answer, stops at diminishing returns, and files resolved decisions back. Interactive only — never invoke under CI, loops, or other non-interactive runs.
    0
    installs
19. ▌
    Ctx Research · keli-wen

    Deep research grounded in the project's durable context system. Use for /ctx-research, "ctx research", "research X starting from our contexts". Reads existing contexts first, sharpens the question to the real knowledge gap, fans out multi-agent research, verifies key claims, and files results back.
    0
    installs
20. ▌
    Long Horizon · keli-wen

    Execute a spec'd goal in one long autonomous run — hours of agent work pushing a whole acceptance ledger, with humans only at the two gates, spec before and review after. Use for /long-horizon, "make this a long-horizon goal", "run this across sessions", or when resuming work in a repo that already has a `.long-horizon/` workspace. Admission is interactive and iterative; the run is fan-out-driven and side-effect-bounded by an authorization envelope; progress is evidence-gated; a live report.html shows the ledger as a DAG.
    0
    installs