From ad7b0f01c077c6dbb80163c7b6f38c85bb8bfe43 Mon Sep 17 00:00:00 2001
From: "Alice (OpenClaw)" <alice@cowbay.org>
Date: Thu, 23 Apr 2026 11:34:49 +0800
Subject: [PATCH] Initial release of openclaw-auto-continue skill

---
 openclaw-auto-continue.skill    | Bin 0 -> 2311 bytes
 openclaw-auto-continue/SKILL.md | 142 ++++++++++++++++++++++++++++++++
 2 files changed, 142 insertions(+)
 create mode 100644 openclaw-auto-continue.skill
 create mode 100644 openclaw-auto-continue/SKILL.md

diff --git a/openclaw-auto-continue.skill b/openclaw-auto-continue.skill
new file mode 100644
index 0000000000000000000000000000000000000000..f3764573aa794c3117bb5b1f7a9e6c090a7d3260
GIT binary patch
literal 2311
zcmZ{mc{CJU8^8zSHQA}GV`m02V+q-^WpA-GgUL3wJ~0@L)DU58+4m*e+el?;!H_5+
zjFgFqoUFr4*|KL}KGl29ch38r?mf?QpZm}6dCs|i+@Fm#3y>Y~b7@}6bN*HQlLP@^
zKwyw}fTuq?R2dzD3sm+D48ZvYgm}XdmyZEh^229+SC1m(CI^5CIKu(}{7N=Qz!OIZ
z5a1Xx&v~tOODvWR0Py7n03`klw70fAe;$VM`US=&%=+Sw;$Pqz2TB^a^W^JIH(S(%
z*@(J(Fe*F7=}MQ~8*)CK{0Y}u0;_1QbV2A((}0fBi3@;SW~c<e6z^Sv%?tPR?~#z^
zdB)q;H=C6&!|<<el%KO8jukwqbePy(xxExpSdo~kAqJwR_bE16de2`d6#kwQpwQFf
zjnr@zzAZV9mDQB<l_I@J-H#uJqs)>1<r^0X#KM5x+t@CvJq31qgilt(hu13md~TWP
z)&s8YCarFtFbu?;o`#3#f|b0OrjF!ECxutT@@|C!hY#8lAEd{!v7@ra*w1QSu)CS-
zJlxju7Q`Lan91STzDT-%p*>*RPMe0Ttn3RDTG4iPWO$eYNT<VRg>q!R@yh6R{7@6D
z0B}=J%LJ*NdY=4LgJFfAy93eMo{KIIR6Z8|U?c^b%^^%YzW3q0i*>Pt?Bje&-`g9h
z=CyVMV#`*VmooiIYAjR>aAkIRQq4_42`J=6$gZ(y8dvW-B`>*PMcFBRE~D+^x@i_t
zke>8_IKF`edahBM0#uPC-Bq`_CK&1&p}iKiM_;EL>b&0Frj{-i9|RfboxyK4QlA>=
zZ7))Z@e)PhyMvTaaf!&S$r;)h5h@Y?BdBHbKbu}E`8nA&BEYevY3Szg9?xOK&a}+v
zvpm^6F6UVDtYa}J-Wjmy2#DNAJ?2cR^{sa52qb9G2~^%wwFUy$QfU_D_KpnX6;+d>
zqDIWu!NO&IdoU_B4t$N6!C7`k0SwEokz0fOwV~qkk+#c<HSIMu?Fm1-8Ki17PUzoL
zZwjtL0J>Qn>gCOZs(8#qyB{x6fLVDtx`B1_2Ry{FzukXe(rR&6lV8&M4}C&$sngg8
z^737)8j1{*@IAs8B5z^1!BB)BX3~`c6O?HNB7(DhCp&6#QTPtJYy^Dcepmg6@o>kN
z=Q*fz$>Tx8%L9wsfBP>_GWyN@wt7nZG8C)Ep+bpet3spPh%`u*#TP?6FMY>1nVV5!
z79p+T$ly<MgRr4?(o5ALqEe@yVeT|6*pQC^DD5dnKM84k4?OfZIa45dizD%P89so_
z^}{XelZ@r}cXrC8sQUHTrH!`f=sl!T+=$738oORj0S~O?@${M??20dqE$YVbBbsMA
zGv*rASUMTa6rQ8)6k|OoaELr}78kv?dKMTu!^*T9?0XA+VNi2YzJ#Hrt~+$R+L9)s
zQg7n~8jWy3v?z>r-o0y}D*E&u*QxQ7AfQTZlI>x&^*Ag88g;fU9sgW+XLgz>v1A+{
zaSOLZhi_gIAJyJoTzZ(c2##E*Z`JK~^SstRSP;i8&d@d=x*e!n(R!e6&%dy)bSRL~
zXF`zN5|KOWBdy~42i-l;iM?+zX_EedP8;$ums5D1H6T3v>T?;md$qatr(Gv}eeT-K
zit!2RPuQ(MDlHkZRo|>2?UP^P?#a%DrCXKTG}cx&WOOxpk6q4}cp@0<sEc)B8v|9N
z<(ir>(QGN}GvP;%qcGP3w}A<>?HKl0Op0_`PFZIrO=EKN;je~PS5IM^3{Nsq8tlgf
z#F4si+&wt@3M^yD3ut|)`Do{k&f*-zxtGg2$oo1ap&x${vpM5wE%%iLvrHN+RP)bh
zxK2)NA?X?Esq@5=C+aI$Rf0yJ(Se8UK;C9tmBSZ*+@yxOKse)daf`PzPM$*x3>=d}
zW3?wvbL#7nC3~Z`V_5Y*RBAqy?|V*6RNn5h5JFrYb*d~QprLqpeThbp7tTl9MI+>@
z*eqCe=Ay|tLw$=Nhu$$nkr$P3nADIiY}RA~TMtm18=>l5BS79ck+5(XkbC7LKBk0c
z{Ao&}Uj36gNiA*u!l%B92!b!gx)>KdPPElc##Bq6X*3+~-zp=c$)kLjghHlB<(plS
z@hhH*eCdc*sz*`u&V4(5129E|lHsv1Ib~Tl@W@{)CBZOMOY$4)m@Q8ZxVG-iM=<mI
zABLK<VSVZMjX>@AGpFY@nzH*#pP1JbNpDkOk*X7VW~IWqMDjs~QZM#gqyqO_e^&Di
zr}4|rxlH!kIIgCMOYQ)MRn|3&>kvBBd=tK?c)VqUM4*Xzm+`!iw*iFH1C*V2PF-M>
zDZr*cl1~dImh^r`+plf88Lq>-tN76Wb2KBr8N6pC)`F{|huTL#X)URJ3j{{%tFJ|2
zIdAB02{pbZgLN72`EyUqU*~G>7e*0zRk=ECAv=lRJ&|uyK6dd7Hj}IQLkxPYvSVEP
zD)26pmnC!`5#ne6+bdHiO7nbjPz31G5F}9QQr$skaGcaTiVmdtMBFMnq@tL!JP*0_
zDr`H~mb&R&#4BZ51|5zhA)0`6`d=$pP^XRVemzC9bk_AroJubIT2_Zo*_4)WH@#a|
z$e3@$tP$D=<+e{)6LJflD!U$OSWL*ATPsNZh+e!BI{A^s4aA#2(5dM$FZ!KZ?6bK$
zc#1S;+me@p?p-cX8{#}yBUo4uEW|vNhM6Jlci31hUqo@rWm&pWnV*&wj*J`9*h$FF
zyzMA8CGs?_NN#E{RnW9wG-`>Xpk}Kdr)C+!YGcjBEY9*LVG#O99e4rzMnB6x>I3U<
wefZZ8{~P`%dH4-yI>OdR+5Q>+Kb1IY@>3=LuL<j4KWAe;+U-Xt9Q5<{U#~bC8vp<R

literal 0
HcmV?d00001

diff --git a/openclaw-auto-continue/SKILL.md b/openclaw-auto-continue/SKILL.md
new file mode 100644
index 0000000..8f01c3b
--- /dev/null
+++ b/openclaw-auto-continue/SKILL.md
@@ -0,0 +1,142 @@
+---
+name: openclaw-auto-continue
+description: Use when an OpenClaw user wants auto-next, auto-continue, auto follow-up, or wants the agent to continue multi-step work in the same chat without waiting after every step.
+---
+
+# OpenClaw Auto Continue
+
+## Overview
+Use this skill when an OpenClaw agent should keep going in the same session instead of stopping after each intermediate step.
+
+This feature is exposed as the chat command:
+- `/auto-continue`
+- alias: `/ac`
+
+It is a **session-scoped switch**, not a global default.
+
+## When to Use
+Use when the user says things like:
+- "開 auto next"
+- "自動續跑"
+- "不要每一步都停下來"
+- "auto continue"
+- "auto next"
+- "checkpoint 後自己繼續"
+
+Do **not** use it when the user wants explicit approval at each step, or when the work contains risky / destructive decisions that should pause for confirmation.
+
+## Commands
+### Enable
+```text
+/ac on
+```
+Equivalent full form:
+```text
+/auto-continue on
+```
+
+### Disable
+```text
+/ac off
+```
+Equivalent full form:
+```text
+/auto-continue off
+```
+
+### Status
+```text
+/ac status
+```
+Equivalent full form:
+```text
+/auto-continue status
+```
+
+## Effective Behavior
+When enabled, the current session is configured to:
+- `queueMode = "followup"`
+- `queueDebounceMs = 0`
+- `queueCap = 1`
+- `queueDrop = "summarize"`
+
+When disabled, the session clears these queue settings and clears queued items.
+
+## Important Boundaries
+- This is **per session / per chat**, not global.
+- It does **not** mean the agent should ignore approvals, safety boundaries, or destructive-action confirmation.
+- It does **not** guarantee infinite autonomous looping; it mainly makes follow-up work in the same session continue more aggressively.
+- If the user wants it active in a specific chat, enable it in that chat.
+
+## How to Explain It to Users
+Short version:
+- "開了之後，我會比較傾向在同一串裡自動接下一步，不會每一步都停住等你推。"
+
+Practical version:
+- Good for multi-step execution
+- Good for checkpoint-then-continue behavior
+- Not ideal when the user wants to supervise each step manually
+
+## Example: Off vs On
+### When off
+Typical pattern:
+1. The agent finishes one visible step
+2. The agent reports that step
+3. The flow may pause until the user nudges again
+
+### When on
+Typical pattern:
+1. The agent finishes one visible step
+2. The agent continues into the next low-risk step in the same session
+3. The user sees fewer unnecessary pauses during multi-step work
+
+## Troubleshooting
+### `/ac` says unknown or does nothing
+Possible causes:
+- The running OpenClaw installation does not include the command yet
+- The chat is not hitting the expected installation/runtime
+- The sender is not authorized for command use on that surface
+
+Check:
+- `/ac status`
+- If needed, inspect the live install rather than a repo checkout
+
+### It still pauses sometimes
+That can be normal. Auto-continue does not override:
+- approval gates
+- safety constraints
+- destructive action confirmation
+- user-choice decision points
+
+### It worked in one chat but not another
+This is expected when the other chat/session has not enabled it yet. The setting is session-scoped.
+
+## Verification
+After enabling, verify with:
+```text
+/ac status
+```
+Expected result should indicate the session is no longer default and is using followup behavior.
+
+A practical verification flow:
+1. Run `/ac on`
+2. Run `/ac status`
+3. Give the agent a multi-step but low-risk task
+4. Confirm the agent continues without waiting after every intermediate step
+
+If you need concrete implementation evidence, the verified live installation path was:
+- `/home/chchang/.nvm/versions/node/v22.22.0/lib/node_modules/openclaw/dist/commands-handlers.runtime-Akj_Dqoi.js`
+
+## Operator Guidance
+Recommend enabling it when:
+- the user wants smooth multi-step execution
+- the user dislikes repeated nudges
+- the work is mostly deterministic and low-risk
+
+Recommend leaving it off when:
+- the user wants step-by-step supervision
+- the task has many decision gates
+- the task contains destructive or approval-heavy actions
+
+## One-Line Rule
+**`/ac on` turns on session-level auto-followup for the current chat; `/ac off` turns it back off.**