You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
5.**--full-auto for building** - auto-approves changes
264
264
6.**vanilla for reviewing** - no special flags needed
265
265
7.**Parallel is OK** - run many Codex processes at once for batch work
266
-
8.**NEVER start Codex in ~/.openclaw/** - it'll read your soul docs and get weird ideas about the org chart!
266
+
8.**NEVER start Codex inside your OpenClaw state directory** (`$OPENCLAW_STATE_DIR`, default `~/.openclaw`) - it'll read your soul docs and get weird ideas about the org chart!
267
267
9.**NEVER checkout branches in ~/Projects/openclaw/** - that's the LIVE OpenClaw instance!
If still empty, check `/data/.clawdbot/openclaw.json`:
@@ -130,7 +131,7 @@ If in watch mode: Also filter out any issue numbers already in the PROCESSED_ISS
130
131
Error handling:
131
132
132
133
- If curl returns an HTTP 401 or 403 → stop and tell the user:
133
-
> "GitHub authentication failed. Please check your apiKey in the OpenClaw dashboard or in ~/.openclaw/openclaw.json under skills.entries.gh-issues."
134
+
> "GitHub authentication failed. Please check your apiKey in the OpenClaw dashboard or in the active OpenClaw config path (`$OPENCLAW_CONFIG_PATH`, default `~/.openclaw/openclaw.json`) under `skills.entries.gh-issues`."
134
135
- If the response is an empty array (after filtering) → report "No issues found matching filters" and stop (or loop back if in watch mode).
135
136
- If curl fails or returns any other error → report the error verbatim and stop.
136
137
@@ -228,7 +229,7 @@ Run these checks sequentially via exec:
228
229
229
230
If HTTP status is not 200, stop with:
230
231
231
-
> "GitHub authentication failed. Please check your apiKey in the OpenClaw dashboard or in ~/.openclaw/openclaw.json under skills.entries.gh-issues."
232
+
> "GitHub authentication failed. Please check your apiKey in the OpenClaw dashboard or in the active OpenClaw config path (`$OPENCLAW_CONFIG_PATH`, default `~/.openclaw/openclaw.json`) under `skills.entries.gh-issues`."
232
233
233
234
5. **Check for existing PRs:**
234
235
For each confirmed issue number N, run:
@@ -362,7 +363,8 @@ You are a focused code-fix agent. Your task is to fix a single GitHub issue and
362
363
IMPORTANT: Do NOT use the gh CLI — it is not installed. Use curl with the GitHub REST API for all GitHub operations.
363
364
364
365
First, ensure GH_TOKEN is set. Check: `echo $GH_TOKEN`. If empty, read from config:
Copy file name to clipboardExpand all lines: skills/openai-whisper-api/SKILL.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -49,7 +49,7 @@ Defaults:
49
49
50
50
## API key
51
51
52
-
Set `OPENAI_API_KEY`, or configure it in `~/.openclaw/openclaw.json`. Optionally set `OPENAI_BASE_URL` (for example `http://127.0.0.1:51805/v1`) to use an OpenAI-compatible proxy or local gateway:
52
+
Set `OPENAI_API_KEY`, or configure it in the active OpenClaw config file (`$OPENCLAW_CONFIG_PATH`, default `~/.openclaw/openclaw.json`). Optionally set `OPENAI_BASE_URL` (for example `http://127.0.0.1:51805/v1`) to use an OpenAI-compatible proxy or local gateway:
Copy file name to clipboardExpand all lines: skills/sherpa-onnx-tts/SKILL.md
+7-5Lines changed: 7 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -63,26 +63,28 @@ Local TTS using the sherpa-onnx offline CLI.
63
63
64
64
## Install
65
65
66
-
1. Download the runtime for your OS (extracts into `~/.openclaw/tools/sherpa-onnx-tts/runtime`)
67
-
2. Download a voice model (extracts into `~/.openclaw/tools/sherpa-onnx-tts/models`)
66
+
1. Download the runtime for your OS (extracts into `$OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/runtime`, default `~/.openclaw/tools/sherpa-onnx-tts/runtime`)
67
+
2. Download a voice model (extracts into `$OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/models`, default `~/.openclaw/tools/sherpa-onnx-tts/models`)
68
68
69
-
Update `~/.openclaw/openclaw.json`:
69
+
Update the active OpenClaw config file (`$OPENCLAW_CONFIG_PATH`, default `~/.openclaw/openclaw.json`). Use a path inside your active state directory (`$OPENCLAW_STATE_DIR`, default `~/.openclaw`) for the runtime and model directories:
@@ -248,7 +252,7 @@ export function registerDnsCli(program: Command) {
248
252
defaultRuntime.log("");
249
253
defaultRuntime.log(
250
254
theme.muted(
251
-
"Note: enable discovery.wideArea.enabled in ~/.openclaw/openclaw.json on the gateway and restart the gateway so it writes the DNS-SD zone.",
255
+
"Note: enable discovery.wideArea.enabled in the active OpenClaw config ($OPENCLAW_CONFIG_PATH, default ~/.openclaw/openclaw.json) on the gateway and restart the gateway so it writes the DNS-SD zone.",
0 commit comments