bowei/skills-win
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Portabilize hardcoded C:\Users\bowei paths across skill docs

Browse Source 
Replace machine-specific C:\Users\bowei\... paths in 7 skill docs with
%USERPROFILE% / $env:USERPROFILE (or $USERPROFILE in Git Bash blocks).
Conda paths use a two-layout resolver (miniconda3\envs vs .conda\envs) or
reference ~\skills_env.md CONDA_LANGGRAPH_PYTHON, since the conda location
is machine-specific. Fixes paths that resolved wrong on non-bowei machines.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
bowei
2026-07-20 20:35:43 +08:00
co-authored by Claude Opus 4.8
parent 2ad9206a88
commit fbfa060b67
7 changed files with 48 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fft-analyse/SKILL.md
+1 -1
View File
@@ -164,7 +164,7 @@ sign-extended and require no bit-width guess. When using hex columns, pass
## Skill Script Location ## Skill Script Location
``` ```
C:\Users\bowei\.claude\skills\fft-analyse\scripts\fft_analyse.py %USERPROFILE%\.claude\skills\fft-analyse\scripts\fft_analyse.py
``` ```
Always use the **absolute path** when invoking from any working directory. Always use the **absolute path** when invoking from any working directory.
fpga-goldenref-flow/SKILL.md
+8 -8
View File
@@ -25,7 +25,7 @@ description: >
```powershell ```powershell
conda run -n langgraph python ` conda run -n langgraph python `
"C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" ` "$env:USERPROFILE\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
start --input-dir "E:\<proj>\Notes" --output-dir "E:\<proj>\fpga_runs" start --input-dir "E:\<proj>\Notes" --output-dir "E:\<proj>\fpga_runs"
``` ```
@@ -41,10 +41,10 @@ conda run -n langgraph python `
| Item | Value | | Item | Value |
|---|---| |---|---|
| Root | `E:\LangGraph_Design\fpga-goldenref-flow` | | Root | `E:\LangGraph_Design\fpga-goldenref-flow` |
| Conda env | `langgraph` (`C:\Users\bowei\.conda\envs\langgraph`) | | Conda env | `langgraph` (path 见 `~\skills_env.md` 的 `CONDA_LANGGRAPH_PYTHON`) |
| Graph name | `fpga_goldenref_flow` (在 `langgraph.json` 里声明；进程内驱动直接 `build_graph()`) | | Graph name | `fpga_goldenref_flow` (在 `langgraph.json` 里声明；进程内驱动直接 `build_graph()`) |
| Default input dir | `Notes/` (contains PR00.md, Task00.md) | | Default input dir | `Notes/` (contains PR00.md, Task00.md) |
| Helper script | `C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py` | | Helper script | `%USERPROFILE%\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py` |
--- ---
@@ -63,7 +63,7 @@ conda run -n langgraph python `
Run the helper script using the `langgraph` conda environment: Run the helper script using the `langgraph` conda environment:
```powershell ```powershell
conda run -n langgraph python ` conda run -n langgraph python `
"C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" ` "$env:USERPROFILE\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
start ` start `
--input-dir "E:\<project-path>\Notes" ` --input-dir "E:\<project-path>\Notes" `
--output-dir "E:\<project-path>\fpga_runs" --output-dir "E:\<project-path>\fpga_runs"
@@ -100,7 +100,7 @@ Ask the user which model (use AskUserQuestion), offering **Opus 4.8 (default/rec
**Fable 5**, **Sonnet 4.6**. Then resume with the choice: **Fable 5**, **Sonnet 4.6**. Then resume with the choice:
```powershell ```powershell
conda run -n langgraph python ` conda run -n langgraph python `
"C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" ` "$env:USERPROFILE\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
resume --output-dir "E:\<project-path>\fpga_runs" ` resume --output-dir "E:\<project-path>\fpga_runs" `
--plan-model opus # or: fable | sonnet | a full id like claude-opus-4-8 --plan-model opus # or: fable | sonnet | a full id like claude-opus-4-8
``` ```
@@ -137,7 +137,7 @@ Wait for the user's answer before proceeding to Step 3.
**If the user approves:** **If the user approves:**
```powershell ```powershell
conda run -n langgraph python ` conda run -n langgraph python `
"C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" ` "$env:USERPROFILE\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
resume --output-dir "E:\<project-path>\fpga_runs" resume --output-dir "E:\<project-path>\fpga_runs"
``` ```
(Default behaviour is approved — no extra flag needed.) (Default behaviour is approved — no extra flag needed.)
@@ -145,7 +145,7 @@ conda run -n langgraph python `
**If the user rejects:** **If the user rejects:**
```powershell ```powershell
conda run -n langgraph python ` conda run -n langgraph python `
"C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" ` "$env:USERPROFILE\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
resume --output-dir "E:\<project-path>\fpga_runs" ` resume --output-dir "E:\<project-path>\fpga_runs" `
--rejected --feedback "<user feedback verbatim>" --rejected --feedback "<user feedback verbatim>"
``` ```
@@ -161,7 +161,7 @@ exit code 2 again with new plans — repeat Step 2.
> 额度被占满，工作流已停在断点（状态已存 SQLite，不降级）。等 codex 空出来后从断点续跑： > 额度被占满，工作流已停在断点（状态已存 SQLite，不降级）。等 codex 空出来后从断点续跑：
> ```powershell > ```powershell
> conda run -n langgraph python ` > conda run -n langgraph python `
> "C:\Users\bowei\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" ` > "$env:USERPROFILE\.claude\skills\fpga-goldenref-flow\scripts\run_fpga_local.py" `
> continue --output-dir "E:\<project-path>\fpga_runs" > continue --output-dir "E:\<project-path>\fpga_runs"
> ``` > ```
fpga-imx6-flow/SKILL.md
+6 -6
View File
@@ -29,9 +29,9 @@ file, so `start`/`resume` survive across separate process calls.
| Item | Value | | Item | Value |
|---|---| |---|---|
| Project root | `E:\LangGraph_Design\FPGA-imx6-flow` | | Project root | `E:\LangGraph_Design\FPGA-imx6-flow` |
| Conda env | `langgraph` (`C:\Users\bowei\.conda\envs\langgraph`) | | Conda env | `langgraph` (path 见 `~\skills_env.md` 的 `CONDA_LANGGRAPH_PYTHON`) |
| Graph | `app.main_graph:build_graph` (in-process; no langgraph dev) | | Graph | `app.main_graph:build_graph` (in-process; no langgraph dev) |
| Driver | `C:\Users\bowei\.claude\skills\fpga-imx6-flow\scripts\run_imx6_flow.py` | | Driver | `%USERPROFILE%\.claude\skills\fpga-imx6-flow\scripts\run_imx6_flow.py` |
| Checkpoint | `<project>\runs\skill_checkpoint.sqlite` (keyed by `--thread-id`) | | Checkpoint | `<project>\runs\skill_checkpoint.sqlite` (keyed by `--thread-id`) |
| Design source | `Notes/fpga-imx6-flow.excalidraw`, plan `Notes/Task00.md` | | Design source | `Notes/fpga-imx6-flow.excalidraw`, plan `Notes/Task00.md` |
@@ -72,8 +72,8 @@ USB-Blast 处于连接状态时给板卡上电或断电（保护 JTAG 适配器
> `conda run --no-capture-output`. The driver also re-configures its stdout to UTF-8. > `conda run --no-capture-output`. The driver also re-configures its stdout to UTF-8.
``` ```
PY = C:\Users\bowei\.conda\envs\langgraph\python.exe PY = <CONDA_LANGGRAPH_PYTHON — see ~\skills_env.md>
RUN = C:\Users\bowei\.claude\skills\fpga-imx6-flow\scripts\run_imx6_flow.py RUN = %USERPROFILE%\.claude\skills\fpga-imx6-flow\scripts\run_imx6_flow.py
``` ```
## Step 0 — Confirm the environment (REQUIRED before driving) ## Step 0 — Confirm the environment (REQUIRED before driving)
@@ -83,8 +83,8 @@ Verify it before starting, so a missing env surfaces as a clear instruction rath
than a cryptic import error mid-run: than a cryptic import error mid-run:
```powershell ```powershell
$py = "C:\Users\bowei\.conda\envs\langgraph\python.exe" $py = @("$env:USERPROFILE\miniconda3\envs\langgraph\python.exe","$env:USERPROFILE\.conda\envs\langgraph\python.exe") | Where-Object { Test-Path $_ } | Select-Object -First 1
if (-not (Test-Path $py)) { Write-Host "[MISSING] langgraph env" } else { if (-not $py) { Write-Host "[MISSING] langgraph env" } else {
& $py -c "import langgraph; from langgraph.checkpoint.sqlite import SqliteSaver; from langgraph.types import Command; print('[OK] langgraph + checkpoint-sqlite')" & $py -c "import langgraph; from langgraph.checkpoint.sqlite import SqliteSaver; from langgraph.types import Command; print('[OK] langgraph + checkpoint-sqlite')"
} }
``` ```
fpga_flash/SKILL.md
+5 -5
View File
@@ -24,7 +24,7 @@ Claude 在执行前需先确认脚本的完整路径。使用 Glob 工具查找
``` ```
C:/Users/<当前用户>/.claude/skills/fpga_flash/scripts/gen_mcs.py C:/Users/<当前用户>/.claude/skills/fpga_flash/scripts/gen_mcs.py
``` ```
或直接使用默认路径：`C:/Users/bowei/.claude/skills/fpga_flash/scripts/` 或直接使用默认路径：`%USERPROFILE%/.claude/skills/fpga_flash/scripts/`
**scripts/ 目录内容：** **scripts/ 目录内容：**
``` ```
@@ -38,7 +38,7 @@ scripts/
**调用方式（Bash 工具）：** **调用方式（Bash 工具）：**
```bash ```bash
python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/<script>.py" [参数...] python "$USERPROFILE/.claude/skills/fpga_flash/scripts/<script>.py" [参数...]
``` ```
各脚本通过命令行参数接受变量（Vivado 安装目录、工程名、bit 文件路径、mcs 文件路径等），内部调用 Vivado `-mode batch -source <tcl模板> -tclargs <参数>` 完成执行，全程不产生临时文件。 各脚本通过命令行参数接受变量（Vivado 安装目录、工程名、bit 文件路径、mcs 文件路径等），内部调用 Vivado `-mode batch -source <tcl模板> -tclargs <参数>` 完成执行，全程不产生临时文件。
@@ -52,7 +52,7 @@ python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/<script>.py" [参数...
调用 `check_flash_csv.py`，检查 `xicom_cfgmem_part_table.csv` 中是否已包含 `w25q128bv-spi-x1_x2_x4`： 调用 `check_flash_csv.py`，检查 `xicom_cfgmem_part_table.csv` 中是否已包含 `w25q128bv-spi-x1_x2_x4`：
```bash ```bash
python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/check_flash_csv.py" \ python "$USERPROFILE/.claude/skills/fpga_flash/scripts/check_flash_csv.py" \
--vivado-dir "D:/Xilinx/Vivado/2018.1" --vivado-dir "D:/Xilinx/Vivado/2018.1"
``` ```
@@ -87,7 +87,7 @@ python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/check_flash_csv.py" \
用户确认后，**Claude 自动调用**： 用户确认后，**Claude 自动调用**：
```bash ```bash
python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/gen_mcs.py" \ python "$USERPROFILE/.claude/skills/fpga_flash/scripts/gen_mcs.py" \
--vivado-dir "D:/Xilinx/Vivado/2018.1" \ --vivado-dir "D:/Xilinx/Vivado/2018.1" \
--bit-file "E:/Xilinx_design/smod/SMOD_DTMB_CG/RU_golden/RU_golden.runs/impl_1/RU_golden_top.bit" \ --bit-file "E:/Xilinx_design/smod/SMOD_DTMB_CG/RU_golden/RU_golden.runs/impl_1/RU_golden_top.bit" \
--mcs-file "E:/Xilinx_design/smod/SMOD_DTMB_CG/RU_golden/RU_golden.runs/impl_1/RU_golden_smod.mcs" --mcs-file "E:/Xilinx_design/smod/SMOD_DTMB_CG/RU_golden/RU_golden.runs/impl_1/RU_golden_smod.mcs"
@@ -104,7 +104,7 @@ python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/gen_mcs.py" \
确认板卡已上电并连接 JTAG 后，**Claude 自动调用**： 确认板卡已上电并连接 JTAG 后，**Claude 自动调用**：
```bash ```bash
python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/program_flash.py" \ python "$USERPROFILE/.claude/skills/fpga_flash/scripts/program_flash.py" \
--vivado-dir "D:/Xilinx/Vivado/2018.1" \ --vivado-dir "D:/Xilinx/Vivado/2018.1" \
--flash-part "w25q128bv-spi-x1_x2_x4" \ --flash-part "w25q128bv-spi-x1_x2_x4" \
--bit-file "E:/Xilinx_design/smod/SMOD_DTMB_CG/RU_golden/RU_golden.runs/impl_1/RU_golden_top.bit" \ --bit-file "E:/Xilinx_design/smod/SMOD_DTMB_CG/RU_golden/RU_golden.runs/impl_1/RU_golden_top.bit" \
fpga_flash/Task01.md
+3 -3
View File
@@ -24,8 +24,8 @@
需要在 `SKILL.md` 中的“执行规范”或相关步骤的命令示例中进行如下调整（在后续实施时可直接修改）： 需要在 `SKILL.md` 中的“执行规范”或相关步骤的命令示例中进行如下调整（在后续实施时可直接修改）：
1. **更改执行命令**：将所有示例中的 `python` 更改为 `python.exe`。 1. **更改执行命令**：将所有示例中的 `python` 更改为 `python.exe`。
*原版：* `python "C:/Users/bowei/.claude/skills/fpga_flash/scripts/gen_mcs.py" ...` *原版：* `python "%USERPROFILE%/.claude/skills/fpga_flash/scripts/gen_mcs.py" ...`
*修改后：* `python.exe "C:/Users/bowei/.claude/skills/fpga_flash/scripts/gen_mcs.py" ...` *修改后：* `python.exe "%USERPROFILE%/.claude/skills/fpga_flash/scripts/gen_mcs.py" ...`
2. **增加跨环境路径转换指令**：在 `SKILL.md` 头部或执行规范中增加一条针对 WSL 环境的强调说明： 2. **增加跨环境路径转换指令**：在 `SKILL.md` 头部或执行规范中增加一条针对 WSL 环境的强调说明：
> **【WSL 跨环境执行重点约束】** > **【WSL 跨环境执行重点约束】**
@@ -39,7 +39,7 @@ OpenClaw 对 `SKILL.md` 的支持与 Claude Code 兼容。可以通过以下方
在 WSL 中执行 OpenClaw 的 skill 安装命令，直接指向包含 `SKILL.md` 的目录。例如： 在 WSL 中执行 OpenClaw 的 skill 安装命令，直接指向包含 `SKILL.md` 的目录。例如：
```bash ```bash
openclaw skills install /mnt/c/Users/bowei/.claude/skills/fpga_flash openclaw skills install /mnt/c/Users/<当前用户>/.claude/skills/fpga_flash
``` ```
*(注：根据 OpenClaw `skills --help` 的提示，`install` 指令支持本地路径安装。)* *(注：根据 OpenClaw `skills --help` 的提示，`install` 指令支持本地路径安装。)*
langgraph-plan-review/SKILL.md
+19 -16
View File
@@ -5,7 +5,7 @@ description: Use the LangGraph plan-review workflow from the current Claude Code
# LangGraph Plan Review Workflow # LangGraph Plan Review Workflow
Use this skill to run the LangGraph plan-review workflow. All scripts are bundled under the skill's own `scripts\` directory (`C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\`) — no dependency on `E:\LangGraph_Design\lab00`. Use this skill to run the LangGraph plan-review workflow. All scripts are bundled under the skill's own `scripts\` directory (`%USERPROFILE%\.claude\skills\langgraph-plan-review\scripts\`) — no dependency on `E:\LangGraph_Design\lab00`.
## 运行方式：进程内驱动，无 dev server（2026-07 起） ## 运行方式：进程内驱动，无 dev server（2026-07 起）
@@ -16,8 +16,9 @@ Use this skill to run the LangGraph plan-review workflow. All scripts are bundle
- **入口**：用 `langgraph` conda 环境的 python 跑 `clean_run.py`： - **入口**：用 `langgraph` conda 环境的 python 跑 `clean_run.py`：
```powershell ```powershell
$PY = "C:\Users\bowei\.conda\envs\langgraph\python.exe" # CONDA_LANGGRAPH_PYTHON from ~\skills_env.md; resolves either conda layout.
$RUN = "C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\clean_run.py" $PY = @("$env:USERPROFILE\miniconda3\envs\langgraph\python.exe","$env:USERPROFILE\.conda\envs\langgraph\python.exe") | Where-Object { Test-Path $_ } | Select-Object -First 1
$RUN = "$env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\clean_run.py"
# 首次（到 write_plan 中断）： # 首次（到 write_plan 中断）：
& $PY $RUN --task-id 10 --work-dir "<work_dir>" --notes-dir Notes --prompt "<原始请求>" & $PY $RUN --task-id 10 --work-dir "<work_dir>" --notes-dir Notes --prompt "<原始请求>"
# resume（写完/改完 Task10.md 后；resume 值 base64(JSON)）： # resume（写完/改完 Task10.md 后；resume 值 base64(JSON)）：
@@ -61,7 +62,7 @@ conda run -n langgraph langgraph --version
| `langgraph-sdk` | Python client used by `run_workflow.py` to submit runs | | `langgraph-sdk` | Python client used by `run_workflow.py` to submit runs |
| `httpx` | HTTP health-check in `run_workflow.py` | | `httpx` | HTTP health-check in `run_workflow.py` |
**Codex auth** (if not already set up): `C:\Users\bowei\.codex\auth.json` must contain a valid ChatGPT OAuth token. Run `codex auth login` if the file is missing. **Codex auth** (if not already set up): `%USERPROFILE%\.codex\auth.json` must contain a valid ChatGPT OAuth token. Run `codex auth login` if the file is missing.
## Invariants ## Invariants
@@ -72,8 +73,8 @@ conda run -n langgraph langgraph --version
```powershell ```powershell
<resolved conda.exe> run -n langgraph python <resolved conda.exe> run -n langgraph python
``` ```
- Codex CLI is installed in the `langgraph` conda env as `codex.cmd` at `C:\Users\bowei\.conda\envs\langgraph\codex.cmd`. It must be invoked via `cmd /c` because `.cmd` files are not directly executable by Python subprocess on Windows. - Codex CLI is installed in the `langgraph` conda env as `codex.cmd` (path = the langgraph env from `~\skills_env.md` `CONDA_LANGGRAPH_PYTHON`, with `python.exe` → `codex.cmd`). It must be invoked via `cmd /c` because `.cmd` files are not directly executable by Python subprocess on Windows.
- Codex auth uses ChatGPT OAuth tokens stored in `C:\Users\bowei\.codex\auth.json`. No API key is needed. - Codex auth uses ChatGPT OAuth tokens stored in `%USERPROFILE%\.codex\auth.json`. No API key is needed.
- `run_langgraph.ps1` sets `CODEX_HOME` from `-CodexHome`, existing `CODEX_HOME`, or `<UserProfile>\.codex`. - `run_langgraph.ps1` sets `CODEX_HOME` from `-CodexHome`, existing `CODEX_HOME`, or `<UserProfile>\.codex`.
- **Always use `review_task.py` as the Codex review shim.** Pass it via `--codex-review-command` as a JSON array with no spaces. This shim handles all Windows-specific codex invocation requirements: `cmd /c`, stdin prompt passing, `--skip-git-repo-check`, session resume, and explicit `cwd`. - **Always use `review_task.py` as the Codex review shim.** Pass it via `--codex-review-command` as a JSON array with no spaces. This shim handles all Windows-specific codex invocation requirements: `cmd /c`, stdin prompt passing, `--skip-git-repo-check`, session resume, and explicit `cwd`.
- Keep all workflow files under `<Claude launch work_dir>\Notes` unless the user explicitly overrides `-NotesDir`. - Keep all workflow files under `<Claude launch work_dir>\Notes` unless the user explicitly overrides `-NotesDir`.
@@ -92,13 +93,13 @@ Use `manage_dev_server.ps1` to start it before the first `run_langgraph.ps1` cal
```powershell ```powershell
# Start (idempotent — safe to call even if already running) # Start (idempotent — safe to call even if already running)
C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 start $env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 start
# Stop (call once when workflow returns {"status":"done"}) # Stop (call once when workflow returns {"status":"done"})
C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 stop $env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 stop
# Status check # Status check
C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 status $env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 status
``` ```
- `start` waits up to 45 s for `http://127.0.0.1:2024/ok` to respond, then prints the Studio URL. - `start` waits up to 45 s for `http://127.0.0.1:2024/ok` to respond, then prints the Studio URL.
@@ -116,7 +117,7 @@ C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps
1. Determine `TaskId` from the user. If missing, ask for it. 1. Determine `TaskId` from the user. If missing, ask for it.
2. Start the dev server (idempotent): 2. Start the dev server (idempotent):
```powershell ```powershell
C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 start $env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 start
``` ```
Wait for the "[dev-server] Ready" line in the output. Then **immediately tell the user** in your text response: Wait for the "[dev-server] Ready" line in the output. Then **immediately tell the user** in your text response:
- that the dev server is running, and - that the dev server is running, and
@@ -127,10 +128,12 @@ C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps
> https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024 > https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
3. Start or resume the LangGraph app: 3. Start or resume the LangGraph app:
```powershell ```powershell
# Use double backslashes (\\) in the JSON string so Windows paths are valid JSON. # Build the JSON array with ConvertTo-Json so Windows backslashes are escaped for you.
# $task_path / $latest_discuss_path / etc. are Python Template placeholders — keep them literal. # $task_path / $latest_discuss_path / etc. are Python Template placeholders — single-quote them literal.
$codexCmd = '["C:\\Users\\bowei\\.conda\\envs\\langgraph\\python.exe","C:\\Users\\bowei\\.claude\\skills\\langgraph-plan-review\\scripts\\review_task.py","$task_path","$latest_discuss_path","$codex_session_id","$work_dir"]' $PY = @("$env:USERPROFILE\miniconda3\envs\langgraph\python.exe","$env:USERPROFILE\.conda\envs\langgraph\python.exe") | Where-Object { Test-Path $_ } | Select-Object -First 1
C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\run_langgraph.ps1 ` $review = "$env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\review_task.py"
$codexCmd = ConvertTo-Json -Compress @($PY,$review,'$task_path','$latest_discuss_path','$codex_session_id','$work_dir')
& "$env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\run_langgraph.ps1" `
-TaskId <TaskId> ` -TaskId <TaskId> `
-Prompt "<original user request>" ` -Prompt "<original user request>" `
-CodexReviewCommand $codexCmd ` -CodexReviewCommand $codexCmd `
@@ -144,13 +147,13 @@ C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps
**Why `review_task.py`**: Using the shim keeps all codex-specific logic in Python, and the JSON array stays simple. **Why `review_task.py`**: Using the shim keeps all codex-specific logic in Python, and the JSON array stays simple.
`run_langgraph.ps1` base64-encodes the JSON command and resume payload before passing them through `conda run`, so normal PowerShell single-quoted JSON can be used. **Windows paths inside the JSON string must use `\\` (double backslash) to produce valid JSON**, e.g. `C:\\Users\\bowei\\...`. `run_langgraph.ps1` automatically sets `PYTHONIOENCODING=utf-8` so prompts containing Unicode (Chinese, etc.) pass through correctly. `run_langgraph.ps1` base64-encodes the JSON command and resume payload before passing them through `conda run`, so normal PowerShell single-quoted JSON can be used. **Windows paths inside the JSON string must use `\\` (double backslash) to produce valid JSON** (`ConvertTo-Json` does this for you), e.g. `%USERPROFILE%\\...`. `run_langgraph.ps1` automatically sets `PYTHONIOENCODING=utf-8` so prompts containing Unicode (Chinese, etc.) pass through correctly.
5. Inspect the command output after each resume. 5. Inspect the command output after each resume.
- Check `"status"` to determine next action: `"waiting"` means perform the next `action_required`; `"done"` means the workflow is complete. - Check `"status"` to determine next action: `"waiting"` means perform the next `action_required`; `"done"` means the workflow is complete.
- If a new `latest_discuss_path` is present in the output, read that discuss file for context. - If a new `latest_discuss_path` is present in the output, read that discuss file for context.
6. Stop when the workflow returns `{"status":"done", ...}`: 6. Stop when the workflow returns `{"status":"done", ...}`:
```powershell ```powershell
C:\Users\bowei\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 stop $env:USERPROFILE\.claude\skills\langgraph-plan-review\scripts\manage_dev_server.ps1 stop
``` ```
## Rejection File Rule ## Rejection File Rule
langgraph-vivado-install/SKILL.md
+6 -6
View File
@@ -160,7 +160,7 @@ Codex CLI 是 OpenAI 发布的命令行代码审查工具，以 npm 全局包形
在 PowerShell 中运行： 在 PowerShell 中运行：
```powershell ```powershell
$condaEnvPath = (C:\Users\bowei\miniconda3\Scripts\conda.exe run -n langgraph python -c "import sys; print(sys.prefix)").Trim() $condaEnvPath = (& "$env:USERPROFILE\miniconda3\Scripts\conda.exe" run -n langgraph python -c "import sys; print(sys.prefix)").Trim()
$codexCmd = Join-Path $condaEnvPath "codex.cmd" $codexCmd = Join-Path $condaEnvPath "codex.cmd"
if (Test-Path $codexCmd) { if (Test-Path $codexCmd) {
Write-Host "[OK] Codex CLI 已安装: $codexCmd" Write-Host "[OK] Codex CLI 已安装: $codexCmd"
@@ -176,12 +176,12 @@ if (Test-Path $codexCmd) {
首先确认 npm 可用（Node.js 需已安装在 conda 环境或系统 PATH 中）： 首先确认 npm 可用（Node.js 需已安装在 conda 环境或系统 PATH 中）：
```powershell ```powershell
C:\Users\bowei\miniconda3\Scripts\conda.exe run -n langgraph npm --version & "$env:USERPROFILE\miniconda3\Scripts\conda.exe" run -n langgraph npm --version
``` ```
- **若 npm 可用**：执行安装： - **若 npm 可用**：执行安装：
```powershell ```powershell
C:\Users\bowei\miniconda3\Scripts\conda.exe run -n langgraph npm install -g @openai/codex & "$env:USERPROFILE\miniconda3\Scripts\conda.exe" run -n langgraph npm install -g @openai/codex
``` ```
安装完成后，再次执行 2c-1 检查 `codex.cmd` 是否出现。若仍不存在，报告错误并停止，请用户手动检查 npm 全局安装路径。 安装完成后，再次执行 2c-1 检查 `codex.cmd` 是否出现。若仍不存在，报告错误并停止，请用户手动检查 npm 全局安装路径。
@@ -192,7 +192,7 @@ C:\Users\bowei\miniconda3\Scripts\conda.exe run -n langgraph npm --version
### 2c-3. 验证 Codex CLI 可执行 ### 2c-3. 验证 Codex CLI 可执行
```powershell ```powershell
$env:CODEX_HOME = "C:\Users\bowei\.codex" $env:CODEX_HOME = "$env:USERPROFILE\.codex"
cmd /c "$codexCmd" --version cmd /c "$codexCmd" --version
``` ```
@@ -203,7 +203,7 @@ cmd /c "$codexCmd" --version
### 2c-4. 验证 Codex Auth ### 2c-4. 验证 Codex Auth
Codex CLI 的认证 token 存储在 `$CODEX_HOME\auth.json`（默认 `C:\Users\bowei\.codex\auth.json`）。 Codex CLI 的认证 token 存储在 `$CODEX_HOME\auth.json`（默认 `%USERPROFILE%\.codex\auth.json`）。
```powershell ```powershell
$codexHome = if ($env:CODEX_HOME) { $env:CODEX_HOME } else { "$env:USERPROFILE\.codex" } $codexHome = if ($env:CODEX_HOME) { $env:CODEX_HOME } else { "$env:USERPROFILE\.codex" }
@@ -226,7 +226,7 @@ if (Test-Path $authFile) {
- **若 `$authOk = $true`**：继续进入 Step 3。 - **若 `$authOk = $true`**：继续进入 Step 3。
- **若 `$authOk = $false`**：停止并提示： - **若 `$authOk = $false`**：停止并提示：
> "Codex CLI 尚未完成认证，或认证已失效。请在终端运行 `codex` 并按提示完成 ChatGPT OAuth 登录，登录成功后 auth.json 将自动写入 `C:\Users\bowei\.codex\`。完成后重新触发本技能或手动继续到 Step 3。" > "Codex CLI 尚未完成认证，或认证已失效。请在终端运行 `codex` 并按提示完成 ChatGPT OAuth 登录，登录成功后 auth.json 将自动写入 `%USERPROFILE%\.codex\`。完成后重新触发本技能或手动继续到 Step 3。"
**在用户确认认证完成之前，不继续后续步骤。** **在用户确认认证完成之前，不继续后续步骤。**