菜单
Guides the user through configuring pi — provider, model, base URL, and API key. Use when the user asks to "setup pi", "configure pi", "pi setup", "set up pi provider", "pi config", "change pi model", or invokes /pi:setup. Only run this skill when the user explicitly requests pi setup — never auto-invoke.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/FradSer/dotclaude --skill setup命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Reviews a pull request: runs its own baseline review of the PR diff, then a persistent Monitor watches CI and incoming reviewer comments, triages each comment through an independent skeptical agent, applies only verified fixes, and commits+pushes via inline git commands until CI passes and no comments remain to adopt — then asks whether to merge. Use this skill when the user asks to "review a PR", "monitor PR review comments", "address reviewer feedback on #123", or "watch CI on a pull request".
Creates atomic conventional git commits using git-agent and pushes changes to the remote repository.
Creates atomic conventional git commits using git-agent. This skill should be used when the user requests "commit", "git commit", "create commit", or wants to commit changes using AI atomic commits.
正在显示 SKILL.md
基于 SOC 职业分类
| name | setup |
| description | Guides the user through configuring pi — provider, model, base URL, and API key. Use when the user asks to "setup pi", "configure pi", "pi setup", "set up pi provider", "pi config", "change pi model", or invokes /pi:setup. Only run this skill when the user explicitly requests pi setup — never auto-invoke. |
| user-invocable | true |
| disable-model-invocation | true |
| argument-hint | [--endpoint NAME] [--provider PROVIDER] [--model MODEL] [--base-url URL] [--api-key KEY] | --edit-config | --list-models | --test | --doctor |
| allowed-tools | ["Bash(pi:*)","Bash(jq:*)","Bash(cat:*)","Bash(mkdir:*)","Bash(mv:*)","Bash(echo:*)","Bash(command -v:*)","Bash(ls:*)","Bash(vi:*)","Read","Write"] |
This skill is for human-only setup. Never invoke it automatically. Only run when the user explicitly calls /pi:setup. Configure pi's provider, model, and endpoint so /pi:delegate and /pi:review can use them without repeating flags.
command -v pi >/dev/null 2>&1
If not installed, guide the user:
npm install -g @earendil-works/pi-coding-agent
Or via the standalone installer:
curl -fsSL https://pi.dev/install.sh | sh
Then stop — do not proceed without pi installed.
Both /pi:delegate and /pi:review read from the same settings chain:
$ARGUMENTS).claude/pi.local.json — project-specific overrides, gitignored.claude/pi.json — project shared defaults, committed~/.claude/pi.local.json — global user-wide defaultsThis skill writes to ~/.claude/pi.local.json (global, takes effect for all projects).
The settings file uses the named-endpoint format shared by /pi:delegate and /pi:review. All fields are optional — only override what you want to change.
Values can reference environment variables using $VAR or ${VAR} syntax — they are resolved at read time by /pi:delegate and /pi:review. This is useful for API keys: "apiKey": "$MY_API_KEY" reads from the environment variable at runtime.
{
"endpoints": {
"local-proxy": {
"provider": "openai",
"baseUrl": "http://10.10.0.195:8317/v1",
"models": ["gemini-3.6-flash-high", "gemini-3.6-pro"]
}
},
"defaultEndpoint": "local-proxy",
"defaultModel": "gemini-3.6-flash-high",
"thinking": "max",
"withPackages": false
}
Each endpoint key has:
provider (required) — pi's known provider name (openai, anthropic, google, etc.)baseUrl (optional) — custom API endpoint; when present it is written to ~/.pi/agent/models.json at runtimeapiKey (optional) — API key or $ENV_VAR referencemodels — array of model IDs available via this endpointTop-level withPackages (default false) is the clean-mode escape hatch: when true, /pi:delegate and /pi:review load packages/skills/extensions from the pi CLI home (~/.pi, configured via pi install / pi list — not Claude Code plugins). Leave it false unless you intentionally want bridge tasks to inherit that interactive pi configuration.
Legacy flat fields (provider/model/baseUrl/apiKey) are still honored by the delegate skill as a fallback when no defaultEndpoint is set, but new setups should use the endpoint format.
--list-models flagWhen $ARGUMENTS is exactly --list-models, read the current settings and show the effective configuration:
echo "=== Current pi configuration ==="
echo "Settings file: $HOME/.claude/pi.local.json"
if [ -f "$HOME/.claude/pi.local.json" ]; then
cat "$HOME/.claude/pi.local.json"
else
echo "(not configured — pi uses its defaults)"
fi
echo ""
echo "To configure, run: /pi:setup --endpoint <name> --provider <name> --model <id> [--base-url <url>]"
echo "Or use interactive mode: /pi:setup --edit-config"
Then stop — do not proceed to setup.
--test flagWhen $ARGUMENTS includes --test, run a quick connectivity test. Build the command as an array so each flag is a distinct argument under both bash and zsh (zsh does not word-split an unquoted ${PROVIDER:+--provider ...} expansion):
CMD=(pi -p)
# Provider: use the resolved PROVIDER; else if a custom BASE_URL is set, use the
# models.json key (PROVIDER_KEY, default openai) so the probe reaches the custom endpoint.
if [ -n "$PROVIDER" ]; then
CMD+=(--provider "$PROVIDER")
elif [ -n "$BASE_URL" ]; then
CMD+=(--provider "${PROVIDER_KEY:-openai}")
fi
# Only pass --model when set — an empty --model is silently accepted by pi but the
# probe then runs without the intended model (setup never resolves MODEL itself).
[ -n "$MODEL" ] && CMD+=(--model "$MODEL")
CMD+=(--thinking low --no-session --no-context-files --approve --no-extensions --no-skills "Reply with exactly: OK. Model: <model-name>")
# </dev/null: pi -p hangs on a terminal/pipe stdin (mis-detects interactive) — force non-interactive.
"${CMD[@]}" </dev/null
Report the result: "pi responded successfully with model " on exit 0, or the error on failure.
Show the user their current configuration:
echo "=== Current pi configuration ==="
if [ -f "$HOME/.claude/pi.local.json" ]; then
cat "$HOME/.claude/pi.local.json"
else
echo "No configuration file found."
fi
If $ARGUMENTS contains flags, parse them directly:
| Flag | Description |
|---|---|
--endpoint | Endpoint key name (default local-proxy) |
--provider | LLM provider name (openai, anthropic, google, etc.) |
--model | Model ID (e.g. gemini-3.6-flash-high, claude-sonnet-4-20250514) |
--base-url | Custom API endpoint URL (OpenAI-compatible) |
--api-key | API key for the provider (stored in settings file, or reference $ENV_VAR) |
If no flags are provided, use the AskUserQuestion tool to ask the user:
openai, anthropic, google, or "Other" for custom)gemini-3.6-flash-high, claude-sonnet-4-20250514)$ENV_VAR reference? (leave empty to use environment variables)mkdir -p "$HOME/.claude"
# Read existing config
EXISTING="{}"
if [ -f "$HOME/.claude/pi.local.json" ]; then
EXISTING=$(cat "$HOME/.claude/pi.local.json")
fi
# Endpoint target: an explicit --endpoint names the key to write; otherwise reconfigure
# the existing defaultEndpoint (so a plain /pi:setup reaches the endpoint the skills read).
ENDPOINT_IS_EXPLICIT="0"
if [[ "$ARGUMENTS" == *"--endpoint"* ]]; then
ENDPOINT_IS_EXPLICIT="1"
ENDPOINT="${ENDPOINT:-local-proxy}"
else
ENDPOINT="${ENDPOINT:-$(echo "$EXISTING" | jq -r 'if .defaultEndpoint and .defaultEndpoint != "" then .defaultEndpoint else "local-proxy" end')}"
fi
# Merge into the endpoints map — only override non-empty fields.
# When an explicit --endpoint is given, make it the default so provider and model
# resolve consistently (see defaultModel note below).
echo "$EXISTING" | jq \
--arg e "$ENDPOINT" \
--arg explicit "${ENDPOINT_IS_EXPLICIT:-}" \
--arg provider "${PROVIDER:-}" \
--arg model "${MODEL:-}" \
--arg baseUrl "${BASE_URL:-}" \
--arg apiKey "${API_KEY:-}" \
'.endpoints[$e] = (.endpoints[$e] // {provider: (if $provider != "" then $provider else "openai" end)}) |
.endpoints[$e].provider = (if $provider != "" then $provider else .endpoints[$e].provider end) |
.endpoints[$e].baseUrl = (if $baseUrl != "" then $baseUrl else .endpoints[$e].baseUrl // "" end) |
.endpoints[$e].apiKey = (if $apiKey != "" then $apiKey else .endpoints[$e].apiKey // "" end) |
.endpoints[$e].models = ((.endpoints[$e].models // []) + [($model | select(. != ""))] | unique) |
.defaultEndpoint = (if $explicit == "1" then $e else (.defaultEndpoint // $e) end) |
.defaultModel = (if $model != "" then $model else .defaultModel // "" end)' \
> "$HOME/.claude/pi.local.json.tmp" && \
mv "$HOME/.claude/pi.local.json.tmp" "$HOME/.claude/pi.local.json"
--testRun the test automatically after writing config. pi has no --base-url flag — a custom endpoint goes through ~/.pi/agent/models.json. Write it there first (idempotent: register baseUrl + model, skip when unchanged), then test:
# Resolve the agent dir the same way pi-agent does, so setup writes to the
# endpoint pi actually reads (matches AGENT_DIR / PI_CODING_AGENT_DIR overrides).
AGENT_DIR="${AGENT_DIR:-${PI_CODING_AGENT_DIR:-$HOME/.pi/agent}}"
# Ensure the endpoint is in the agent-dir models.json (pi reads endpoints from there)
# Use PROVIDER_KEY for the write so $PROVIDER (possibly empty = pi's default) is untouched.
if [ -n "$BASE_URL" ]; then
PROVIDER_KEY="${PROVIDER:-openai}"
mkdir -p "$AGENT_DIR"
EXISTING=$(cat "$AGENT_DIR/models.json" 2>/dev/null)
EXISTING="${EXISTING:-{}}" # empty file (exists but 0 bytes) → {} so jq has valid input
NEW=$(echo "$EXISTING" | jq -c --arg provider "$PROVIDER_KEY" --arg baseUrl "$BASE_URL" --arg model "$MODEL" \
'.providers[$provider] = (.providers[$provider] // {}) |
.providers[$provider].baseUrl = $baseUrl |
if $model != "" then
(.providers[$provider].models //= []) |
.providers[$provider].models |= (
if any(.id == $model) then . else . + [{id: $model}] end
)
else . end')
if [ "$NEW" != "$EXISTING" ]; then
echo "$NEW" > "$AGENT_DIR/models.json.tmp" && mv "$AGENT_DIR/models.json.tmp" "$AGENT_DIR/models.json"
fi
fi
CMD=(pi -p)
# Provider: use the resolved PROVIDER; else if a custom BASE_URL is set, use the
# models.json key (PROVIDER_KEY, default openai) so the probe reaches the custom endpoint.
if [ -n "$PROVIDER" ]; then
CMD+=(--provider "$PROVIDER")
elif [ -n "$BASE_URL" ]; then
CMD+=(--provider "${PROVIDER_KEY:-openai}")
fi
# Only pass --model when set — an empty --model is silently accepted by pi but the
# probe then runs without the intended model (setup never resolves MODEL itself).
[ -n "$MODEL" ] && CMD+=(--model "$MODEL")
CMD+=(--thinking low --no-session --no-context-files --approve --no-extensions --no-skills "Reply with exactly: OK. Model: <model-name>")
# Pin the probe to the agent dir we just wrote (matches pi-agent's run pattern).
# </dev/null: pi -p hangs on a terminal/pipe stdin (mis-detects interactive).
PI_CODING_AGENT_DIR="$AGENT_DIR" "${CMD[@]}" </dev/null
Report success or failure to the user.
Show the final configuration and tell the user:
pi configured successfully. Both `/pi:delegate` and `/pi:review` will use these settings by default.
To override for a single invocation:
/pi:delegate <task> --endpoint <name> --model <id>
/pi:review --endpoint <name> --model <id>
To edit manually:
/pi:setup --edit-config
To view current config:
/pi:setup --list-models
Configure an endpoint in ~/.claude/pi.local.json:
{
"endpoints": {
"local-proxy": {
"provider": "openai",
"baseUrl": "http://10.10.0.195:8317/v1",
"models": ["gemini-3.6-flash-high", "gemini-3.6-pro"]
}
},
"defaultEndpoint": "local-proxy",
"defaultModel": "gemini-3.6-flash-high"
}
Or via /pi:setup --edit-config --global.
/pi:setup --endpoint anthropic-direct --provider anthropic --model claude-sonnet-4-20250514
/pi:setup --endpoint google --provider google --model gemini-3.6-flash-high
/pi:delegate — delegates coding tasks to pi/pi:review — reviews code via pi with read-only tools~/.claude/pi.local.json — global user settings (read by both delegate and review)