Agent Skillsnyldn/claude-octopus › skill-doctor

skill-doctor

GitHub

环境诊断工具,检测插件配置、认证、调度器及钩子等14类问题。用于排查运行异常、更新后验证或演示前检查,确保系统正确运行并提前发现潜在故障。

.claude/skills/skill-doctor/SKILL.md nyldn/claude-octopus

Trigger Scenarios

系统功能异常且原因不明 安装或更新插件后验证环境 重要演示或工作流运行前检查 验证提供商认证状态 确认调度器和钩子配置正确

Install

npx skills add nyldn/claude-octopus --skill skill-doctor -g -y
More Options

Non-standard path

npx skills add https://github.com/nyldn/claude-octopus/tree/main/.claude/skills/skill-doctor -g -y

Use without installing

npx skills use nyldn/claude-octopus@skill-doctor

指定 Agent (Claude Code)

npx skills add nyldn/claude-octopus --skill skill-doctor -a claude-code -g -y

安装 repo 全部 skill

npx skills add nyldn/claude-octopus --all -g -y

预览 repo 内 skill

npx skills add nyldn/claude-octopus --list

SKILL.md

Frontmatter
{
    "name": "skill-doctor",
    "effort": "low",
    "trigger": "EXPLICITLY USE when user asks about:\n- \"doctor\" or \"run doctor\" or \"diagnostics\"\n- \"check my setup\" or \"is everything working\"\n- \"health check\" or \"environment check\"\n- \"what's wrong with my setup\" or \"why isn't octopus working\"\n- \"check providers\" or \"check auth\" or \"check hooks\"\n\nDO NOT activate for:\n- Initial setup (use \/octo:setup)\n- Project status or workflow progress (use \/octo:status)\n- Debugging application code (use \/octo:debug)",
    "description": "Environment diagnostics — check providers, auth, config, hooks, scheduler, and more",
    "disable-model-invocation": true
}

Environment Doctor

Overview

Run environment diagnostics across 14 check categories. Doctor 2.0 identifies misconfigured providers, stale loaded or cached plugin versions, invalid plugin assembly, unwritable state, non-terminal run records, orphan process evidence, broken hooks, and other issues that prevent Claude Octopus from working correctly.

Core principle: Detect problems before they surface in workflows.


When to Use

Use this skill when:

  • Something isn't working and you're not sure why
  • After installing or updating the plugin
  • Before a demo or important workflow run
  • Checking if providers are properly authenticated
  • Verifying scheduler, hooks, or skills are correctly configured

Do NOT use for:

  • First-time setup (use /octo:setup — it guides configuration)
  • Project workflow status (use /octo:status)
  • Debugging application code (use /octo:debug)

The Process

Step 1: Resolve Plugin Root and Run Full Diagnostics

Use this resolver before running Octopus scripts. Do not assume ~/.claude-octopus/plugin exists; Windows Git Bash installs may not support the stable symlink. Run this as a single Bash call.

OCTO_PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
if [[ -z "$OCTO_PLUGIN_ROOT" || ! -x "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" ]]; then
  OCTO_PLUGIN_ROOT="${HOME}/.claude-octopus/plugin"
fi
if [[ ! -x "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" ]] && command -v octopus >/dev/null 2>&1; then
  OCTO_BIN="$(command -v octopus)"
  OCTO_PLUGIN_ROOT="$(cd "$(dirname "$OCTO_BIN")/.." && pwd)"
fi
if [[ ! -x "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" ]]; then
  OCTO_PLUGIN_ROOT="$(
    find "${HOME}/.claude/plugins" -type f -path "*/scripts/orchestrate.sh" -print 2>/dev/null \
      | sed 's#/scripts/orchestrate.sh$##' \
      | { grep -E '(nyldn-plugins|claude-octopus|/octo(/[0-9]|$))' || true; } \
      | sort \
      | tail -1
  )"
fi
if [[ -z "$OCTO_PLUGIN_ROOT" || ! -x "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" ]]; then
  echo "Claude Octopus plugin root not found. Reinstall the octo plugin, then retry doctor diagnostics."
  exit 1
fi
mkdir -p "${HOME}/.claude-octopus"
_octo_stable="${HOME}/.claude-octopus/plugin"
if [[ ! -L "$_octo_stable" ]] || [[ "$(cd "$OCTO_PLUGIN_ROOT" 2>/dev/null && pwd -P)" != "$(cd "$_octo_stable" 2>/dev/null && pwd -P)" ]]; then
  [[ -L "$_octo_stable" || -f "$_octo_stable" ]] && rm -f "$_octo_stable" 2>/dev/null || true
  ln -s "$OCTO_PLUGIN_ROOT" "$_octo_stable" 2>/dev/null || true
fi
unset _octo_stable
export OCTO_PLUGIN_ROOT
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor --verbose

This runs all 14 check categories and displays a formatted report.

Step 2: Filter by Category (Optional)

If the user asks about a specific area, reuse the resolver from Step 1 and replace its final doctor --verbose invocation with one of these lines. These are replacement lines, not standalone shell calls; OCTO_PLUGIN_ROOT must be resolved in the same Bash call.

bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor providers
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor providers --live
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor companions
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor auth
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor config
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor updates
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor state
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor smoke
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor hooks
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor scheduler
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor skills
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor conflicts
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor agents
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor recurrence
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor cache

Step 3: Check & Install Dependencies

Reuse the Step 1 resolver and replace its final invocation with the dependency checker to find missing CLIs, statusline config, and recommended plugins:

bash "$OCTO_PLUGIN_ROOT/scripts/install-deps.sh" check

If the check reports missing deps, offer to install them:

bash "$OCTO_PLUGIN_ROOT/scripts/install-deps.sh" install

This auto-installs Codex CLI, jq, and the statusline resolver. Antigravity CLI (agy) setup is detected and reported with install guidance. For plugins (claude-mem, document-skills), it prints /plugin install commands the user must run manually.

Step 4: Verbose or JSON Output

As above, run these as the final line of the Step 1 resolver call:

# Detailed output for troubleshooting
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor --verbose

# Machine-readable output
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor --json

# Combine: specific category + verbose
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor auth --verbose

Doctor 2.0 JSON always uses this outer contract:

{
  "schema_version": "10.0",
  "summary": {"passed": 0, "warnings": 0, "failures": 0, "exit_code": 0},
  "results": []
}

A check with status fail makes both summary.exit_code and the process exit code 1, while stdout remains valid JSON. Warnings remain structured but do not make the command fail. Unknown flags, unknown categories, and multiple category arguments are usage errors with exit code 2; do not retry them as full scans.

The providers --live variant is an explicit, bounded AGY capability check. It uses one small real request to verify the CLI version, live model catalog and keyring authentication, configured model, and print-mode dispatch. Do not run it from startup hooks or routine preflight. If its catalog/auth stage fails, tell the user to launch plain agy and complete the browser sign-in; AGY has no separate login shell subcommand. On macOS keyring errors, direct them to Keychain Access, the Antigravity CLI item, and its Access Control settings.

Step 5: Interactive Remediation (MANDATORY for fixable issues)

After running diagnostics, if ANY fixable issues are found, you MUST use AskUserQuestion to offer fixes. Do NOT just print instructions — offer to execute them.

Before each accepted repair, restate the exact target and action. Configuration repairs must use a validated sibling temporary file and atomic rename; if any step fails, keep the original and report the failure. Cache cleanup, stale PID cleanup, login flows, package installation, and plugin updates always require explicit confirmation. After repair, rerun only the affected category first, then offer a full scan.

RTK not installed:

AskUserQuestion({
  questions: [{
    question: "RTK saves 60-90% on bash output tokens. Install it now?",
    header: "Install RTK",
    multiSelect: false,
    options: [
      {label: "Install via brew (Recommended)", description: "brew install rtk — fast, macOS"},
      {label: "Install via cargo", description: "cargo install rtk-token-killer"},
      {label: "Skip", description: "Continue without RTK"}
    ]
  }]
})

If user chooses install, run it, then offer hook setup.

RTK installed but hook not configured on macOS/Linux:

On Windows Git Bash, do not offer rtk init -g. RTK uses CLAUDE.md injection mode there, so report the hook check as skipped.

AskUserQuestion({
  questions: [{
    question: "RTK is installed but the Claude Code hook isn't active. Configure it?",
    header: "RTK Hook",
    multiSelect: false,
    options: [
      {label: "Run rtk init -g (Recommended)", description: "Auto-installs Claude Code bash hook on macOS/Linux"},
      {label: "Skip", description: "I'll configure it later"}
    ]
  }]
})

Missing optional providers:

AskUserQuestion({
  questions: [{
    question: "Some providers are missing. Install them?",
    header: "Providers",
    multiSelect: true,
    options: [
      {label: "Codex CLI", description: "npm install -g @openai/codex"},
      {label: "Antigravity CLI", description: "Install agy, then verify with agy --version && agy models"},
      {label: "Skip all", description: "Continue with available providers"}
    ]
  }]
})

Auth expired: Offer to run the login command for the expired provider.

Multiple fixable issues: Batch them into a single AskUserQuestion with multiSelect where appropriate, rather than asking one at a time.


Check Categories

Category What it checks
providers Claude Code version, Codex CLI installed, Antigravity CLI installed, Perplexity API key, Ollama local LLM (server + models), circuit breaker status, provider fallback history
companions Optional companion tools and integrations
auth Authentication status for each provider
config Plugin version, install scope, feature flags, strict claude plugin validate result
updates Loaded, installed, catalog, and cache versions; Claude marketplace auto-update; reload requirement
state Project state.json, workspace and probe-cache writability, stale results, non-terminal runs, orphan and stale PID evidence
smoke Smoke test cache, model configuration
hooks hooks.json validity, hook scripts
scheduler Scheduler daemon, jobs, budget gates, kill switches
skills Skill files loaded and valid
conflicts Conflicting plugins detection
agents Agent definitions, worktree isolation, CLI registration, version compatibility
recurrence Failure pattern detection — flags repeated quality gate failures, source hotspots, 48h trends
cache Cache size, freshness, and hygiene

Software dependency installation is checked separately by scripts/install-deps.sh check in Step 3, including Node.js, jq, provider CLIs, RTK token compression, the statusline resolver, and recommended plugins.


Interpreting Results

Healthy Output

All checks pass — no action needed.

Common Issues and Fixes

Issue Fix
Codex CLI not found npm install -g @openai/codex or install via codex login
Antigravity CLI not found Install agy, then verify with agy --version and agy models
Perplexity not configured export PERPLEXITY_API_KEY="pplx-..." (optional)
Auth expired Re-run codex login; for AGY, launch plain agy and complete its browser sign-in
Circuit breaker OPEN Provider had 3+ consecutive transient failures — wait for cooldown or check provider status
Stale state Delete .octo/state.json and re-initialize
Invalid hooks.json Check hooks.json syntax — must be valid JSON
RTK not installed Offer to install: brew install rtk && rtk init -g (saves 60-90% tokens). Use AskUserQuestion to offer brew vs cargo install.
RTK installed but hook not configured On macOS/Linux, offer rtk init -g; on Windows Git Bash, report skipped because RTK uses CLAUDE.md injection mode
RTK gain stats unavailable Run some bash commands first, then check rtk gain to see token savings
Conflicting plugins Uninstall conflicting plugins or adjust scope

Integration with Other Skills

Scenario Route
Doctor finds missing provider Suggest /octo:setup to configure
Doctor finds stale project state Suggest /octo:status to review
Doctor finds hook errors Guide user to fix hooks.json
All checks pass, user still has issues Suggest /octo:debug for deeper investigation

Hook Profile

Claude Octopus hooks can run in different profiles to balance cost and coverage.

Current profile: $OCTO_HOOK_PROFILE (default: standard)

Available profiles:

  • minimal — Only session lifecycle and cost tracking hooks (lowest overhead)
  • standard — All hooks except expensive review/security gates (default)
  • strict — All hooks enabled including quality and security gates

Override: Set OCTO_PROFILE=budget|balanced|quality or OCTO_DISABLED_HOOKS=hook1,hook2 to fine-tune. Legacy OCTO_HOOK_PROFILE still works (minimal→budget, standard→balanced, strict→quality).


Intensity Profile

The doctor reports the active intensity profile — a single knob controlling hook gating, model selection, phase skipping, and context verbosity.

What the Doctor Checks

  • Current profile: OCTO_PROFILE value (budget/balanced/quality, default: balanced)
  • Profile source: env var, legacy OCTO_HOOK_PROFILE, or auto-selected from intent
  • Hook gating: which hooks are enabled/disabled at this profile level
  • Model hints: which model (sonnet/opus) is recommended for each phase
  • Context verbosity: compressed/standard/full

Profile Summary

Dimension budget balanced quality
Hooks essential only standard (no quality gates) all hooks
Models Sonnet everywhere Sonnet + Opus for synthesis Opus for most phases
Phases Skip discover if context given Skip re-discovery All phases run
Context Compressed Standard Full inlining

Project Tier Hint

Also report OCTO_TIER when set. This is a recommendation hint, not a hard policy.

Tier Doctor guidance
prototype Prefer faster checks and warn before high-cost provider fanout
mvp Use balanced defaults and consensus on risky changes
production Recommend full verification, security review, and stricter release gates

If unset, show OCTO_TIER=unset and suggest setting it only when the project has a stable risk profile.


Remote Session Checks

If CLAUDE_CODE_REMOTE=true or OCTOPUS_REMOTE_SESSION=true, report:

  • remote session detected
  • autonomous mode default active when no explicit autonomy is set
  • provider probes skipped to conserve time/quota
  • full HUD disabled unless OCTOPUS_REMOTE_STATUSLINE=full
  • provider CLIs may need to be installed in the cloud setup script

Suggest /octo:setup only for configuration guidance; do not recommend interactive provider logins inside the remote session.


Runtime Context

The doctor checks for project-level RUNTIME.md — a file that provides project-specific context (API endpoints, env vars, test commands, build steps) to orchestration prompts.

What the Doctor Checks

  • RUNTIME.md exists in the project root (also checks .octopus/RUNTIME.md and .claude-octopus/RUNTIME.md)
  • If missing, suggest creating one from the template: cp "${HOME}/.claude-octopus/plugin/config/templates/RUNTIME.md" ./RUNTIME.md
  • If present, confirm it contains at least one populated section (not just the template defaults)

Why It Matters

Without a RUNTIME.md, orchestration prompts lack project-specific details — leading to generic advice about test commands, environment variables, and build steps. A populated RUNTIME.md makes every workflow more accurate.


Quick Reference

/octo:doctor was removed in v9.41.0 to preserve Claude Code's native /doctor command. Invoke this manual skill explicitly, or run the CLI directly:

What to say / run Action
/octo:skill-doctor Run all 14 categories inside Claude Code
octopus doctor providers Check provider installation only
octopus doctor auth --verbose Detailed auth status
octopus doctor --json Machine-readable output
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor auth --verbose Detailed auth status when the CLI is unavailable
bash "$OCTO_PLUGIN_ROOT/scripts/orchestrate.sh" doctor --json Machine-readable output when the CLI is unavailable

If the octopus CLI is not on PATH, resolve and export OCTO_PLUGIN_ROOT with the Step 1 resolver, then run the equivalent scripts/orchestrate.sh command directly.

Version History

  • 46d64cb Current 2026-08-28 20:35

    引入Doctor 2.0,增强对陈旧插件版本、无效插件组装、不可写状态及孤儿进程证据的检测能力;增加Windows Git Bash下的插件根目录解析逻辑;强化失败关闭机制与可观测性报告。

  • 242e51d 2026-08-20 09:30

Same Skill Collection

.claude/skills/extract-skill/SKILL.md
.claude/skills/flow-deliver/SKILL.md
.claude/skills/flow-parallel/SKILL.md
.claude/skills/flow-spec/SKILL.md
.claude/skills/skill-agent-topology/SKILL.md
.claude/skills/skill-architecture/SKILL.md
.claude/skills/skill-audit/SKILL.md
.claude/skills/skill-authoring/SKILL.md
.claude/skills/skill-claw/SKILL.md
.claude/skills/skill-code-review/SKILL.md
.claude/skills/skill-content-pipeline/SKILL.md
.claude/skills/skill-context-detection/SKILL.md
.claude/skills/skill-copilot-provider/SKILL.md
.claude/skills/skill-cost-projections/SKILL.md
.claude/skills/skill-coverage-audit/SKILL.md
.claude/skills/skill-debate/SKILL.md
.claude/skills/skill-debug/SKILL.md
.claude/skills/skill-decision-support/SKILL.md
.claude/skills/skill-deck/SKILL.md
.claude/skills/skill-deep-research/SKILL.md
.claude/skills/skill-design-lineage/SKILL.md
.claude/skills/skill-doc-delivery/SKILL.md
.claude/skills/skill-doc-sync/SKILL.md
.claude/skills/skill-factory/SKILL.md
.claude/skills/skill-finish-branch/SKILL.md
.claude/skills/skill-intake/SKILL.md
.claude/skills/skill-intent-contract/SKILL.md
.claude/skills/skill-issues/SKILL.md
.claude/skills/skill-iterative-loop/SKILL.md
.claude/skills/skill-knowledge-work/SKILL.md
.claude/skills/skill-meta-prompt/SKILL.md
.claude/skills/skill-native-escalation-routing/SKILL.md
.claude/skills/skill-parallel-agents/SKILL.md
.claude/skills/skill-prd/SKILL.md
.claude/skills/skill-pressure-test/SKILL.md
.claude/skills/skill-quick/SKILL.md
.claude/skills/skill-resume/SKILL.md
.claude/skills/skill-review-response/SKILL.md
.claude/skills/skill-rollback/SKILL.md
.claude/skills/skill-security-audit/SKILL.md
.claude/skills/skill-security-framing/SKILL.md
.claude/skills/skill-ship/SKILL.md
.claude/skills/skill-staged-review/SKILL.md
.claude/skills/skill-status/SKILL.md
.claude/skills/skill-task-management-v2/SKILL.md
.claude/skills/skill-tdd/SKILL.md
.claude/skills/skill-thought-partner/SKILL.md
.claude/skills/skill-ui-ux-design/SKILL.md
.claude/skills/skill-verification-gate/SKILL.md

Metadata

Files
0
Version
46d64cb
Hash
4d76911f
Indexed
2026-08-20 09:30

trang chủ - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-01 12:23
浙ICP备14020137号-1 $bản đồ khách truy cập$