New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Troubleshooting

by alecs5am in alecs5am/ralphy

Ralphy CLI operations and repair — environment setup, API keys and connectors, ralphy doctor, reading logs, diagnosing a failed generation or render, and the CLI cookbook for verbs other roles call.

Apache-2.0Auto-check passedAgent Workflows

Install Troubleshooting

skills CLI
$ npx skills add alecs5am/ralphy --skill troubleshooting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alecs5am/ralphy troubleshooting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alecs5am/ralphy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/troubleshooting .claude/skills/troubleshooting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
troubleshooting
GitHub stars
138
Token cost
~1.4k tokens
SKILL.md length
405 words
Files
4 (incl. references)
Skills in repo
28
Repo updated
First seen
Licence
Apache-2.0

At a glance

Ralphy CLI operations and repair — environment setup, API keys and connectors, ralphy doctor, reading logs, diagnosing a failed generation or render, and the CLI cookbook for verbs other roles call.

  • Works in 4 steps: NO auto-launch. I don't run a UI or… → Connector-owned keys only. ralphy doctor… → No provider MCP setup. Provider access… → …
  • The user says set this up
  • SKILL.md covers CLI cookbook, Sub-docs (read on demand), Sub-tasks and What I read on start, plus 3 more sections
  • Calls jq and bunx

What it does

Troubleshooting is an agent skill from alecs5am/ralphy. Ralphy CLI operations and repair — environment setup, API keys and connectors, ralphy doctor, reading logs, diagnosing a failed generation or render, and the CLI cookbook for verbs other roles call. USE WHEN the user says "set this up", "set up my keys", "run ralphy doctor", "nothing works", "it failed", "read the logs", "missing key", "why did this generation fail", or asks any question about how a ralphy verb works. TRIGGER (EN): "doctor", "nothing works", "set up keys", "read the logs", "debug this failure"…

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/cli-cookbook.md`, `references/doctor.md` and `references/troubleshooting.md`).

It sits in Agent Workflows. The repository describes itself as: Open-source desktop app for content creation, with an agent runtime and standalone CLI. The licence is Apache-2.0.

When your agent uses it

  • The user says set this up
  • Run ralphy doctor
  • Why did this generation fail
  • Asks any question about how a ralphy verb works

Example prompts

  • “set this up”
  • “set up my keys”
  • “run ralphy doctor”
  • “/troubleshooting”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. NO auto-launch. I don't run a UI or scheduler in the background. Chat is the interface. See core/doctor.md.
  2. Connector-owned keys only. ralphy doctor reports required and optional connectors; keys never leak outside their registered provider…
  3. No provider MCP setup. Provider access goes through Ralphy connectors, not ad-hoc MCP servers.
  4. Logs append-only. cli/lib/gen-log.ts enforces the format. See core/troubleshooting.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 8d139f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • bunx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use bunx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Troubleshooting loads about 1.4k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 145 tokens; SKILL.md has 405 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~145
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alecs5am/ralphy at commit 8d139f0, republished under its Apache-2.0 licence (© alecs5am). 405 words, ~1,409 tokens.

Download SKILL.mdSave it as .claude/skills/troubleshooting/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
troubleshooting
description
Ralphy CLI operations and repair — environment setup, API keys and connectors, `ralphy doctor`, reading logs, diagnosing a failed generation or render, and the CLI cookbook for verbs other roles call. USE WHEN the user says "set this up", "set up my keys", "run ralphy doctor", "nothing works", "it failed", "read the logs", "missing key", "why did this generation fail", or asks any question about how a `ralphy` verb works. TRIGGER (EN): "doctor", "nothing works", "set up keys", "read the logs", "debug this failure", "missing API key", "how do I run <verb>".
namespace
user

Troubleshooting playbook

Read this when: "set up", "set up keys", "ralphy doctor", "nothing works", "read logs", "debug failed generation", "missing key", any ralphy CLI usage question.

Plumbing role. Other roles call me when something breaks, when the environment isn't up, or when the user wants to inspect under the hood. Ops + CLI expert layer beneath the creative roles.

STOP rule. Every observability question is a ralphy verb. Don't cat / tail JSONL by hand — the log readers below sort, merge, and filter for you. AGENTS invariant #2.

CLI cookbook

Every observability question is a ralphy verb. Don't cat JSONL by hand — the log readers below sort, merge, and filter for you.

bash
# Env / setup health
ralphy doctor                                                # full env check (keys, deps, project)
ralphy doctor -p                                             # human-readable
ralphy status                                                # capabilities + linked project
ralphy setup                                                 # interactive wizard (first-time keys)
ralphy config get / set                                      # config CRUD

# Logs (per-project, append-only via cli/lib/gen-log.ts)
ralphy project log <id> --type generations --limit 50        # latest model calls + cost + errors
ralphy project log <id> --type user-prompts --limit 20       # what the user said, when
ralphy project log <id> --type user-assets --limit 20        # what the user uploaded
ralphy project log <id> --type all --limit 200               # merged, chronological JSON
ralphy project timeline <id>                                 # pretty chronological log (table)

# Workspace inspection
ralphy workspace stats                                       # cross-project counts + disk usage
ralphy project list -p                                       # status per project
ralphy assets list                                           # ralphy-assets companion repo
ralphy assets cache-info                                     # local SHA-verified cache
ralphy assets pull <template>                                # auto-runs on `template use`

# Render-specific debug
ralphy project show <id> --assets                            # what's on disk
ralphy project show <id> --scenario                          # current scenario.json

If the user asks "why did this generation fail" — ralphy project log <id> --type generations | jq '. | select(.status=="error")' is the fast move. Don't grep JSONL by hand.

Sub-docs (read on demand)

FileWhen to read it
core/doctor.mdSession start env check, fresh-machine setup, missing keys
core/cli-cookbook.mdAny specific ralphy <command> question / workspace inspection
core/troubleshooting.mdFailed generation, "what was in the last prompt", log reading

Sub-tasks

Sub-taskWhenSub-docs
doctorsession start, "check the environment"doctor
fresh-machine-setup"set up", "first run", missing deps/keysdoctor (setup section)
cli-cookbookany ralph CLI questioncli-cookbook
workspace-inspection"what's in workspace", "show project timeline"cli-cookbook (inspection section)
debug-logsfailed generation, "what was in the last prompt"troubleshooting

What I read on start

  • AGENTS.md — invariants (chat is the interface; no auto-launched UI or scheduler).
  • pwd + package.json + CLAUDE.md + MODELS.md to confirm repo root.
  • docs/agent-guide.md — canonical CLI reference. I don't memorize commands; I look them up.
  • docs/cli-spec.md — flag-level spec.
Show full SKILL.md (146 more words)Show less

Hard rules (inherited from AGENTS.md)

  1. NO auto-launch. I don't run a UI or scheduler in the background. Chat is the interface. See core/doctor.md.
  2. Connector-owned keys only. ralphy doctor reports required and optional connectors; keys never leak outside their registered provider modules.
  3. No provider MCP setup. Provider access goes through Ralphy connectors, not ad-hoc MCP servers.
  4. Logs append-only. cli/lib/gen-log.ts enforces the format. See core/troubleshooting.md.

Background processes — manners

  • I don't spawn long-running processes. AGENTS invariant.
  • If the user explicitly asks for preview — I'll say to run bunx hyperframes preview .ralphy/workspaces/<ws>/projects/<id> foreground in a separate window.
  • If the user complains "port busy" — show lsof -iTCP:<port>, user decides whether to kill / leave it.

Handoff

  • After env up + CLI clear → hand back to the role that triggered me (usually producer playbook).
  • Fresh-machine after setup → producer playbook for the first real end-to-end task.
  • HyperFrames-specific → hyperframes playbook (not me).

© alecs5am, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/troubleshooting of alecs5am/ralphy.

  • SKILL.md
  • references/cli-cookbook.md
  • references/doctor.md
  • references/troubleshooting.md

Open the folder on GitHubat commit 8d139f0

Compare with similar skills

Troubleshooting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Troubleshooting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Troubleshooting this skillalecs5am/ralphy138—~1.4kAutomated safety check: PassApache-2.0
Short Drama Directorlixiaoxiao9888-create/manju-laoli-skill1.1k—~6.4kAutomated safety check: PassMIT
Gemini SkillWJZ-P/gemini-skill832—~1.1kAutomated safety check: PassMIT
Edit Premiere Projecthetpatel-11/Adobe_Premiere_Pro_MCP668—~445Automated safety check: PassMIT
Video Copy AnalyzerALBEDO-TABAI/video-copy-analyzer209—~1.9kAutomated safety check: PassMIT
ComfyComfy-Org/comfy-skills219—~1.4kAutomated safety check: PassMIT

Similar skills

  • Short Drama Director

    lixiaoxiao9888-create/manju-laoli-skill

    【漫剧老李AIGC 全流程Skill · V6.9.8 轻量版 Multi-Agent】抖音与红果爆款短剧/漫剧工业化编剧与视听导演超级系统。全面支持 OpenClaw、WorkBuddy、豆包智能体/扣子(Coze)等多Agent平台，深度适配 Seedance 2.5/2.0（强制二选一，即梦为次选/历史兼容）＋ MiniMax H3 格式支线（七段式→H3…

    1.1k GitHub stars~6.4k tokensUpdated 19 days ago
    Agent WorkflowsAuto-check passed

  • Gemini Skill

    WJZ-P/gemini-skill

    通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。

    832 GitHub stars~1.1k tokensUpdated 21 days ago
    Agent WorkflowsAuto-check passed

  • Edit Premiere Project

    hetpatel-11/Adobe_Premiere_Pro_MCP

    Install, verify, inspect, edit, and export local Adobe Premiere Pro projects through the Premiere MCP Bridge.

    668 GitHub stars~445 tokensUpdated 14 days ago
    Agent WorkflowsAuto-check passed

  • Video Copy Analyzer

    ALBEDO-TABAI/video-copy-analyzer

    视频文案分析一站式工具。下载在线视频（B站/YouTube/抖音等）、使用FunASR进行高速中文语音转录、 自动校正文稿、并进行三维度综合分析（TextContent/Viral/Brainstorming）。

    209 GitHub stars~1.9k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Comfy

    Comfy-Org/comfy-skills

    Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…

    219 GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Run SEO Page Loop

    tsingyuai/growth-lab

    Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review.

    2k GitHub stars~1.2k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

More from alecs5am/ralphy

All 28 skills in this repo

  • Gsap

    alecs5am/ralphy

    GSAP animation reference for HyperFrames. An agent skill from alecs5am/ralphy.

    138 GitHub stars~2.4k tokensUpdated 16 days ago
    Auto-check passed

  • Researcher

    alecs5am/ralphy

    Deep-research workflow for UGC reference material — turns one or more URLs / handles / trend queries into a single cited research report (report.md + sources.json) that a scenarist or art-director…

    138 GitHub stars~1.9k tokensUpdated 16 days ago
    Auto-check passed

  • Editor

    alecs5am/ralphy

    Composition and render craft — assembles scenario.json plus asset-manifest.json into a HyperFrames HTML composition and renders the mp4.

    138 GitHub stars~3.6k tokensUpdated 16 days ago
    Auto-check passed

  • Evaluator

    alecs5am/ralphy

    Quality evaluation of rendered UGC mp4s — scene segmentation, audio loudness / dead-air, caption density, and per-scene visual analysis.

    138 GitHub stars~3.6k tokensUpdated 16 days ago
    Auto-check passed

  • Producer

    alecs5am/ralphy

    End-to-end orchestration — the wrapper that drives the whole production contract across roles, plus batch production.

    138 GitHub stars~4.7k tokensUpdated 16 days ago
    Auto-check passed

  • Scenarist

    alecs5am/ralphy

    Scenario and script craft — writes and reworks the scene-by-scene scenario.json: hook, beat structure, per-scene VO, on-screen text, pacing, and the language/aspect pre-flight.

    138 GitHub stars~3.2k tokensUpdated 16 days ago
    Auto-check passed

Categories

Questions about Troubleshooting

What does Troubleshooting do?

Ralphy CLI operations and repair — environment setup, API keys and connectors, ralphy doctor, reading logs, diagnosing a failed generation or render, and the CLI cookbook for verbs other roles call. Troubleshooting is an agent skill from alecs5am/ralphy. Ralphy CLI operations and repair — environment setup, API keys and connectors, ralphy doctor, reading logs, diagnosing a failed generation or render, and the CLI cookbook for verbs other roles call.

When should I use Troubleshooting?

Troubleshooting fits situations like: the user says set this up; run ralphy doctor; why did this generation fail; asks any question about how a ralphy verb works.

How do I install Troubleshooting in Claude Code?

Run `npx skills add alecs5am/ralphy --skill troubleshooting -a claude-code`. Or copy the skill folder (.agents/skills/troubleshooting in alecs5am/ralphy) into .claude/skills/troubleshooting in your project. Claude Code loads it when a task matches its description.

How do I install Troubleshooting in Codex?

Run `npx skills add alecs5am/ralphy --skill troubleshooting -a codex`. Or copy the skill folder (.agents/skills/troubleshooting in alecs5am/ralphy) into .agents/skills/troubleshooting in your project. Codex loads it when a task matches its description.

Can I use Troubleshooting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alecs5am/ralphy --skill troubleshooting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/troubleshooting, .gemini/skills/troubleshooting, .github/skills/troubleshooting and .opencode/skills/troubleshooting in your project.

What does Troubleshooting need to run?

Going by SKILL.md and its folder, Troubleshooting needs the command-line tools its instructions call (jq and bunx).

Does Troubleshooting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Troubleshooting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Troubleshooting use?

Troubleshooting is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Troubleshooting use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Troubleshooting?

Skills that share tags, products or a category with Troubleshooting: Short Drama Director (lixiaoxiao9888-create/manju-laoli-skill, 1.1k stars), Gemini Skill (WJZ-P/gemini-skill, 832 stars), Edit Premiere Project (hetpatel-11/Adobe_Premiere_Pro_MCP, 668 stars) and Video Copy Analyzer (ALBEDO-TABAI/video-copy-analyzer, 209 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Troubleshooting?

alecs5am (a GitHub user) maintains it in alecs5am/ralphy, which has 138 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 22, 2026.

Source: alecs5am/ralphy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.