Agent skill

What Went Wrong

by skybrush-io in skybrush-io/live

Diagnose what went wrong in the session, why it was inefficient, or where the session derailed

GPL-3.0Auto-check passed

Install What Went Wrong

skills CLI
$ npx skills add skybrush-io/live --skill what-went-wrong -a claude-code

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

GitHub CLI
$ gh skill install skybrush-io/live what-went-wrong --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/skybrush-io/live.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/what-went-wrong .claude/skills/what-went-wrong && 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
what-went-wrong
GitHub stars
122
Token cost
~282 tokens
SKILL.md length
148 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
GPL-3.0

At a glance

Diagnose what went wrong in the session, why it was inefficient, or where the session derailed

  • Works in 3 steps: Describe where it occurred → Explain the root cause → Give recommendations for avoiding…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

What Went Wrong is an agent skill from skybrush-io/live. Diagnose what went wrong in the session, why it was inefficient, or where the session derailed

Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An open-source drone show and drone swarm ground control station GUI frontend. The licence is GPL-3.0.

Example prompts

  • “/what-went-wrong”

Workflow steps

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

  1. Describe where it occurred
  2. Explain the root cause
  3. Give recommendations for avoiding similar issues in the future, e.g. adding or fixing docs, tests, typing; updating AGENTS.md; fixing a…

What it can do on your machine

Read from SKILL.md and the folder at commit e104a06. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

What Went Wrong loads about 282 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~282

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 skybrush-io/live at commit e104a06, republished under its GPL-3.0 licence (© skybrush-io). 148 words, ~282 tokens.

Download SKILL.mdSave it as .claude/skills/what-went-wrong/SKILL.md (or your agent's skills folder).
name
what-went-wrong
description
Diagnose what went wrong in the session, why it was inefficient, or where the session derailed

Analyze this session and identify what went wrong

Focus on:

  • Wrong assumptions, e.g. what we assumed that turned out to be incorrect
  • Misleading information, e.g. outdated information in read files, misleading user prompt
  • Missed information, e.g. what was available but overlooked or not sought out
  • Process failures, e.g. skipped verification (linting, typechecking, tests)
  • Bad project state, e.g. lack of relevant information, documentation, architecture guide

Do not overload the user with unimportant comments, nitpicking! Just high impact changes, if there are any. Highlight 0-3 issues at most.

If you find no issues, briefly summarize what you considered and state why you see no room for improvement

If there are issues, for each issue:

  1. Describe where it occurred
  2. Explain the root cause
  3. Give recommendations for avoiding similar issues in the future, e.g. adding or fixing docs, tests, typing; updating AGENTS.md; fixing a skill

Be informative but concise!

© skybrush-io, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/what-went-wrong of skybrush-io/live.

Open the folder on GitHubat commit e104a06

Compare with similar skills

What Went Wrong 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.

What Went Wrong compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
What Went Wrong this skillskybrush-io/live122—~282Automated safety check: PassGPL-3.0
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Diagnose Gatewayopenclaw/openclaw392k—~670Automated safety check: PassMIT
Diagnosegithub/awesome-copilot40k1 repos~1kAutomated safety check: PassMIT
Diagnose Why Work Stoppedpaperclipai/paperclip99k—~2.8kAutomated safety check: PassMIT
Diagnosing Missing RecordingsPostHog/posthog40k—~2kAutomated safety check: PassCustom licence

Similar skills

  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Diagnose Gateway

    openclaw/openclaw

    Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.

    392k GitHub stars~670 tokensUpdated today
    Auto-check passed
  • Diagnose

    github/awesome-copilot

    Official

    Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report…

    40k GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check passed
  • Diagnose Why Work Stopped

    paperclipai/paperclip

    Diagnose stalled, looping, or over-recovered Paperclip issue trees and propose a no-code product-rule plan.

    99k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Official

    Diagnoses why a session recording is missing or was not captured.

    40k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Diagnosing Superpowers Sessions

    jnMetaCode/superpowers-zh

    Investigates what went wrong in a superpowers session by reading its transcript, reports findings with path and line citations, and can draft a GitHub issue or redacted bundle.

    8.3k GitHub stars~858 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from skybrush-io/live

  • Feature Overview

    skybrush-io/live

    Write concise architecture overview documents for features. An agent skill from skybrush-io/live.

    122 GitHub stars~704 tokensUpdated yesterday
    Auto-check passed
  • Changelog

    skybrush-io/live

    Update the changelog from recent changes. An agent skill from skybrush-io/live.

    122 GitHub stars~341 tokensUpdated yesterday
    Auto-check passed
  • Learn

    skybrush-io/live

    Reflect on user corrections and propose AGENTS.md or skill updates

    122 GitHub stars~107 tokensUpdated yesterday
    Auto-check passed

Questions about What Went Wrong

What does What Went Wrong do?

Diagnose what went wrong in the session, why it was inefficient, or where the session derailed. What Went Wrong is an agent skill from skybrush-io/live.

How do I install What Went Wrong in Claude Code?

Run `npx skills add skybrush-io/live --skill what-went-wrong -a claude-code`. Or copy the skill folder (.agents/skills/what-went-wrong in skybrush-io/live) into .claude/skills/what-went-wrong in your project. Claude Code loads it when a task matches its description.

How do I install What Went Wrong in Codex?

Run `npx skills add skybrush-io/live --skill what-went-wrong -a codex`. Or copy the skill folder (.agents/skills/what-went-wrong in skybrush-io/live) into .agents/skills/what-went-wrong in your project. Codex loads it when a task matches its description.

Can I use What Went Wrong 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 skybrush-io/live --skill what-went-wrong -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/what-went-wrong, .gemini/skills/what-went-wrong, .github/skills/what-went-wrong and .opencode/skills/what-went-wrong in your project.

What does What Went Wrong need to run?

SKILL.md names no scripts, command-line tools or credentials: What Went Wrong is instructions for the agent only.

Does What Went Wrong 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 What Went Wrong 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 What Went Wrong use?

What Went Wrong is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does What Went Wrong use?

About 282 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to What Went Wrong?

Skills that share tags, products or a category with What Went Wrong: Diagnosing Superpowers Sessions (obra/superpowers, 297k stars), Diagnose Gateway (openclaw/openclaw, 392k stars), Diagnose (github/awesome-copilot, 40k stars) and Diagnose Why Work Stopped (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains What Went Wrong?

skybrush-io (a GitHub organization) maintains it in skybrush-io/live, which has 122 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 8, 2026.

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