Skills

systematic-debugging

systematic-debugging is a skill in obra/superpowers, last changed 9 Oct 2026. It can run shell commands and bundle scripts. Our pattern check flagged nothing at commit 2ce8aa1 on 26 Oct 2026.

Pattern check: nothing flagged · commit 2ce8aa1 · 26 Oct 2026

Install
From the author
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Licence
MIT
Repo stars
305.7k
Folder last changed
9 Oct 2026 (opens in a new tab)
Publisher
obra
Files
11 files
Checked
2ce8aa1 (opens in a new tab) · 26 Oct 2026

Install

Each tab says whether it installs commit 2ce8aa1, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 2ce8aa1, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/obra/superpowers.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b &&
  git -C "$tmp" sparse-checkout set -- skills/systematic-debugging &&
  git -C "$tmp" checkout -q 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/systematic-debugging &&
  cp -R "$tmp"/skills/systematic-debugging/. .claude/skills/systematic-debugging/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Or install the superpowers plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add obra/superpowers --scope project &&
  claude plugin install superpowers@superpowers-dev --scope project
Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 2ce8aa1. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Bundles scripts

    The folder holds code files the agent may run.

    condition-based-waiting-example.ts · find-polluter.sh

Pattern check

Pattern check: nothing flagged · commit 2ce8aa1 · 26 Oct 2026

We checked every text file in this skill, at commit 2ce8aa1 on 26 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

    • Note

      Reference files that SKILL.md doesn't link: CREATION-LOG.md, test-academic.md, test-pressure-1.md, test-pressure-2.md and test-pressure-3.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: CREATION-LOG.md (120 lines), condition-based-waiting.md (116 lines), defense-in-depth.md (123 lines) and root-cause-tracing.md (170 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Reference files that SKILL.md doesn't link: CREATION-LOG.md, test-academic.md, test-pressure-1.md, test-pressure-2.md and test-pressure-3.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: CREATION-LOG.md (120 lines), condition-based-waiting.md (116 lines), defense-in-depth.md (123 lines) and root-cause-tracing.md (170 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      Reference files that SKILL.md doesn't link: CREATION-LOG.md, test-academic.md, test-pressure-1.md, test-pressure-2.md and test-pressure-3.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: CREATION-LOG.md (120 lines), condition-based-waiting.md (116 lines), defense-in-depth.md (123 lines) and root-cause-tracing.md (170 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

11 files

PathSize
CREATION-LOG.md (opens in a new tab)4.2 KB
SKILL.md (opens in a new tab)9.3 KB
condition-based-waiting-example.ts (opens in a new tab)4.9 KB
condition-based-waiting.md (opens in a new tab)3.4 KB
defense-in-depth.md (opens in a new tab)3.6 KB
find-polluter.sh (opens in a new tab)1.9 KB
root-cause-tracing.md (opens in a new tab)5.2 KB
test-academic.md (opens in a new tab)653 B
test-pressure-1.md (opens in a new tab)1.9 KB
test-pressure-2.md (opens in a new tab)2.2 KB
test-pressure-3.md (opens in a new tab)2.6 KB

More from obra/superpowers

  • brainstorming

    obra/superpowers

    You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +2

    MIT · 305.7k repo stars · Updated 21 Oct 2026

  • diagnosing-superpowers

    obra/superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +1

    MIT · 305.7k repo stars · Updated 20 Oct 2026

  • dispatching-parallel-agents

    obra/superpowers

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 305.7k repo stars · Updated 23 Jul 2026

  • executing-plans

    obra/superpowers

    Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Bundles scripts

    MIT · 305.7k repo stars · Updated 21 Oct 2026

  • finishing-a-development-branch

    obra/superpowers

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network

    MIT · 305.7k repo stars · Updated 12 Aug 2026

  • receiving-code-review

    obra/superpowers

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

    Pattern check: Nothing flaggedWhat it can touch: Reaches the network

    MIT · 305.7k repo stars · Updated 23 Jul 2026

All skills in obra/superpowers