systematic-debugging
Skill0 starsChanged 4 months agoMITView on GitHub
Systematic root-cause debugging: investigate before fixing, log hypotheses, trace data flow, and stop to reassess after 3 failed fix attempts. Use when debugging a non-obvious failure, when a fix attempt did not work, or when asked to find a root cause. Skip for trivial errors whose cause is stated in the error message.
190 other projects use a version of this.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- chrysogonus/power-agentstheir own version, first seen Nov 8, 2026
- willy92wins/DayZ-Modding-Knowledge-Packtheir own version, first seen Nov 8, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
- Leodorareluctant259Skill
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
obraSkilldiagnosing-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.
Also in 20 projects that use this
mjunaidcaSkillbuilding-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).
Also in 4 projects that use this
- mjunaidcaSkill
building-chat-interfaces
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.
Also in 4 projects that use this
- +2 more from Leodorareluctant259
- +5 more from mjunaidca
Other versions190 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 190
- obra/superpowers★ 314ksame name
- NousResearch/hermes-agent★ 262ksame name
- open-metadata/OpenMetadata★ 16ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- openai/plugins★ 7.8ksame name
- ChrisWiles/claude-code-showcase★ 6.1ksame name
- farm-fe/farm★ 5.6ksame name
- microsoft/FluidFramework★ 4.9ksame name
180 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- answer-shapesSkill
- claim-verificationSkill
- create-prSkill
- findings-ledgerSkill
- git-safetySkill
- invariant-auditSkill
- lossless-doc-compressSkill
- model-orchestrationSkill
- office-hoursSkill
- plan-reviewSkill
- prompt-caching-playbookSkill
- review-ratchetSkill
- spec-fidelity-reviewSkill
- staff-reviewSkill
- test-adequacy-reviewSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 177 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
No fixes without investigation.
- Very specific: line 20
Before each probe, write one line: HYPOTHESIS: <what you believe is wrong and why> → TEST: <cheapest observation that can falsify it>.
- Distinctive: line 22
Run the test — a log line, an assertion, a targeted read — and record what it ruled out.
- Distinctive: line 28
Follow the value through the layers it passes through (input → transform → output) until you find the first place reality diverges from …
- Very specific: line 35
After 3 failed fix attempts — three HYPOTHESIS lines whose fixes did not survive their test — STOP.
“Common” is measured: kept by at least 6 in 10 of the 177 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Systematic debugging
The Iron Law
No fixes without investigation. Reproduce the failure first, read the actual error (not what you assume it says), and locate the failing layer before editing anything. A fix that skips investigation is a guess.
Hypothesis loop
Before each probe, write one line:
HYPOTHESIS: <what you believe is wrong and why> → TEST: <cheapest observation that can falsify it>.
Run the test — a log line, an assertion, a targeted read — and record what it
ruled out. If the hypothesis is wrong, don't guess again blind — return to
gathering evidence.
Trace the data, not the blame
Follow the value through the layers it passes through (input → transform → output) until you find the first place reality diverges from expectation. Fix at the divergence point, not at the symptom. A fix proposed before tracing the data flow is a guess, not a diagnosis.
The 3-strikes stop rule
After 3 failed fix attempts — three HYPOTHESIS lines whose fixes did not
survive their test — STOP. Do not try variant #4 of the same idea.
Re-read the evidence, list what every failed attempt assumed in common, and
question that shared assumption — it is usually a wrong architectural belief, not a
string of bad luck. Escalate or ask the user rather than continuing to guess.
Exit criteria
A fix ships only with the reproducing check that now passes — see
verification-before-completion for the evidence bar before claiming done.
Provenance
Distilled from the gstack /investigate skill by Garry Tan
(garrytan/gstack, MIT) — method only,
none of the gstack runtime (no telemetry, gbrain, or scope-freeze tooling
carried over).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.