debug
Skill1 starsChanged 5 months agoMITView on GitHub
Systematically diagnose and fix bugs, unexpected behavior, or failing tests with scientific method approach. Use when something is broken and the cause is not immediately obvious.
192 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- Firzus/agent-skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- microsoft/veronatheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-discord, add-slack 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.
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
- MicrosoftSkill
add-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
- +10 more from microsoft
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- s1lver091/pi-agent-config★ 473% same
Wrote their own version · 191
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- anthropics/knowledge-work-plugins★ 35ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- openai/symphony★ 27ksame name
- FalkorDB/FalkorDB★ 10ksame name
- NVIDIA/TensorRT-Model-Optimizer★ 5.6ksame name
- NVIDIA/Model-Optimizer★ 5.6ksame name
181 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 repository15 other files it gives its agents.
- ci-preflightSkill
- code-reviewSkill
- docx-processingSkill
- github-publishSkill
- implementSkill
- pdf-processingSkill
- permission-modesSkill
- planSkill
- pptx-processingSkill
- refactorSkill
- security-testingSkill
- specSkill
- testSkill
- web-developmentSkill
- xlsx-processingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 15 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
15
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Do not guess. Work systematically: reproduce, isolate, hypothesize, verify.
- Distinctive: line 12
Before touching any code, confirm you can reproduce the problem.
- Distinctive: line 17
If you cannot reproduce it, stop and ask for more information.
- Distinctive: line 21
If there is an error message or stack trace:
- Distinctive: line 22
Read the full trace, not just the first line
- Distinctive: line 24
Check what values were in scope at that point
- Distinctive: line 29
Add temporary logging or assertions to confirm assumptions about state
- Distinctive: line 31
Check: when did this last work?
- Distinctive: line 35
Write one sentence: "I believe X is happening because Y." Do not skip this.
- Distinctive: line 36
Do not skip this. It prevents you from randomly changing code and hoping it works.
- Distinctive: line 42
Check the actual values at runtime if possible
- Distinctive: line 43
Look for edge cases the author may have missed
- Distinctive: line 45
If your hypothesis is wrong, return to step 3.
- Distinctive: line 50
Do not refactor surrounding code while fixing a bug
- Distinctive: line 51
Add a test that would have caught this bug
“Common” is measured: kept by at least 6 in 10 of the 175 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
Debugging (Opus 级: 科学方法)
Do not guess. Work systematically: reproduce, isolate, hypothesize, verify.
Step 1: Reproduce
Before touching any code, confirm you can reproduce the problem.
- What is the exact input or sequence of actions that triggers it?
- Is it consistent or intermittent?
- Does it happen in all environments or only some?
If you cannot reproduce it, stop and ask for more information.
Step 2: Read the error
If there is an error message or stack trace:
- Read the full trace, not just the first line
- Find the deepest frame in your own code (not library internals) — that is your starting point
- Check what values were in scope at that point
Step 3: Isolate
Narrow down where the problem lives before reading more code.
- Add temporary logging or assertions to confirm assumptions about state
- Bisect: is the problem in the input, the transformation, or the output?
- Check: when did this last work? Use
git logandgit blameto find recent changes
Step 4: Form a hypothesis
Write one sentence: "I believe X is happening because Y." Do not skip this. It prevents you from randomly changing code and hoping it works.
Step 5: Verify the hypothesis
Find the code that should implement the behavior you described.
- Read it carefully
- Check the actual values at runtime if possible
- Look for edge cases the author may have missed
If your hypothesis is wrong, return to step 3. Do not guess-and-check.
Step 6: Fix
Make the smallest possible change that fixes the root cause.
- Do not refactor surrounding code while fixing a bug
- Add a test that would have caught this bug
- Record the lesson in ~/pi_learnings.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.