Debug incident
Finish with Proof: a portable execution protocol for coding agents—diagnose before patching, bound delegation, and verify real outcomes.
npx -y skills add MiaoY0uShan/FP --skill debug-incidentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Debug-first diagnosis protocol for unknown failures. Use when the cause is unknown, a bug needs diagnosis before fixing, or the user asks 'what's wrong' without requesting a fix. Provides structured hypothesis-probe-decision loop with evidence tracking.
SKILL.md
1.2 KB, 189 tokens by cl100k_base, as published. Nobody here has run it
FP Debug-First Diagnosis
Load ../templates/debug-incident-checklist.md for the full checklist.
Route
pin symptom → read-only baseline → falsifiable hypothesis
→ cheapest discriminating probe → decision → authorized fix
→ original reproduction + regression + negative control
Rules
- Read-only until a cause is supported and user authorizes a fix.
- Keep at most two active hypotheses; run one discriminating probe at a time.
- Speculative patches are never probes.
- Three consecutive non-narrowing probes → architecture/observability checkpoint.
- After hypothesis is supported, extra probes must change a named decision or fill a named acceptance row. Otherwise stop and reuse evidence.
Active incident variant: OBSERVE → CONTAIN → RESTORE → REPAIR → LEARN
Preserve evidence, access, and rollback. Restore service before permanent repair.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most debug triage skills give in 189 tokens
Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07
- Investigate root cause before proposing any fixin 102 of 839, across 67 files
- Read error messages completelyin 89 of 839, across 49 files
- Create a failing test case before fixingin 84 of 839, across 46 files
- Reproduce the issue consistentlyin 82 of 839, across 41 files
- Change one variable at a timein 82 of 839, across 42 files
- Check recent changesin 74 of 839, across 36 files
- Write the regression test before fixingin 74 of 839, across 40 files
- Fix the root cause not the symptomin 60 of 839, across 45 files
- Implement a single fix at a timein 59 of 839, across 20 files
- Trace data flow backward to the sourcein 50 of 839, across 20 files
- Remove all debug instrumentationin 49 of 839, across 13 files
- Form a single hypothesisin 48 of 839, across 18 files
Said here and by no other author read
- load the incident checklist template
- pin the symptom first
- establish a read-only baseline
- run the cheapest discriminating probe
- keep at most two active hypotheses
- stop probing after three non-narrowing probes
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.