debugger-debbie

Solid

Dispatch a five-paradigm parallel debugging swarm against a stubborn, recurring, or shape-shifting bug. Each paradigm is a separate sub-agent with a different epistemology; they investigate independently and converge. Triggers: "investigate this deeply", "five paradigms on it", "dispatch Debugger Debbie", "we keep peeling the same kind of mask", "this is the Nth time this drift class has hit us", "the previous point-fixes did not stop the chain", "give me a structural answer not another reactive patch". Does NOT handle: one-line typo fixes, bugs with an already-localised stack trace, or first-occurrence bugs cheaper to fix than investigate (5×subagent budget).

AI & Automation 1,281 stars 105 forks Updated today MIT

Install

View on GitHub

Quality Score: 89/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# debugger-debbie Dispatch a five-paradigm parallel debugging swarm — five sub-agents, each constrained to a different structured debugging epistemology — against a single bug. Independent investigations converge on the same fix while each surfaces findings the others structurally cannot. This is a **heavy** skill. Five sub-agents × investigation time × tokens. Do not use it for cheap bugs. Use it when reactive patches keep arriving in the same shape and the team is asking for a structural answer. --- ## When to Use This Skill Use this skill when ANY of the following are true: - A bug class has recurred three or more times under different surface symptoms. - Multiple reactive PRs have shipped point-fixes and the next mask is expected. - The bug crosses a system boundary (CLI ↔ SaaS, producer ↔ schema, snapshot ↔ fixture) and ownership is contested. - An operator says "we keep finding new versions of the same thing". - A canary, gate, or release blocker has fired and the team needs high confidence before re-running it. - The mean-time-to-recur is shorter than the mean-time-to-fix. Do NOT use this skill when: - The bug has a clear stack trace and a single suspect file. - The fix is mechanical (typo, missing import, wrong constant). - Total token cost of five paradigms exceeds the cost of just shipping the fix. - A previous run of this skill is still in flight on the same bug. --- ## The Five Paradigms Each paradigm has a memorable label, a one-line essence,...

Details

Author
Priivacy-ai
Repository
Priivacy-ai/spec-kitty
Created
7 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category