Perf Theory Gatherer
- 63 installs
- 931 repo stars
- Updated July 26, 2026
- avifenesh/agentsys
perf-theory-gatherer is a skill that generates git-history-backed performance hypotheses for a specific scenario.
About
perf-theory-gatherer generates performance hypotheses for a specific scenario by reviewing recent git history and identifying the code paths involved. A developer uses it during performance work to produce up to five evidence-backed hypotheses before running any experiments. It only proposes theories and never suggests optimizations, keeping diagnosis separate from fixes.
- Generates up to 5 performance hypotheses tied to git history and code paths
- Each hypothesis carries evidence (file/path or git change) and a low/medium/high confidence
- Hypotheses only, no optimization suggestions
Perf Theory Gatherer by the numbers
- 63 all-time installs (skills.sh)
- Ranked #284 of 596 Debugging skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
perf-theory-gatherer capabilities & compatibility
- Capabilities
- perf hypothesis · git history analysis · code path analysis
- Use cases
- debugging
- Pricing
- Free
What perf-theory-gatherer says it does
Generate performance hypotheses for a specific scenario.
MUST check git history before hypothesizing.
No optimization suggestions; only hypotheses.
npx skills add https://github.com/avifenesh/agentsys --skill perf-theory-gathererAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 63 |
|---|---|
| repo stars | ★ 931 |
| Last updated | July 26, 2026 |
| Repository | avifenesh/agentsys ↗ |
What it does
Produce evidence-backed performance hypotheses for a slow scenario before running perf experiments.
Who is it for?
Diagnosing a slow scenario by forming evidence-linked hypotheses before testing.
Skip if: Applying optimizations or running the perf experiments themselves.
When should I use this skill?
When generating performance hypotheses backed by git history and code evidence.
What you get
A ranked list of up to 5 performance hypotheses, each with evidence and a confidence level.
- performance hypotheses with evidence and confidence
By the numbers
- up to 5 hypotheses maximum
- 3 required steps
Files
perf-theory-gatherer
Generate performance hypotheses for a specific scenario.
Follow docs/perf-requirements.md as the canonical contract.
Required Steps
1. Review recent git history (scope to relevant paths when possible). 2. Identify code paths involved in the scenario (repo-intel or grep). 3. Produce up to 5 hypotheses with evidence + confidence.
Output Format
hypotheses:
- id: H1
hypothesis: <short description>
evidence: <file/path or git change>
confidence: low|medium|high
- id: H2
...Constraints
- MUST check git history before hypothesizing.
- No optimization suggestions; only hypotheses.
- Keep to 5 hypotheses maximum.
Related skills
Azure DiagnosticsSystematically diagnose and resolve production issues on Microsoft Azure using official Microsoft guidance.495k1.3kAzure MessagingQuickly diagnose and fix connection, authentication, and message-processing failures when using Azure Event Hubs or Service Bus SDKs.483k1.3k
Diagnosing BugsGet a systematic, step-by-step process that surfaces the real root cause instead of guessing at bugs.291k200k
Use My BrowserWhen their agent task requires access to the live browser session, rendered DOM state, authenticated dashboards, localhost apps, or DevTools-selected elements instea269k71
Systematic DebuggingFollow a repeatable four-phase process that forces root-cause discovery before any code changes.210k265k
Safe DebugGet conservative, non-destructive diagnosis of deep learning and agent errors before any code changes are made.185k512