Agentsys perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
install
source · Clone the upstream repo
git clone https://github.com/agent-sh/agentsys
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/agent-sh/agentsys "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.kiro/skills/perf-theory-gatherer" ~/.claude/skills/agent-sh-agentsys-perf-theory-gatherer && rm -rf "$T"
manifest:
.kiro/skills/perf-theory-gatherer/SKILL.mdsource content
perf-theory-gatherer
Generate performance hypotheses for a specific scenario.
Follow
docs/perf-requirements.md as the canonical contract.
Required Steps
- Review recent git history (scope to relevant paths when possible).
- Identify code paths involved in the scenario (repo-intel or grep).
- 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.