SkillsAdd

smithery/composiohq

perf-theory-gatherer

Use when generating performance hypotheses backed by git history and code evidence.

Installation

$ npx skills add smithery/composiohq --skill perf-theory-gatherer
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

perf-theory-gatherer Similar name
composio-community/awesome-claude-plugins

Use when generating performance hypotheses backed by git history and code evidence.

479 installs

Also in this package

Other skills from smithery/composiohq · top by installs.

npx skills add smithery/composiohq
twitter-algorithm-optimizer 0 tailored-resume-generator 0 support-ticket-triage 0 spreadsheet-formula-helper 0 perf-theory-tester 0 perf-profiler 0 perf-investigation-logger 0 perf-code-paths 0 perf-benchmarker 0 perf-baseline-manager 0

Browse all from smithery/composiohq

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 831 B
  • docs SUMMARY.md 111 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

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-map 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.