All skills

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

  • 1 file
  • 831 B
  • Updated 8 months ago
  • GitHub

Use this Skill: https://skilld.dev/gh/composiohq/awesome-claude-plugins/theory

This session only. Nothing lands on disk.

SKILL.md

≈23 tokens always: the name and description. ≈170 when used: this file.

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.

Source: SKILL.md on GitHub

No third-party reports yet.

Signed by skilld at 12730bf. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 8 months ago
version
1.0.0

README badge

README badge for composiohq/awesome-claude-plugins/theory