rbadillap/sre/evidence-before-claims

Claude Code and agent skill by rbadillap/sre

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Discipline. Verify before saying something is true, and say what wasn't verified. Applied by the orchestrators in this package before stating a cause, declaring a fix effective or reporting a result.

Install

npx vskill@latest install rbadillap/sre/evidence-before-claims

SKILL.md

Evidence before claims

Verify before saying something is true, and say what wasn't verified.

When

Before naming a cause, before saying a mitigation worked, before marking anything done, and in every written result.

When not

Never skip it. When there's no time to verify, the claim is written as a hypothesis, and the work goes on.

How

  1. Label every statement as one of:
  • Verified: a signal, log, command output or record shows it. Say which.
  • Hypothesis: likely, not yet shown. Say what would confirm or rule it out.
  • Not verified: couldn't be checked. Say why.
  1. Turn hypotheses into checks. "The job is exhausting connections" becomes a check: which clients hold the connections, and did the timing match?
  2. Test the action, not only the cause. A mitigation is also an experiment. If the signal recovers after it, that supports the cause. If nothing changes, undo it and reconsider.
  3. Confirm with the signal users live. A fix is effective when the user-facing signal recovers, not when the process restarts.

The mistake it prevents

A guess travels as a fact, and the next decision is built on it.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/rbadillap/sre/evidence-before-claims/badge)](https://verified-skill.com/skills/rbadillap/sre/evidence-before-claims)

Something wrong with this skill or its page? Tell us.