Inspect Runtime Evidence

Use when determining whether an adapter, integration, feature, or package is actually executable from read-only runtime evidence.

9 stars 3 forksOther

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sandbaseai/workbuddy-skill --skill inspect-runtime-evidence
Manual install
git clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/inspect-runtime-evidence ~/.claude/skills/inspect-runtime-evidence

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Inspect Runtime Evidence

Use this skill to answer “does it actually run and support the requested capability?” from evidence, not from labels, configuration, or an optimistic README. Stay read-only: do not mutate logic, assets, packages, evidence, runtime state, or release artifacts.

## Define the inspection

Record the exact adapter, integration, feature set, package, version, platform, environment, and requested capabilities. Use exact identifiers and capability names; never select by product genre, display label, or a similar-looking implementation. State the report identity, evidence time, scope, and out-of-scope paths.

## Map capabilities precisely

For every requested capability, map it to one status:

- **supported:** verified by current execution evidence;
- **extension-verified:** verified only through an explicitly named extension or adapter;
- **authoring-only:** can be configured or authored but has no execution proof;
- **blocked:** evidence shows a missing dependency, incompatible contract, permission, platform, or failure;
- **unknown:** evidence is absent, stale, partial, or contradictory.

Do not collapse unknown into supported. A missing hosted row is not a pass. A fake, recording, or deterministic test backend is local evidence only and must not be described as native or production execution.

## Assess evidence quality
Read the full skill on GitHub

Details

Skill name
inspect-runtime-evidence
Path
skills/inspect-runtime-evidence/SKILL.md
License
MIT
Repo updated
8 September 2026

FAQ

What does the Inspect Runtime Evidence skill do?

Use when determining whether an adapter, integration, feature, or package is actually executable from read-only runtime evidence.

How do I install the Inspect Runtime Evidence skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill inspect-runtime-evidence. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Inspect Runtime Evidence popular?

It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.

Related skills

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.