coldpass

Xwh630/ai-agent-handbook

GitHub ↗ · How this check works

Per-setup public labels: Linux / Haiku: Works

Static status badge · SVG · read-only JSON. Embed with ![Coldpass status](https://coldpass.dev/badge/Xwh630--ai-agent-handbook.svg).

ai-agentautogencrewailanggraphllamaindexmcp

Works

Only older checks are saved; no current product test.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Tested on Linux
PlatformHaikuLuna
Linuxyes

Linux / Haiku 5.5: yes · Oct 16, 2026 · 09eaced97246 · claude-code / 2.1.300 (Claude Code)
Recorded operation: python3 /workspace/examples/10-agent-skill/main.py /workspace/examples/10-agent-skill/sample-skill

Needs keys or browser
None seen
Setup time
22 s
22 s to a working result
Issue
none found in recorded check

Safety: no observations were recorded for the selected revision. Functional results do not establish a safety result.

Run details

Haiku 5.5

Native agent · Checked operation passed

Checked operation python3 /workspace/examples/10-agent-skill/main.py /workspace/examples/10-agent-skill/sample-skill

Agent-reported scope: Run the README-documented Agent Skill validator (examples/10-agent-skill/main.py) on the bundled sample-skill; it performs static SKILL.md spec checks and reports pass/fail counts.

Run details
run
Xwh630--ai-agent-handbook-claude-haiku-5-5-1792198062392946731
date
Oct 16, 2026
time to working
21.6s
product hosting / execution
Local command in the guest
recorded operation scope
Exercised: the zero-dependency skill validator on the bundled sample skill, real run returning exit 0 with 5 passes, 0 errors, 0 warnings. Not exercised: the full requirements.txt install (crewai, chromadb, langgraph, etc.), any LLM-backed example (examples/01-react-agent and others need OPENAI_API_KEY or similar, so no credentials were obtained), the --strict/--json modes, the Docker path, and the full repository lint/unit suites (out of scope).
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.007411
Recorded source
https://github.com/Xwh630/ai-agent-handbook
Tool transport
mcp-assigned-vm
Test version
readme-752a79557132262b5d1322ca513a303546bc27f661e57355353618601d631408
revision
09eaced9724605cdbe05f261b70fc966c94c6c8a
Whose fault: not assigned · resolved

  • Evidence unavailable in the public snapshot.
What the agent did

Run the README-documented Agent Skill validator (examples/10-agent-skill/main.py) on the bundled sample-skill; it performs static SKILL.md spec checks and reports pass/fail counts.

README.md: 快速开始 (examples/10-agent-skill/README.md quickstart: python3 main.py ./sample-skill)
python3 main.py ./sample-skill (run from examples/10-agent-skill, Python 3.12.3, stdlib only, no install required)

run JSON · checker evidence · agent report unavailable · transcript excerpt unavailable · error excerpt unavailable