0xnyn/canary/canary-review
Claude Code and agent skill by 0xnyn/canary
- community
Checking that the SKILL.md file is still in the repository.
Open and triage recorded Canary sessions in the local viewer. Use when the user wants to look at, replay, compare, or triage a recorded session — or asks what happened in a run, to open the report, or to see the trace/video/screenshots. Trigger phrases — "open the canary viewer", "show me the last session", "what failed in that run", "review the recording", "open the report".
Install
npx vskill@latest install 0xnyn/canary/canary-reviewSKILL.md
Canary review (triage)
Open recorded sessions in the local viewer and summarize what happened. Sessions live in ~/.canary/sessions/<id>/ — each has results.json, report.html, and trace / video / HAR / console / screenshots.
When to use
- Browsing or replaying recorded sessions.
- Triaging a run: which steps passed/failed, console errors, network failures.
- Opening the report or the trace for a specific session.
Examples
Example 1: open the viewer
User says: "open the canary viewer" or "let me see my sessions" Run npx @usecanary/ui (a local server, like npx playwright show-trace) in the background and give the URL. Pass --dir <path> for a non-default folder.
Example 2: triage the last run
User says: "what failed in the last session?" or "summarize the latest run" Read the newest ~/.canary/sessions/*/results.json, summarize steps (pass/fail, durations, console/network issues) with the report.html path, then open the viewer.
Workflow
- Browse:
npx @usecanary/ui(--dir <path>for a non-default sessions folder). List sessions
without the UI via npx @usecanary/cli session list; check what's running with npx @usecanary/cli status [--session <id>].
- Summarize: read the session's
results.json(steps, summary, artifacts) and report pass/fail
with counts; cite the report.html path.
- Review is read-only — don't modify session files.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/canary-review/SKILL.md
Popularity
- Repository stars
- 485
- Repository forks
- 38
- 7-day trend score
- 31
Stars and forks are for the whole GitHub repository, not this skill alone. 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
[](https://verified-skill.com/skills/0xnyn/canary/canary-review)