takazudo/gco-2nd
skills/gco-2nd/SKILL.md
Get a second opinion from GitHub Copilot CLI on a plan or approach. Use when: (1) Planning phase of /x-as-pr or /x-wt-teams to validate the approach, (2) User says 'gco 2nd', 'copilot 2nd', or 'copilot opinion', (3) Wanting an alternative perspective before committing to a plan.
$ install --global
skillsauthnpx skillsauth add takazudo/claude-resources gco-2ndInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 9, 2026, 5:00 AM188.0s1 file scanned
SKILL.md
- name:
- gco-2nd
- description:
- Get a second opinion from GitHub Copilot CLI on a plan or approach. Use when: (1) Planning phase of /x-as-pr or /x-wt-teams to validate the approach, (2) User says 'gco 2nd', 'copilot 2nd', or 'copilot opinion', (3) Wanting an alternative perspective before committing to a plan.
GCO 2nd Opinion
Get a second opinion from GitHub Copilot CLI on a plan, approach, or codebase exploration.
Process
Step 0: Pre-flight Rate Limit Check
Before doing anything, check if Copilot is currently in degraded mode:
RATE_CHECK=$(node $HOME/.claude/scripts/gco-rate-limit.js check 2>&1)
If the output starts with degraded:, notify the user that Copilot is in low-cost mode (auto-downgraded model) but proceed with Copilot anyway — it is still usable. Do NOT skip.
Step 1: Build Context Prompt
Construct a prompt that includes:
- The current plan or approach being considered
- Key files or areas of the codebase involved
- Specific questions or concerns
You are reviewing a development plan. Provide a second opinion.
## Context
<what the project is, what repo we're in>
## Current Plan
<the plan or approach being considered>
## Questions
1. Are there any risks, edge cases, or issues with this approach?
2. Is there a simpler or better alternative?
3. Are there any files or areas of the codebase that should be considered but aren't mentioned?
4. Any other suggestions or concerns?
Be concise and practical. Focus on actionable feedback. If the plan looks solid, say so briefly — don't invent problems.
Step 2: Run Copilot
LOGDIR=$(node $HOME/.claude/scripts/get-logdir.js)
mkdir -p "$LOGDIR"
DATETIME=$(date +%Y%m%d_%H%M%S)
bash $HOME/.claude/skills/gco/scripts/gco-run.sh \
"<prompt>" \
"$LOGDIR/${DATETIME}-gco-2nd.md" \
"$LOGDIR/${DATETIME}-gco-2nd-stderr.log"
Timeout: 15 minutes.
Step 3: Collect Results
- Read the output file
- If empty or missing, check stderr log for errors (a 402 no-quota error means Copilot Premium is exhausted — treat it as a failure)
- If Copilot timed out, failed, or produced no output, skip — the plan proceeds without the second opinion
Step 4: Return Feedback
Return the Copilot feedback to the caller. The caller decides whether to incorporate it into the plan.
No fallback needed. If Copilot fails, skip — the plan proceeds without the second opinion. This is advisory, not critical.
When Called by /x-as-pr or /x-wt-teams
- After forming an initial plan, send it to Copilot for feedback
- If useful feedback is returned, update the plan
- Optionally re-run with the updated plan (up to 3 iterations total)
- Finalize and proceed with implementation
Important Notes
- Copilot reads workspace files for context — no need to paste file contents into the prompt
- All file writing done by Claude Code, never by Copilot
- This is advisory — never block the workflow if Copilot is unresponsive
- NEVER use
~in paths — use$HOME
Related Skills
takazudo/dev-linkify-cc-resources
development
VerifiedTrustedCommunity
Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.
10SKILL.mdUpdated Jun 2, 2026
takazudo/opus-2nd
development
VerifiedTrustedCommunity
Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.
10SKILL.mdUpdated May 29, 2026
takazudo/dev-ai-based-test
tools
VerifiedTrustedCommunity
AI-based testing via subagent + a per-task test-flow skill. Use when the user wants to verify something that mechanical assertions can't fully capture — image recognition, visual size/position comparison, animation smoothness, multi-step manual flows that need AI judgment. Triggers: 'AI-based test', 'AI test', 'visual verify', 'image recognition test', 'manual operation test', 'human-eye check', 'verify visually', 'compare screenshots', 'looks the same', 'looks correct'. The skill's job is to (1) author a focused test-flow skill that captures the exact procedure + verdict criteria, then (2) dispatch a verification subagent via the Agent tool that loads BOTH the test-flow skill AND a browser-driving skill (/verify-ui primary, /headless-browser fallback) so the subagent has clear context and consistent verdicts. NEVER uses `claude -p` — subagent dispatch goes through the Agent tool exclusively.
10SKILL.mdUpdated May 29, 2026
takazudo/cleanup-resources
development
VerifiedTrustedCommunity
End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.
10SKILL.mdUpdated May 29, 2026