takazudo/opus-2nd
skills/opus-2nd/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add takazudo/claude-resources opus-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, 5:01 AM133.4s1 file scanned
SKILL.md
- name:
- opus-2nd
- description:
- 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.
- argument-hint:
- <plan-file-path>
Opus 2nd Opinion
Provide a second opinion on a development plan by spawning a general-purpose Agent with model: opus. Mirrors the Sonnet-subagent pattern already used by /big-plan's Step 9 verification, just with Opus.
$ARGUMENTS is the absolute path to the plan markdown file (and optionally extra free-text context after the path).
Process
Step 1: Spawn the Opus subagent
Invoke the Agent tool with:
subagent_type:general-purposemodel:opusdescription:Opus 2nd opinion on planprompt: the self-contained prompt template in Step 2 below, with$ARGUMENTSsubstituted into the plan path.
Step 2: Prompt template
You are providing an independent Opus second opinion on a development plan.
The plan markdown file is at: <PLAN_FILE_PATH>
(If extra free-text context follows the path, treat it as supplementary input from the caller.)
Read the plan file. If it references source GitHub issues you need to understand intent, fetch them with `gh issue view <number>`.
Answer concretely:
1. Are there any risks, edge cases, or correctness traps in this approach?
2. Is the sub-task breakdown sound? Any sub-task too large, too coupled, or too vague to start without questions?
3. Are there missing sub-tasks or hidden dependencies the plan glossed over?
4. Is the dependency order correct? Can more sub-tasks run in parallel? Are the wave assignments sensible?
5. Are any items from the plan's "Original requirements checklist" missing from the sub-tasks?
6. Is there a simpler or materially better alternative worth flagging?
Be concise and practical. Focus on actionable feedback. If the plan looks solid, say so briefly — do not invent problems to look thorough.
Return a single markdown response with this shape:
## Opus review
### Verdict
<one-sentence overall judgment: solid / minor revisions / significant rework>
### Concrete suggestions
- <suggestion 1>
- ...
### Risks / edge cases
- <risk 1>
- ...
### Missing or under-specified
- <gap 1>
- ...
Omit any subsection with nothing to report rather than padding it with filler.
Read-only — do not edit any files. The caller decides what to incorporate.
When this skill is called from /big-plan's Step 9 (verification), replace the review-questions block with the verification questions/report format specified in that step instead.
Step 3: Return the feedback
The Agent's response IS the review. Hand it back to the caller verbatim or under a ### Opus review / ### Opus verification subsection of the caller's review log.
Important Notes
- Opus uses Anthropic quota — more expensive than
/codex-2nd//gco-2nd. Justify the cost with concrete, actionable feedback - Caller is responsible for consolidating Opus output with other reviewers when multiple flags were combined
- Read-only — the spawned Agent must never edit files
- 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/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
takazudo/prototype-first-wisdom
tools
VerifiedTrustedCommunity
Solve a complex bug or design problem by building a tiny isolated prototype first, instead of patching the production system in place. Trigger PROACTIVELY when (1) the same bug has resisted 2+ in-place fix attempts (fail-retry loop), (2) the user mentions "minimal prototype", "from zero", "from scratch", "simple script", "sandbox", "standalone", "isolate", "play around", or "try a sandbox version", (3) you find yourself ranking a list of suspects and ruling them out via source-grep on a runtime/visual bug, (4) the user is brainstorming many design options for a UI surface and wants speed (e.g., "make 20 patterns of the top page"), (5) the next reasonable step would be "instrument the existing complex code" — pause and consider this skill instead. Build the prototype in the repo-scoped Dropbox-synced cclogs dir (`$DROPBOX_CCLOGS_DIR/<repo>/<descriptive-name>/`) so it survives switching between Mac and WSL; the exception is a prototype that must import the repo's production code or use its workspace/Vite tooling — keep that one in `__inbox/<descriptive-name>/` in the project root (in-repo, gitignored) so relative imports resolve. Match the project's tech stack (HTML+CSS+vanilla JS for static sites, Vite+React for React apps, Node script for CLI/utility logic). Don't commit it — its value is the learning, not the artifact. **Variant for repeated regression cycles (8+ in-place fixes on the same bug class):** keep the prototype as a committed sub-package named `packages/prototype-<topic>/` — see the "Variant: project-level reference prototype" section below.
10SKILL.mdUpdated May 15, 2026