alexei-led/researching-web
plugins/dev-tools/skills-codex/researching-web/SKILL.md
Web research via Perplexity AI. Use for technical comparisons (X vs Y), best practices, industry standards, recent developments. Triggers on "research", "compare", "vs", "best practice", "which is better", "pros and cons", "what's new in". NOT for API references or library docs (use looking-up-docs for syntax, examples, and framework documentation).
$ install --global
skillsauthnpx skillsauth add alexei-led/claude-code-config researching-webInstall 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: May 11, 2026, 3:38 AM18.6s1 file scanned
SKILL.md
- description:
- Web research via Perplexity AI. Use for technical comparisons (X vs Y),
- name:
- researching-web
<!-- generated by scripts/build/generate-skills.py — edits to this file will be overwritten by `make build`. Edit the canonical SKILL.md (or add a SKILL.codex.md / SKILL.pi.md sidecar to diverge). -->
<!-- Platform guidance for non-Claude models (Codex CLI, Gemini CLI) -->
<!-- Persistence: Keep going until the task is fully resolved. Do not stop at the first obstacle. -->
<!-- Tool use: Use available tools to verify — do not guess at file contents, paths, or command output. -->
<!-- Planning: Reflect between steps. Decompose complex problems into logical sub-steps before acting. -->
<!-- Reliability: Assess risk before irreversible actions. Ask for clarification on ambiguity. -->
<!-- Completeness: Generate complete responses without truncating. Review your output against the original constraints. -->
Web Research with Perplexity
Default: Call Perplexity MCP directly. Only spawn agent when codebase context is explicitly needed.
Critical Routing Rules
- Use this for web-grounded research: comparisons, recommendations, best practices, standards, recent developments, licensing, ecosystem, and market/release facts.
- Do not use this for narrow API syntax or framework examples. Route those to
looking-up-docs; prefer official docs for exact syntax. - Do not answer research questions from memory. Use current sources, cite URLs, and mark stale-source risk or unknowns. If live retrieval is unavailable, say exactly that final evidence must be grounded in URL-cited sources before factual claims or recommendations are trusted.
- Separate sourced facts from recommendation/judgment. If evidence is missing, say what is missing instead of filling gaps.
- If the user asks to "describe the workflow", describe the source-gathering and output structure; do not present an uncited final recommendation as fact.
Response Contract
For research output, include:
- Research question and decision criteria.
- Sources consulted or source plan; citations/URLs required for factual claims. If only a plan is available, state: "final evidence must be grounded in URL-cited sources."
- Evidence table or bullets grouped by criterion.
- Recommendation separated from sourced facts.
- Unknowns, assumptions, and stale-source risks.
Best For
- Technology comparisons (X vs Y)
- Best practices, industry standards
- OWASP, security guidelines
- Official docs as supporting sources for non-syntax facts
- Stable technical content
Default Mode: Direct Web Research
Use this for 90% of research requests. When user says "ask Perplexity", "research", "look up", etc., use the available web research tool with a scoped research question.
This is fast, reliable, and what users expect.
Deep Mode: Agent (Rare)
Only use when user explicitly asks to compare research with their current code.
Trigger phrases that warrant agent:
- "compare my code to best practices"
- "is my implementation following standards"
- "research and show how my code differs"
DO NOT use agent for:
- Simple "ask Perplexity about X" requests
- General research questions
- "What is the best way to do X" (unless they mention their code)
Query Formulation Tips
- Be specific: "Go 1.25 error handling best practices 2025"
- Include context: "Redis vs Memcached for session storage in Go services"
- Ask comparisons: "Pros and cons of gRPC vs REST for microservices"
- Include year: "Claude Code context optimization 2025"
Reference Following (Deep Research)
After Perplexity returns results with citations:
- Review all cited URLs in the response
- WebFetch top 2-3 most relevant sources for deeper context
- Synthesize comprehensive answer combining all sources
# After Perplexity response with citations
WebFetch(url="<cited-url-1>", prompt="Extract key details about <topic>")
WebFetch(url="<cited-url-2>", prompt="Extract implementation examples")
Use reference following when:
- Initial answer is high-level and needs specifics
- User asks "tell me more" or "dig deeper"
- Implementing something that needs detailed guidance
Output Structure
## Summary
[Key findings - 2-3 sentences]
## Details
[Organized findings by topic]
## Recommendations
[Actionable items for the project]
## Sources
- [Source](url) - [what was learned]
Related Skills
alexei-led/writing-shell
tools
VerifiedTrustedCommunity
Idiomatic shell development for POSIX sh, Bash, Zsh, Fish, hooks, CI shell steps, and scriptable CLI glue. Use when writing or changing `.sh`, `.bash`, `.zsh`, `.fish`, `.bats`, shell functions, shell pipelines, or command-runner recipes. Emphasizes portability, quoting, safe filesystem/process handling, non-TUI CLI tools, ShellCheck, shfmt, Bats, and ShellSpec. NOT for Python, TypeScript, Go, web code, or infrastructure operations.
33SKILL.mdUpdated Jun 5, 2026
alexei-led/spec-flow
tools
VerifiedTrustedCommunity
Use when planning, executing, checkpointing, finishing, or inspecting lightweight spec-driven work. Runs one task at a time using `.spec/` markdown files and the bundled `specctl` helper. NOT for broad product discovery beyond a short requirement interview.
33SKILL.mdUpdated Jun 5, 2026
alexei-led/operating-infra
testing
VerifiedTrustedCommunity
Author, inspect, troubleshoot, and review infrastructure across IaC, Kubernetes, cloud resources, containers, CI/CD, and Linux hosts. Use when changing Terraform/OpenTofu, Kubernetes, Helm, Kustomize, Dockerfiles, GitHub Actions, AWS, GCP, Cloud Run, BigQuery, IAM, logs, instances, or service health. NOT for deploy/apply/rollback workflows (see deploying-infra). NOT for shell scripts or generic command pipelines (see writing-shell).
33SKILL.mdUpdated Jun 5, 2026
alexei-led/configuring-git-hygiene
development
VerifiedTrustedCommunity
Configure safe git workflow hygiene: pre-commit/pre-push hooks, Gitleaks secret scanning, .gitignore rules, local git config, and guardrails. Use when setting up git hooks, gitleaks/git leaks, staged pre-commit checks, pre-push validation, core.hooksPath, .gitignore, or git config best practices. NOT for creating commits (use committing-code), cleaning branches/worktrees (use cleanup-git), or creating worktrees (use using-git-worktrees).
33SKILL.mdUpdated Jun 5, 2026