RonanCodes/perplexity-research
skills/perplexity-research/SKILL.md
AI-powered web research using the Perplexity API. Searches the live web and returns sourced answers with citations. Use when user wants to research, look up, search the web, or find current information.
research
Updated May 1, 2026
$ install --global
skillsauthnpx skillsauth add RonanCodes/ronan-skills perplexity-researchInstall 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 1, 2026, 2:29 AM179.4s1 file scanned
SKILL.md
- name:
- perplexity-research
- description:
- AI-powered web research using the Perplexity API. Searches the live web and returns sourced answers with citations. Use when user wants to research, look up, search the web, or find current information.
- category:
- research
- argument-hint:
- <query> [--model sonar|sonar-pro|sonar-reasoning-pro]
- allowed-tools:
- Bash(curl *) Read Write Edit
- - pipeline:
- input
- - platform:
- agnostic
- - role:
- primitive
Perplexity Research
Search the live web via the Perplexity API. Returns sourced answers with citation URLs.
Usage
/perplexity-research "What are the latest changes in Claude Code?"
/perplexity-research "React Server Components best practices" --model sonar-pro
Models
| Model | Best for |
|-------|----------|
| sonar | Quick facts, simple questions (default) |
| sonar-pro | Complex multi-step, more citations |
| sonar-reasoning-pro | Chain-of-thought, deep analysis |
Process
1. Find API Key
Check these locations in order for PERPLEXITY_API_KEY:
${CLAUDE_PLUGIN_DATA}/.env(plugin-wide, survives updates — preferred)~/.config/ro/.env- Project root
.env - Environment variable already set
If not found: direct user to https://perplexity.ai/settings/api to create a key (starts with pplx-), then save it to the plugin data dir: mkdir -p "$CLAUDE_PLUGIN_DATA" && echo "PERPLEXITY_API_KEY=pplx-..." >> "$CLAUDE_PLUGIN_DATA/.env". Or run /ro:setup-wizard --tokens.
2. Call the API
# Load the key
PERPLEXITY_API_KEY=$(grep PERPLEXITY_API_KEY <env-file> | cut -d= -f2-)
# Make the request
RESPONSE=$(curl -s https://api.perplexity.ai/chat/completions \
-H "Authorization: Bearer $PERPLEXITY_API_KEY" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"MODEL\",
\"messages\": [{\"role\": \"user\", \"content\": \"QUERY\"}]
}")
Default model is sonar. Override with --model flag or PERPLEXITY_MODEL from .env.
3. Parse and Display
The response is OpenAI-compatible JSON. Answer: choices[0].message.content. Citations: citations array at root level.
Display as a Research Results heading with the answer text, then a Sources section with numbered citation URLs. Extract citations: echo "$RESPONSE" | python3 -c "import sys,json; [print(f'{i+1}. {u}') for i,u in enumerate(json.loads(sys.stdin.read()).get('citations',[]))]"
4. Save Results (optional)
If the user wants to save, write to research-<slugified-query>.md with frontmatter (title, date, source: perplexity-api, model).
Error Handling
- 401: Invalid API key — guide to https://perplexity.ai/settings/api
- 429: Rate limited — wait and retry
- Empty response: Suggest refining the query
Shared Plugin .env
All /ro:* skills share one env file at ${CLAUDE_PLUGIN_DATA}/.env (Claude Code) or ~/.config/ro/.env (other agents). See .env.example at the plugin root.
PERPLEXITY_API_KEY=pplx-...
PERPLEXITY_MODEL=sonar
Never commit API keys.
Related Skills
RonanCodes/skills/linear-pipeline
testing
VerifiedTrustedCommunity
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
SKILL.mdUpdated Jul 5, 2026
RonanCodes/skills/in-your-face
development
VerifiedTrustedCommunity
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
SKILL.mdUpdated Jul 5, 2026
RonanCodes/codex
tools
VerifiedTrustedCommunity
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
SKILL.mdUpdated Jul 5, 2026
RonanCodes/warranty-check
research
VerifiedTrustedCommunity
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".
SKILL.mdUpdated Jul 4, 2026