ShaheerKhawaja/deep-research
skills/deep-research/SKILL.md
8-phase autonomous research pipeline with multi-source discovery, 4-layer citation verification, hypothesis generation, and PIVOT/REFINE/PROCEED decision loops. Confidence-gated — loops until 95%+ confidence.
$ install --global
skillsauthnpx skillsauth add ShaheerKhawaja/ProductionOS deep-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: Apr 23, 2026, 2:11 AM10.6s1 file scanned
SKILL.md
- name:
- deep-research
- description:
- 8-phase autonomous research pipeline with multi-source discovery, 4-layer citation verification, hypothesis generation, and PIVOT/REFINE/PROCEED decision loops. Confidence-gated — loops until 95%+ confidence.
- argument-hint:
- [topic, depth, or source mix]
deep-research
Overview
Use this as the Codex-first research workflow for ProductionOS. It should take a topic, break it into concrete research questions, gather and verify sources, synthesize competing hypotheses, and only deliver claims that are evidence-backed.
Source references:
.claude/commands/deep-research.mdscripts/arxiv-scraper.sh
Inputs
topic: required research question or areadepth:quick,standard,deep, orexhaustivesources:arxiv,web,docs, orall
Codex Workflow
- Scope the topic into 3-5 specific research questions.
- Discover sources appropriate to the selected depth.
- Verify sources before trusting them.
- title and author sanity
- direct relevance
- source quality
- Synthesize the evidence.
- consensus
- contradictions
- missing information
- Generate competing hypotheses and select the best-supported one.
- If confidence is still low, refine the search instead of bluffing.
Expected Output
- research questions
- verified source set
- synthesis with contradictions called out
- selected hypothesis with confidence
- explicit unknowns
Guardrails
- do not present weakly supported claims as facts
- prefer primary sources when available
- if confidence stays low, say so and stop rather than pretending certainty
Related Skills
ShaheerKhawaja/writing-plans
tools
VerifiedTrustedCommunity
Implementation planning workflow that turns approved ideas into dependency-aware execution plans.
7SKILL.mdUpdated Apr 23, 2026
ShaheerKhawaja/wiki-rag
development
VerifiedTrustedCommunity
Local RAG and Graph RAG over the SecondBrain wiki vault. Progressive context loading (hot cache -> index -> domain -> entity). Graph traversal via wikilink resolution. Use when agents need cross-project context, when answering questions that span multiple domains, or when building context for planning tasks. Triggers on: "wiki context", "cross-project context", "what do we know about", "check the wiki", "graph context", "/wiki-rag".
7SKILL.mdUpdated Apr 23, 2026
ShaheerKhawaja/ux-genie
devops
VerifiedTrustedCommunity
UX improvement pipeline — creates user stories from UI guidelines, maps user journeys, identifies friction, dispatches fix agents. The user-experience equivalent of /production-upgrade.
7SKILL.mdUpdated Apr 23, 2026
ShaheerKhawaja/tdd
development
VerifiedTrustedCommunity
Test-driven development workflow that writes failing tests first, implements minimally, and refactors safely.
7SKILL.mdUpdated Apr 23, 2026