kenoxa/run-research
skills/run-research/SKILL.md
Use when: 'deep research', 'outsource research', 'research prompt', 'research handoff'.
$ install --global
skillsauthnpx skillsauth add kenoxa/spine run-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 22, 2026, 6:59 AM283.7s4 files scanned
SKILL.md
- name:
- run-research
- description:
- >-
- Use when:
- deep research', 'outsource research', 'research prompt', 'research handoff'.
- argument-hint:
- [research goal] [--target chatgpt|claude] [--depth deep]
Read-only — no code changes, no builds, no test runs.
Phases
Phase Trace: log row per phase. Frame (zero-dispatch), Gather (G), Compile (zero-dispatch), Output (zero-dispatch). Include depth classification and target.
| Phase | Agent | Reference |
|-------|-------|-----------|
| Frame | mainthread | — |
| Gather | @scout + gather-scout.md OR @researcher + gather-researcher.md | gated |
| Compile | mainthread | template-prompt.md |
| Output | mainthread | — |
Frame
Clarify research goal. Identify:
- Research question — what decision does this inform?
- Scope — boundaries, in/out, time range
- Output format — named format from template or user-specified
- Target —
--target chatgpt|claude(default:chatgpt) - Depth — standard (default) or
--depth deep
Gather
Gated dispatch:
| Condition | Dispatch |
|-----------|----------|
| Purely external (no codebase dependency) | zero-dispatch |
| Standard depth | @scout + references/gather-scout.md |
| --depth deep | @researcher + references/gather-researcher.md |
Output: .scratch/<session>/research-context.md
Compile
- Read template-prompt.md.
- Fill 4 required sections from goal + gathered context.
- Apply security redaction (rules in template ref).
- Apply UI adaptation per
--target(table in template ref). - Select output format.
Output
- Write prompt to
.scratch/<session>/research-prompt.md. - Attempt clipboard copy (
pbcopy/xclip). Fail-silent on error. - Print: file path, character count, clipboard status, target UI.
- Suggest: "Paste into [target] Deep Research. When you have results, start
/do-frameor/do-designwith the findings."
Anti-Patterns
- Answering the research question instead of compiling a prompt for external AI
- Skipping security redaction before output
- Auto-dispatching do-frame or do-design after output (suggest only)
- Exceeding structural item caps in gather output (see gather refs)
Related Skills
kenoxa/use-worktree
tools
VerifiedTrustedCommunity
Use when: 'create a worktree', 'git worktree', 'parallel branch'.
2SKILL.mdUpdated May 22, 2026
kenoxa/use-session
tools
VerifiedTrustedCommunity
Use when: 'session state', 'resume work', 'worktree session'.
2SKILL.mdUpdated May 22, 2026
kenoxa/use-goal-prompt
development
VerifiedTrustedCommunity
Use when: 'goal prompt'.
2SKILL.mdUpdated May 22, 2026
kenoxa/run-council
testing
VerifiedTrustedCommunity
Thinking-lens stress-test on a recommendation.
2SKILL.mdUpdated May 5, 2026