a-green-hand-jack/discovery-router
skills/discovery-router/SKILL.md
Route research discovery tasks — idea validation, literature review, reference reading, corpus comparison, or project synthesis — to the correct skill. Use when the task involves exploring ideas, surveying literature, reading papers, comparing multiple papers, or connecting references to the project. Do not perform the review or synthesis directly.
$ install --global
skillsauthnpx skillsauth add a-green-hand-jack/ml-research-skills discovery-routerInstall 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 19, 2026, 5:18 AM225.3s3 files scanned
SKILL.md
- name:
- discovery-router
- description:
- Route research discovery tasks — idea validation, literature review, reference reading, corpus comparison, or project synthesis — to the correct skill. Use when the task involves exploring ideas, surveying literature, reading papers, comparing multiple papers, or connecting references to the project. Do not perform the review or synthesis directly.
- allowed-tools:
- Read, Bash
Discovery Router
You are a router. Do not perform the literature review or synthesis directly.
Your job: classify the task → select one child skill → hand off.
Before Routing — Mandatory
- Detect scope:
git rev-parse --git-common-dirvs--show-toplevel. - If
memory/BRIEFING.mdexists, read it for current project phase (early discovery vs pre-submission novelty check vs rebuttal).
Classification Buckets
| Bucket | Key signals | Route to |
|---|---|---|
| idea-validate | pursue/park/kill decision, novelty check for a new idea, feasibility, FIVE+C framework | research-idea-validator |
| literature-survey | survey a topic, map related work, rank papers, find canonical + closest + recent work | literature-review-sprint |
| reference-inventory | what sources do we have, index reference/, track new papers, manage library | reference-library-manager |
| read-paper | read a specific paper or small set, extract method/benchmark/theory/risk into source card | reference-reading-summarizer |
| corpus-compare | compare 5+ papers side by side, closest-work ranking, gap identification, comparison matrix | reference-corpus-analyzer |
| project-synthesize | connect source cards to project claims/risks/baselines/experiments/writing contract | reference-project-synthesizer |
| citation-coverage | find missing citations before submission, coverage check, insertion points | citation-coverage-audit |
Routing Steps
- Identify the single most blocking bucket.
- If uncertain within the reference triple (
reference-reading-summarizer/reference-corpus-analyzer/reference-project-synthesizer), readreferences/contrastive-routing.md. - Select exactly one child skill.
- Hand off — state which skill and why.
Hard Constraints
- Do not read or summarize papers yourself; route to
reference-reading-summarizer. - Do not produce a comparison matrix yourself; route to
reference-corpus-analyzer. - Do not connect sources to project memory yourself; route to
reference-project-synthesizer. - If the user wants to validate a new idea (not survey existing work), prefer
research-idea-validatoroverliterature-review-sprint.
Related Skills
a-green-hand-jack/ml-research-bootstrap
testing
VerifiedTrustedCommunity
Bootstrap project-local ml-research-skills. Use from global installs when creating a new ML research project, enabling this collection in an existing ML research repo, or deciding whether to install the full bundle locally. Route to project-init for new projects; do not handle paper or experiment work directly.
4SKILL.mdUpdated May 26, 2026
a-green-hand-jack/project-ops-router
development
VerifiedTrustedCommunity
Route project operations tasks — git, memory, bootstrap, remote, workspace, code review, timeline, ops — to the correct skill. Use when the task involves commits, pushes, worktrees, project memory, enabling project-local skills, SSH/server coordination, sidecar runners, or audits. Do not solve the ops task directly.
4SKILL.mdUpdated May 19, 2026
a-green-hand-jack/paper-writing-router
testing
VerifiedTrustedCommunity
Route ML/AI paper writing tasks to the correct skill — contract planning, prose drafting, section writing, consistency editing, review simulation, rebuttal, submission, or citation work. Use when the task involves writing, revising, reviewing, or submitting a paper instead of guessing between paper-writing-assistant, paper-writing-contract-planner, paper-reviewer-simulator, auto-paper-improvement-loop, or citation skills. Do not draft prose directly.
4SKILL.mdUpdated May 19, 2026
a-green-hand-jack/ml-research-router
data-ai
VerifiedTrustedCommunity
Project-local router for ML research skill selection. Use inside an initialized ML research project, or while maintaining this skill repo, when the user describes an ML research/paper/experiment/discovery/ops/release workflow and may not know the skill; route to a domain router or high-signal leaf. Do not use for generic non-ML projects.
4SKILL.mdUpdated May 19, 2026