a-green-hand-jack/project-ops-router
skills/project-ops-router/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add a-green-hand-jack/ml-research-skills project-ops-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 26, 2026, 4:24 AM44.4s3 files scanned
SKILL.md
- name:
- project-ops-router
- description:
- 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.
- allowed-tools:
- Read, Bash
Project Ops Router
You are a router. Do not perform the operation 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 phase and active worktrees.
Classification Buckets
| Bucket | Key signals | Route to |
|---|---|---|
| git-ops | commit, push, merge, rebase, stash, conflict, lock file, worktree state, Git failure | safe-git-ops |
| new-branch/worktree | create branch, new worktree, experiment branch, paper venue branch, arXiv branch | new-workspace |
| project-memory | claim board, evidence, risk, action, handoff, phase dashboard, memory bootstrap, closeout | research-project-memory |
| skills-bootstrap | enable ml-research-skills in a project, decide local vs global install, avoid full bundle in non-ML repo | ml-research-bootstrap |
| project-init | initialize project, create paper/code/slides repos, GitHub Project, root AGENTS.md | project-init |
| remote-server | SSH, server state, sync safety, SLURM/RunAI coordination, remote logs, artifacts, HPC | remote-project-control |
| code-review | review implementation, fresh-context audit, writer/reviewer separation, review bundle | code-reviewer |
| sidecar | one-shot Codex task, bounded scan, precommit classifier, draft proposal, ephemeral run | sidecar-task-runner |
| sync-paper | promote experiment results to paper memory, sync evidence, project-sync | project-sync |
| timeline | retrospective, progress summary, git history timeline, mentor report, phase planning | work-timeline-planner |
| token-audit | token usage, Codex burn, cache reuse, session cost, attention telemetry | token-usage-auditor |
| skill-audit | skill inventory, routing quality, stale references, validation readiness, skill system | skill-system-auditor |
| personalization | user preferences, repeated corrections, private memory, reusable rules from trajectory | personalization-memory |
| memory-publish | audit private memory/skills before publishing, redaction, privacy risk | memory-publication-auditor |
Routing Steps
- Identify the single most blocking bucket.
- If uncertain between
safe-git-opsandremote-project-control, readreferences/contrastive-routing.md. - Select exactly one child skill.
- Hand off — state which skill and why.
Hard Constraints
- Do not run git commands yourself before handing off to
safe-git-ops. - Do not connect to servers yourself before handing off to
remote-project-control. - Do not write to memory boards yourself; route to
research-project-memory. - If a task spans ops and experiment/paper domains, ops work (commit/push/sync) goes to this router first; scientific work goes to the appropriate domain router after.
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/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
a-green-hand-jack/experiment-evidence-router
development
VerifiedTrustedCommunity
Route ML experiment planning, execution, debugging, result interpretation, and evidence packaging tasks to the correct skill. Use this when the task involves experiments, compute, results, or evidence — instead of guessing between run-experiment, run-status-monitor, experiment-debugger, result-diagnosis, research-results-auditor, statistical-analysis-planner, or paper packaging skills. Do not solve the task directly.
4SKILL.mdUpdated May 19, 2026