Ops Projects Skill for Claude
Portfolio dashboard for all GSD-tracked projects. Scans ~/Projects and ~/gsd-workspaces for .planning/ directories, shows phase status, git state, blockers, and next actions for every project. Run /ops projects to see the full portfolio.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/davepoon/buildwithclaude --skill ops-projectsWhat it tells the agent to use
found in the instruction textThe instruction itself
11 sections, as written by the authorRuntime Context
Before rendering, load:
- Preferences:
cat ${OPS_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json— readowner,timezone - Daemon health:
cat ${OPS_DATA_DIR}/daemon-health.json— show service status in dashboard footer - GSD registry:
cat ${OPS_DATA_DIR}/registry.json— primary project index (updated by daemon twice daily + on-demand with --sync)
OPS ► PROJECTS — GSD Portfolio Dashboard
Quick commands
# Refresh registry data on demand
bash ${CLAUDE_PLUGIN_ROOT}/scripts/ops-gsd-registry-sync.sh
# Show registry contents
cat ${OPS_DATA_DIR}/registry.json
# Show health summary
cat ${OPS_DATA_DIR}/cache/projects_health.json
Data flow
~/Projects/ ~/gsd-workspaces/
│ │
▼ ▼
[project]/.planning/ [project]/.planning/
│ │
├── HANDOFF.json ├── HANDOFF.json ← active-phase projects
├── STATE.md ├── MILESTONES.md
├── ROADMAP.md └── STATE.md
└── MILESTONES.md
│
▼ ops-gsd-registry-sync.sh (daemon: 6am + 6pm)
│
▼
${OPS_DATA_DIR}/
├── registry.json ← all projects, sorted by priority
└── cache/
└── projects_health.json ← health summary
│
▼ ops-projects skill reads this
Dashboard output
Build the dashboard from ${OPS_DATA_DIR}/cache/projects_health.json (fall back to ${OPS_DATA_DIR}/registry.json if missing). Show:
╔══════════════════════════════════════════════════════════════╗
║ OPS ► PROJECTS [owner] [date] [daemon status] ║
╠══════════════════════════════════════════════════════════════╣
║ GSD Portfolio — 23 projects ║
║ ║
║ 🟢 EXECUTING (3) ║
║ my-webapp Phase 12 [executing] branch: main 0 dirty ║
║ my-plugin Phase 16 [executing] branch: main 2 dirty ║
║ my-saas-app Phase 39 [executing] branch: dev 0 dirty ║
║ ║
║ 🟡 PAUSED (4) ║
║ my-project-a Phase 08 [paused] branch: feat 1 dirty ║
║ my-project-b Phase 3 [verifying] branch: main 0 dirty ║
║ ... ║
║ ║
║ 🔴 BLOCKED (1) ║
║ my-ecommerce Phase 7 [await-UAT] branch: prod 0 dirty ║
║ ║
║ ⚪ IDLE / UNTRACKED (15) ║
║ my-side-project Phase 1 [complete] branch: main 0 dirty ║
║ my-other-app — — branch: dev 3 dirty ║
║ ... ║
╠══════════════════════════════════════════════════════════════╣
║ ⚡ Services: message-listener ● | inbox-digest ⏱ 2h | gsd-registry ⏱ 12h ║
╚══════════════════════════════════════════════════════════════╝
Status indicators (from status field, case-insensitive)
- executing → 🟢
- paused / verifying / phase_complete → 🟡
- human / uat / blocked / pending → 🔴
- empty status + has phase → ⚪ (idle)
- no phase, no status → ⚪ (untracked/no GSD)
Columns per project: ALIAS | PHASE | STATUS | BRANCH | DIRTY | NEXT ACTION
Project deep-dive
If $ARGUMENTS contains a project alias, find it in the registry and show:
╔══════════════════════════════════════════════════════════════╗
║ PROJECT — [alias] ║
╠══════════════════════════════════════════════════════════════╣
║ Path: ~/Projects/[alias]/ ║
║ Phase: [phase] Status: [status] ║
║ Milestone: [milestone name] ║
║ Branch: [branch] Dirty: [N] Unpushed: [N] ║
║ Blockers: [N] ║
║ Next: [next_action text] ║
║ ║
║ GSD files: ✓ ROADMAP ✓ MILESTONES [HAS_HANDOFF] STATE ║
╚══════════════════════════════════════════════════════════════╝
Actions:
[1] Open project directory
[2] Continue GSD (/gsd-next [alias])
[3] Git: branch / status / log
[4] Run /ops projects (back to portfolio)
Present numbered actions and let the user pick by typing the number or action name.
--sync flag
If --sync or --refresh is passed, run the registry sync script first, then display the updated dashboard:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/ops-gsd-registry-sync.sh 2>&1
Show "Refreshing..." while running, then present the full updated dashboard.
Error states
- If
registry.jsonis missing/empty: show a one-shot sync prompt
No project registry found. Run /ops projects --sync to build it.
- If daemon health shows
action_needed: surface that in a warning banner
CLI reference (for manual use)
| Command | What it does |
|---------|-------------|
| /ops projects | Show full portfolio |
| /ops projects [alias] | Deep-dive on one project |
| /ops projects --sync | Force-refresh registry + show dashboard |
| /ops:setup registry | Open registry setup (future) |
Other skills for the same job
different authors, same section of the catalogue
Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests organizational design and headcount planning for a startup.
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.
Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progress or updates, (3) Generate weekly/daily reports from Jira, (4) Publish status summaries to Confluence, or (5) Analyze project blockers and completion. Queries Jira issues, categorizes by status/priority, and creates formatted reports for delivery managers and executives.
Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.
Google Workflow: Today's meetings + open tasks as a standup summary.
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.
How to use it
Take davepoon/ops-projects from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.