project-flow-ops
Operate execution flow — triage tasks, manage priorities, keep progress structured. Use when the user needs backlog control, task planning, or workflow coordination across projects.
git clone --depth 1 https://github.com/Mark393295827/third-brain-v5-skills /tmp/project-flow-ops && cp -r /tmp/project-flow-ops/skills/project-flow-ops ~/.claude/skills/project-flow-opsSKILL.md
# Project Flow Operations Keep execution structured and progress visible — triage, plan, track, and review across projects. ## Usage Template **Prompt** ```text Use project-flow-ops to triage this backlog. Rank priorities, identify blockers, and produce the next execution plan. ``` **Use Case** - Turning scattered tasks or competing projects into a clear action queue. **Expected Result** - The agent returns prioritized work, blockers, next actions, and review cadence. **Output Example** - A ranked backlog with status, owner, next action, blocker, priority reason, and review date. **Verification Case** - Every top-priority item has an owner, next action, status, and reason for priority. **Verified Effect** - A messy backlog becomes a ranked execution queue with visible blockers and review cadence. ## Success Metrics - Top-priority items each have owner, status, blocker, next action, and review date. - Backlog is ranked with a reason for priority instead of only grouped by theme. - Output identifies one immediate next action and one item to defer or drop. ## When to Use - User says "what should I work on next?" - Starting a new task or project - Reviewing progress or blocked items - User feels overwhelmed or unclear on priorities ## Workflow ### P1: Triage — What's Active? Scan current state: ``` ACTIVE: What's in progress now? (limit: 1-2) BACKLOG: What's waiting? (ordered by priority) BLOCKED: What's stuck and why? COMPLETED: What's done since last review? ``` For each blocked item: identify the **one thing** that unblocks it. ### P2: Plan — What's Next? Select the next task from the backlog with clear scope: ``` Task: [one-line description] Why now: [urgency or opportunity] Definition of done: [what "done" looks like] Timebox: [max time to spend] ``` Rule: **One task at a time.** Context switching is the productivity killer. ### P3: Execute — Focus & Track During execution: - Break the task into ≤15 minute steps - Verify after each step (verify-before-claim) - Check in after timebox expires — extend or pivot ### P4: Review — Close & Learn After completion: - What did we learn? - What should be documented? → wiki or SOP - What's next? ## Priority Framework | Priority | Criteria | Action | |----------|----------|--------| | 🔴 Critical | Blocks others, deadline imminent | Do now | | 🟡 Important | Moves key metric, this week | Schedule today | | 🟢 Normal | Valuable, no deadline | Backlog | | ⚪ Low | Nice-to-have | Someday/maybe | ## Anti-patterns - **Doing everything** — multitasking reduces throughput for everyone - **Perfectionism** — done beats perfect for early-stage work - **No timebox** — unbounded tasks expand to fill all available time ## Quality Gates - [ ] Active items limited to 1-2 - [ ] Blocked items have an unblock action identified - [ ] Next task has definition of done and timebox - [ ] Completed items reviewed for documentation needs - [ ] Priority labels applied
Execute a daily knowledge compound closed loop — 7 Key Results from input to feedback with scoring. Use when the user wants to do a daily review, plan their day, or run a knowledge workflow.
Extract reusable knowledge from a work session and save concepts, entities, corrections, patterns, ideas, decisions, and gaps to the wiki. Use when ending a session or when the user says to extract knowledge.
Estimate and track token usage and cost across the knowledge pipeline. Run before expensive tasks to budget, after tasks to log actuals.
Health-check the knowledge wiki — find orphans, broken links, missing frontmatter, contradictions, stale content, and statistical drift. Use when the user says "lint the wiki", "health check", or periodically for maintenance.
Command multi-agent work with bounded roles, ownership, integration gates, and verification loops. Use when the user needs Claude Code Agent Teams, parallel agents, delegation strategy, or multi-agent orchestration.
Design or refactor agent skills, workflows, and operating loops for model-native Agentic Engineering. Use when making skills more autonomous, concise, verifiable, long-horizon capable, token-efficient, and lower-friction for human-LLM collaboration.
Design an AI Six Sigma Black Belt operating model for property service, maintenance dispatch, environmental testing, quote generation, CRM follow-up, and workflow quality dashboards. Use when the user needs a Property Agent OS, AI + Ontology + DMAIC management system, CTQ metrics, agent-team roles, work-order states, or MVP roadmap for operations quality.
Improve a personal or team operating system with self-evolving loops, CASH allocation, 3B creativity, predictive coding, and diagnostics. Use when the user wants to redesign a work method, learning loop, or cognitive operating system.