flow-metrics-interpreter
Read your team's flow metrics — cycle time, throughput, WIP, aging work — and say what they actually mean and what to try, not just restate the numbers. Use when asked to interpret cycle time, what do our flow/Actionable-Agile metrics mean, why is delivery slow, or read our Kanban metrics. Produces the health read per metric, the likely bottleneck the numbers point to, 2–3 concrete process experiments to run next, and the trap-to-avoid so the team doesn't game the metric instead of fixing the flow.
npx skills add mohitagw15856/pm-claude-skills --skill flow-metrics-interpreter --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Flow Metrics Interpreter A dashboard of cycle time and throughput is useless until someone says what it *means* — is the flow healthy, where's it clogging, and what should the team try Monday. This reads the metrics together (they only make sense in relation), points at the likely bottleneck, and proposes specific experiments — while flagging the classic trap of optimising the number instead of the flow it's meant to measure. ## What This Skill Produces - **The health read** — per metric (cycle time, throughput, WIP, aging), what "good" looks like and where you are - **The bottleneck the numbers point to** — read together, where work is actually stalling - **2–3 process experiments** — concrete, small, reversible things to try next (with what to watch) - **The gaming trap** — how this metric gets optimised dishonestly, so you don't ## Required Inputs Ask for these if not provided: - **The metrics** — cycle time (distribution, not just average), throughput per period, current WIP, and any aging/stuck items - **The baseline** — a few periods of history if you have it (a single number can't show a trend) - **Team context** — team size, work type, and any recent changes (reorg, new p
- What This Skill Produces
- Required Inputs
- Framework: Read the Flow, Not the Number
- Output Format
- Flow read — [team] · [period]
- Experiments to try (pick 1–2)
- Quality Checks
- Anti-Patterns
- Example Trigger Phrases
What does the flow-metrics-interpreter skill do?
Read your team's flow metrics — cycle time, throughput, WIP, aging work — and say what they actually mean and what to try, not just restate the numbers. Use when asked to interpret cycle time, what do our flow/Actionable-Agile metrics mean, why is delivery slow, or read our Kanban metrics. Produces the health read per metric, the likely bottleneck the numbers point to, 2–3 concrete process experiments to run next, and the trap-to-avoid so the team doesn't game the metric instead of fixing the flow.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill flow-metrics-interpreter --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.