Documents business processes using BPMN-style mapping, cycle-time analysis, and deterministic bottleneck detection.
- GitHub stars
- 29,625
- Files
- 8
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the process-mapper skill do?
process-mapper documents business processes using BPMN-style mapping, cycle-time analysis, and deterministic bottleneck detection.
Summary generated from the skill's SKILL.md.
About the process-mapper skill
Operations leaders use this skill to document end-to-end business workflows and identify hidden delays in processes like procurement, onboarding, or claims adjudication. It transforms tribal knowledge into structured documentation by converting process data into ASCII swim-lane diagrams and normalized JSON artifacts. The system moves beyond simple mapping by applying deterministic logic rather than intuition to find where work actually stalls.
An agent should load this skill when a team needs to visualize cross-functional handoffs or investigate why a process is moving too slowly. The workflow relies on three specific scripts: process_documenter.py for mapping, cycle_time_analyzer.py for calculating value-add ratios and throughput, and bottleneck_detector.py for identifying constraints. By analyzing P50 and P90 durations, the tools distinguish between actual work and invisible waiting time. This allows users to focus interventions on the true constraint instead of wasting resources on non-bottleneck stages.
What an agent can do with it
- 1Visualize cross-functional handoffsCreate a text-based swim-lane diagram to see how work moves between different owners.
- 2Identify process wasteDetermine if a business process is healthy or waste-heavy based on its value-add ratio.
- 3Detect operational bottlenecksFind the specific stage causing delays using deterministic rules and industry profiles.
- 4Analyze cycle time metricsCalculate total P50 and P90 durations alongside Little's Law throughput estimates.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the process-mapper skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the process-mapper skill in Plugin
/plugin marketplace add alirezarezvani/claude-skills /plugin install business-operations-skills@claude-code-skills
Install the process-mapper skill in Claude Code
~/.claude/skills/process-mapper/SKILL.md
$ npx degit alirezarezvani/claude-skills/business-operations/skills/process-mapper ~/.claude/skills/process-mapperInstall the process-mapper skill in Claude Code (project)
.claude/skills/process-mapper/SKILL.md
$ npx degit alirezarezvani/claude-skills/business-operations/skills/process-mapper .claude/skills/process-mapperInstall the process-mapper skill in Codex
~/.agents/skills/process-mapper/SKILL.md
$ npx degit alirezarezvani/claude-skills/business-operations/skills/process-mapper ~/.agents/skills/process-mapperInstall the process-mapper skill in Gemini CLI
~/.gemini/skills/process-mapper/SKILL.md
$ npx degit alirezarezvani/claude-skills/business-operations/skills/process-mapper ~/.gemini/skills/process-mapperInstall the process-mapper skill in Claude.ai
npx degit alirezarezvani/claude-skills/business-operations/skills/process-mapper process-mapper && zip -r process-mapper.zip process-mapper # claude.ai → Customize → Skills → + → Create skill → Upload a skill → process-mapper.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablealirezarezvani/claude-skills/business-operations/skills/process-mapper is public and reachablegithub.com/alirezarezvani/claude-skills/tree/HEAD/business-o ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/alirezarezvani/claude-skills/commits ↗Pass
- No download-and-run or credential theft in scripts3 scripts read; no download-and-run, remote eval, base64 execution or credential uploadPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/alirezarezvani/claude-skills/blob/HEAD/business-o ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/alirezarezvani/claude-skills/blob/HEAD/business-o ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 111 linesgithub.com/alirezarezvani/claude-skills/blob/HEAD/business-o ↗Pass
SKILL.md
View on GitHubprocess-mapper
BPMN-style business process documentation, bottleneck detection, and cycle-time analysis for internal-operations leaders.
Purpose
Internal-operations work suffers from three recurring failure modes:
- Implicit process — the steps exist only in tribal knowledge, so handoffs drop and onboarding takes weeks.
- Invisible waiting — most of the elapsed time on any business process is queue / wait / approval time, not actual work; teams optimize the wrong stage.
- Local optimization — Goldratt's Theory of Constraints is ignored; resources are added to non-constraint stages, gaining nothing.
This skill produces a documented process map, identifies where work waits, and points the constraint out by name with deterministic logic — not LLM intuition.
When to use
- Documenting a new business process (procurement intake, vendor onboarding, employee onboarding, incident handoff, expense reimbursement, customer onboarding, claims adjudication).
- An existing process is "too slow" but nobody can name the bottleneck.
- Cycle time is being measured but value-add ratio is not — so the team can't tell whether the process is healthy or waste-heavy.
- Cross-functional handoffs are dropping work and root cause is unclear.
Workflow
Five-step deterministic flow:
- Intake. Capture the process as a JSON file with one entry per stage:
name,owner,type(value-add|wait|rework),duration_minutes_p50,duration_minutes_p90. Useassets/process_template.mdand its JSON skeleton. - Map stages. Run
process_documenter.pyto produce an ASCII swim-lane diagram + a normalized JSON artifact. The swim-lane separates lanes by owner so cross-functional handoffs become visible. - Measure cycle time. Run
cycle_time_analyzer.pyto compute total P50, total P90, value-add ratio (VA%), and a Little's-Law throughput estimate. Verdict: VA% > 25% = HEALTHY, 10–25% = TYPICAL, < 10% = WASTE-HEAVY. - Detect bottlenecks. Run
bottleneck_detector.pywith the appropriate--profile(saas / services / manufacturing / healthcare). Output is a ranked list with severity (CRITICAL / HIGH / MEDIUM), root-cause hypothesis, and one recommended action per finding. - Recommend. Pair the bottleneck list with the cycle-time verdict; recommend a single constraint-focused intervention per Goldratt's "subordinate everything to the constraint" rule. Don't recommend optimization of a non-constraint stage.
Scripts
scripts/process_documenter.py — Reads a process JSON, validates it, and emits a text-based BPMN-style swim-lane diagram in Markdown (lanes by owner, stages annotated with type + duration). Also outputs a normalized JSON artifact for downstream tools. Stdlib only. --sample prints a 6-stage procurement-intake example.
scripts/bottleneck_detector.py — Applies three deterministic detection rules: (a) stage P50 > 2× mean of value-add stages, (b) wait-state % > 40% of total cycle, (c) rework % > 15%. Thresholds adjust by --profile because SaaS, services, manufacturing, and healthcare have different "normal" wait ratios. Output is a ranked list with severity, hypothesis, action.
scripts/cycle_time_analyzer.py — Computes total P50 and P90 cycle time, value-add ratio (VA%), wait %, rework %, and a Little's-Law throughput estimate (WIP / cycle time). Per Lean canon: VA% > 25% = HEALTHY, 10–25% = TYPICAL (most non-manufacturing processes land here), < 10% = WASTE-HEAVY.
Quick example
# Renders a BPMN-style swim-lane diagram + normalized JSON for the built-in 6-stage procurement-intake example
cd business-operations/skills/process-mapper && python3 scripts/process_documenter.py --sample
References
references/lean_six_sigma_canon.md— TIMWOOD wastes, value-stream mapping, Theory of Constraints, Kanban WIP, Little's Law. Cites Womack & Jones, Rother & Shook, Goldratt, Ohno, Liker, Pyzdek, Anderson.references/bpmn_essentials.md— Pools, lanes, gateways, events, message flows, common notation mistakes. Cites the OMG BPMN 2.0 spec, Silver, Allweyer, Freund/Rücker, OASIS, ISO/IEC 19510:2013.references/bottleneck_anti_patterns.md— Seven specific anti-patterns drawn from Goldratt, Kim et al., Spear, DORA, Deming, and process-mining research.
Assumptions
- The user can provide stage-level cycle-time data (even rough P50 / P90 estimates). If they cannot, the first step is to instrument the process — not to map it.
- "Process" here means a repeatable business workflow with discrete stages, not a one-off project.
- The user has authority to act on bottlenecks (or can route findings to someone who does). Without that, the output is academic.
- Stage
typeis honest: a "value-add" stage labeled as such by the user really does change the work product from the customer's perspective. Mis-labelling waiting as value-add is the most common data-quality failure.
Anti-patterns
- Mapping every process at once. Pick one. Goldratt: the constraint is a single point.
- Optimizing the non-constraint. If stage 4 is the bottleneck, speeding up stage 2 just builds inventory in front of stage 4. Subordinate everything to the constraint.
- Mistaking total cycle time for processing time. They are almost never the same; VA% reveals the gap.
- Adding people to a wait-bound process. Wait time is not solved by more headcount; it's solved by removing the handoff or batch.
- Treating rework as a separate problem. Rework loops belong in the process map. Hiding them understates true cycle time.
Distinct from
- business-growth skills — external sales motion, lead-funnel conversion, customer-success retention. Process-mapper is internal operations.
- engineering/slo-architect — system-reliability SLOs / error budgets / burn-rate alerts. Process-mapper is business-process cycle time, not system uptime.
- c-level-advisor (COO / CEO) — strategic prioritization of which processes to fix. Process-mapper is the tactical instrument used after that prioritization decision.
- project-management skills — Jira / Confluence ticket workflow tooling. Process-mapper is process design, not ticket tracking.
Forcing-question library (Matt Pocock grill discipline)
Before invoking the tools, the orchestrator (or /cs-grill-bizops) walks the user through these questions one at a time, with a recommended answer + canon citation. Never bundled.
-
"Do you have measured cycle times for the top-3 longest stages, or only estimates?" Recommended: insist on measured data. Canon: Goldratt 1984 (The Goal) — optimizing estimated bottlenecks reliably attacks the wrong constraint.
-
"Are you mapping the current process (as-is) or the intended process (to-be)?" Recommended: map as-is first. To-be after bottleneck is identified. Canon: Rother & Shook 1999 (Learning to See) — value-stream mapping starts with the current state, always.
-
"Where do handoffs occur between teams, and how long does each handoff wait?" Recommended: log every handoff with median wait time. Canon: Reinertsen 2009 (Principles of Product Development Flow) — wait time at handoffs is the largest invisible cost.
-
"What's your batch size at each stage?" Recommended: drive batch size toward 1 wherever possible. Canon: Anderson 2010 (Kanban) — batch size correlates 1:1 with cycle time variance.
-
"What's the rework rate per stage?" Recommended: surface it explicitly; rework loops belong in the map. Canon: Pyzdek (Six Sigma Handbook) — hidden rework drives 30-50% of total cycle time in service processes.
Walk depth-first. Don't open question 4 before 1-3 are answered. After all 5 are locked, invoke process_documenter.py → bottleneck_detector.py → cycle_time_analyzer.py in sequence.
Files in this skill
8process-mapper skill questions
How do I install the process-mapper skill in Claude Code?
Run npx degit alirezarezvani/claude-skills/business-operations/skills/process-mapper ~/.claude/skills/process-mapper. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the process-mapper skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What metrics does the tool use to evaluate process health?
The tool calculates total P50 and P90 cycle time, value-add ratio (VA%), wait percentage, rework percentage, and a Little's-Law throughput estimate.
How is a process categorized based on its value-add ratio?
A VA% greater than 25% is considered healthy, 10–25% is typical, and less than 10% is considered waste-heavy.
What are the deterministic rules for detecting bottlenecks?
Bottlenecks are detected if a stage's P50 is more than twice the mean of value-add stages, if wait-states exceed 40% of the total cycle, or if rework exceeds 15%.