workflow-report — Claude Code skill: what it does, how to install
Creates workflow intelligence reports from CCAM orchestration and delegation data. Surfaces tool bottlenecks, concurrency, and context compaction.
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a claude-codeWhat workflow-report does
The skill inspects agent activity monitored by Claude-Code-Agent-Monitor. It first verifies the scope. The user decides whether to analyze all sessions or a single sessionId. The skill then requests metrics through GET /api/workflows or GET /api/workflows/{sessionId}.
From these payloads, it summarizes orchestration depth, delegation flows, and tool transitions. Output includes an architecture narrative alongside a metrics table and prioritized opportunities. Serialization bottlenecks and error-amplifying branches are flagged only when values directly support them. Causality cannot be inferred from correlation alone.
Working CCAM endpoints are required. Without live responses from the service, the skill cannot map bottlenecks.
What it helps with
- audit subagent orchestration depth and delegation patterns
- locate serialization bottlenecks across tool transitions
- build workflow metrics tables and prioritized improvements
- trace error propagation and context compaction across sessions
Example prompts for the agent
- Generate a workflow-report for all CCAM sessions
- Create an architecture report for session abc-123 with tool transitions
- Review model delegation and serialization bottlenecks in the latest run
How to install workflow-report
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a claude-code2Manually: put the files in place
~/.claude/skills/workflow-report/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/workflow-report/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a codex2Manually: put the files in place
.agents/skills/workflow-report/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a cursor2Manually: put the files in place
.cursor/skills/workflow-report/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor workflow-report2Manually: put the files in place
.github/skills/workflow-report/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-reports/skills/workflow-reportManually: put the files in place
.devin/skills/workflow-report/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about workflow-report
How to install workflow-report in Claude Code?
Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill workflow-report -a claude-code. You can also place the file manually at ~/.claude/skills/workflow-report/SKILL.md.
What does the workflow-report skill do?
It queries CCAM monitoring endpoints to assemble an evaluation of subagent orchestration, tool transitions, and error propagation. The output supplies an architecture overview, a metrics table, and prioritized adjustments.
What endpoints does workflow-report query?
It reads GET /api/workflows for global fleet data and GET /api/workflows/{sessionId} for single-session reviews. Active CCAM services must be reachable to supply these payloads.
Source text
SKILL.md · MIT
---
name: workflow-report
description: >
Create a workflow-intelligence report from CCAM orchestration, delegation,
tool flow, concurrency, complexity, compaction, and fleet-run data. Use for
architecture reviews, agent-fleet analysis, or workflow optimization reports.
---
# Workflow Report
1. Confirm whether the report covers all sessions or one session.
2. Read `GET /api/workflows` and, when scoped, `GET /api/workflows/{sessionId}`.
3. Summarize orchestration depth, subagent types, delegation patterns, tool
transitions, concurrency, model delegation, error propagation, and
compaction.
4. Identify serialization bottlenecks, repeated patterns, and error-amplifying
branches only when supported by returned values.
5. Provide a short architecture narrative, a metrics table, and prioritized
optimization opportunities.
6. Do not claim causality from correlation alone.
© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor
