executive-report — Claude Code skill: CCAM stakeholder reports
Turns CCAM sessions, analytics, cost and alerts into one stakeholder report. Handy before a release or a leadership update.
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-report -a claude-codeWhat executive-report does
The skill reads five CCAM endpoints: GET /api/stats, GET /api/analytics, GET /api/pricing/cost, GET /api/alerts?limit=100 and GET /api/workflows?status=all. It first pins down the time window, provider and data source, then pulls the numbers into a single Markdown report.
What lands in it: scope and data freshness, session, agent, event, token and cost counts, completion, error and alert outcomes, workflow complexity and subagent effectiveness. Then three highlights backed by evidence and three follow-ups in priority order. Markdown tables, values quoted straight from the API.
Nothing on the dashboard gets written — the skill only reads. Where a slice has no entries, it separates a real zero from a gap, which matters once the report goes upstairs.
What it helps with
- pull a release summary out of CCAM data
- show leadership token and cost figures for a period
- work through alerts and session errors
- judge how subagents performed
- export a Markdown report with tables
Example prompts for the agent
- Build a leadership report from CCAM sessions for the past week
- Put together an operational review: cost, alerts, errors
- Draft a Markdown report on workflows and subagents with three highlights
How to install executive-report
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-report -a claude-code2Manually: put the files in place
~/.claude/skills/executive-report/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/executive-report/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-report -a codex2Manually: put the files in place
.agents/skills/executive-report/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-report -a cursor2Manually: put the files in place
.cursor/skills/executive-report/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor executive-report2Manually: put the files in place
.github/skills/executive-report/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-report -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-reports/skills/executive-reportManually: put the files in place
.devin/skills/executive-report/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-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 executive-report
How do I install executive-report in Claude Code?
Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill executive-report -a claude-code. The skill lands in ~/.claude/skills/executive-report/SKILL.md.
What does executive-report do?
It reads CCAM stats, analytics, cost, alerts and workflows, then writes them up as a stakeholder report: the numbers, three highlights, three follow-ups.
Does the skill change anything in the dashboard?
No. It is read-only and leaves dashboard state alone.
Source text
SKILL.md · MIT
--- name: executive-report description: > Generate a concise stakeholder report from CCAM sessions, analytics, cost, alerts, and workflow intelligence. Use for release summaries, leadership updates, operational reviews, or a scoped Markdown report with evidence. --- # Executive Report 1. Confirm the time window, provider scope, and source scope. 2. Read: - `GET /api/stats` - `GET /api/analytics` - `GET /api/pricing/cost` - `GET /api/alerts?limit=100` - `GET /api/workflows?status=all` 3. Report: - Scope and data freshness - Sessions, agents, events, tokens, and cost - Completion, error, and alert outcomes - Workflow complexity and subagent effectiveness - Three evidence-backed highlights - Three prioritized follow-ups 4. Use Markdown tables and cite exact API values. Distinguish zero from missing or unavailable data. 5. Do not mutate dashboard state.
© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor