Menu
Generate a comprehensive project intelligence report — the thing managers actually read.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | executive-report |
| description | Generate a comprehensive project intelligence report — the thing managers actually read. |
| compatibility | opencode |
| metadata | {"audience":"delivery-leads","purpose":"reporting"} |
Generate a comprehensive project health report that aggregates pulse, velocity, drift, coverage, and suggestions into a single document. This is the "CTO dashboard" in document form — a report that gives leadership visibility without them needing to learn CLI commands.
Run these commands and aggregate the output:
hero sprint status --week — sprint health (done, in-flight, at-risk, drift)hero sprint velocity --since 30d — delivery velocity by agent/engineerhero drift --in-flight — current spec-vs-code divergencehero suggest --top 5 — high-churn areas without specshero search --list --status planning — backlog sizehero search --list --status delivering — WIP counthero spec contract check — regression status across delivered specsWrite the report to .hero/reports/report-<date>.md:
# Project Intelligence Report — <date>
## Health summary
- N specs completed this sprint, N in-flight, N at risk
- Delivery velocity: N specs/week (trend: up/down/flat)
- Drift: N specs with warnings, N boundary violations
- Contract coverage: N/M criteria verified, N regressions
## What shipped
<from pulse — done specs with titles>
## What's at risk
<from pulse — at-risk specs with staleness>
<from drift — specs with warnings>
## Where attention is needed
<from suggestions — high-churn uncovered areas>
<from contract check — any regressions>
## Backlog
N specs in planning, N in review
Top priorities: <list top 3 by priority>
## Velocity trend
<from velocity — per-agent metrics>
Behavioral rules that make AI coding agents more reliable — verification, self-correction, and scope discipline.
Debugging guidance and structured report template for thorough bug investigation, evidence gathering, and root cause documentation.
Cold-audit a completed delivery — verify the spec was actually delivered, challenge performative claims, and produce a what-landed report.
Guidelines for generating self-contained HTML mockups that look professional and are easy to iterate on.
Shared implementation guidance for making minimal, correct, maintainable code changes that fit existing systems.
The doctrine for `/roadmap-review` — interactive triage of roadmap-shape drift, walked one item at a time, with paste-ready resolution phrasing for the active sizing lens.