القائمة
Use when a status report, research digest, or experiment comparison is needed for human review
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when a file or module is too large, responsibilities are tangled, or a cross-cutting redesign is needed
Use when literature notes exist and need citation verification, or before publishing any artifact that cites literature
Use at the end of a work session to embed learnings into conventions. Simplified for models with lower reasoning capacity.
Use at the end of a work session, or when accumulated findings need to be embedded into conventions, skills, or patterns
Use when the Slack bot needs to handle an operational action like launching an experiment, querying status, or processing approvals
Use when a plan, finding, or design needs adversarial review before committing to it
| name | report |
| description | Use when a status report, research digest, or experiment comparison is needed for human review |
| complexity | medium |
| model-minimum | glm-5 |
| allowed-tools | ["Read","Grep","Glob","Write","Bash(cd infra/scheduler && npx tsx src/report/run-report.ts *)","Bash(git diff *)","Bash(git log *)","Bash(git status)","Bash(git add *)","Bash(git commit *)"] |
| argument-hint | <type> [project=<name>] [from=YYYY-MM-DD] [to=YYYY-MM-DD] |
Generate a formatted report with charts from akari's data sources.
| Type | Argument | What it shows |
|---|---|---|
| Operational | operational | Session health, cost trend, budget burn rates, verification compliance |
| Research digest | research | Experiments completed, findings, decision records, knowledge output |
| Project status | project [project=<name>] | Per-project health, tasks, budget, experiments, log entries |
| Experiment comparison | experiment-comparison [ids=<id1,id2>] | Side-by-side experiment results and parameter diffs |
Extract from the user's message:
operational, research, project, experiment-comparison (default: operational)project and experiment-comparison types)experiment-comparison)Run the report generator:
cd infra/scheduler && npx tsx src/report/run-report.ts --type <type> [--project <name>] [--from YYYY-MM-DD] [--to YYYY-MM-DD] [--ids id1,id2]
This generates:
reports/<type>-<date>.mdreports/charts/*.pngreports/charts/.If the user wants to preserve the report:
git add reports/git commit -m "report: <type> <date>"/report operational — generates operational dashboard for the last 7 days/report research from=2026-02-10 — research digest since Feb 10/report project project=sample-project — sample-project status/report experiment-comparison ids=strategic-100,model-comparison-focused-v2 — compare two experiments