feat(lead): Modus ich ersetzt meins im Lead-Radar

- Neuer Modus `ich` (Wochenselbstreview) über alle Projekte statt nur 🔒 Meins: Zusagen aus Sally, Termine, Abgeben, Fokus und Kennzahlen mit Verlauf
- `references/meins.md` entfällt, ersetzt durch `references/ich.md`; Trigger und Invocation in SKILL.md angepasst
- `tag`: neuer Block „Du heute“ mit eigenen fälligen und mehrfach verschobenen To-dos
- `execute.md`: To-do anlegen nur im Modus `ich`, nur für eigene Zusagen
- `lead-meeting-prep`: Meins-Items über `--projects` statt `--scope meins` laden
This commit is contained in:
m3ta-chiron committed 2026-11-05 13:24:38 +01:00
1 parent 27eefdc9cf
commit dd7db9e662
6 files changed
+129 -71

No files matched your search

+10 -9
View File
@@ -4,11 +4,12 @@ description: |
Sascha's leadership radar: read the IT cockpit through one lens, turn the situation into
numbered decision proposals, execute them in Basecamp/Zammad after one batch approval.
Modes: tag (morning Lagebild, Zammad + 👥 IT), freitag (prepare the Friday close),
meins (weekly review of Sascha's own 🔒 Meins to-dos), person <slug> (prepare a 1:1),
ich (weekly self-review: Sascha's own to-dos across all projects, commitments from Sally,
delegation candidates, metrics against the last runs), person <slug> (prepare a 1:1),
portfolio (monthly review of Sascha's projects). Also answers "wem delegiere ich X"
via person mode.
Triggers: "Lagebild", "Freitags-Abschluss vorbereiten", "Wochenreview", "1:1 vorbereiten",
"Portfolio-Review".
Triggers: "Lagebild", "Freitags-Abschluss vorbereiten", "Wochenreview", "meine Woche",
"Selbstreview", "1:1 vorbereiten", "Portfolio-Review".
compatibility: opencode, claude-code
---
@@ -16,7 +17,7 @@ compatibility: opencode, claude-code
Guiding question of every run: *What must Sascha decide now, and whom does he give it to?* One run = one mode → one Lagebild → one numbered proposal list → one batch approval → execution.
Invocation: `/lead-radar <tag|freitag|meins|person <slug>|portfolio>`. Without a mode, pick from the user's words via the trigger phrases above; still unclear → ask with the five modes as options.
Invocation: `/lead-radar <tag|freitag|ich|person <slug>|portfolio>`. Without a mode, pick from the user's words via the trigger phrases above; still unclear → ask with the five modes as options.
## Sources of truth
@@ -56,7 +57,7 @@ From `/home/sascha.koenig/p/PM`:
python3 tools/it-cockpit/cockpit.py --json --scope <mode> [--person <slug>]
```
A run takes 20–90 s. Save the JSON to the scratchpad and work from that file. Every output carries `drift` and `errors`; an entry under `errors` (e.g. Zammad without `ZAMMAD_TOKEN`) means that source is blind for this run: say so in one line at the top of the Lagebild and continue with the rest. Use live `basecamp` calls only for detail questions the cockpit does not answer (comments under an item, a card's history).
For `ich` add `--dry-run`: the state is written only at the very end of the run, after execution (see `references/ich.md`). A run takes 20–90 s. Save the JSON to the scratchpad and work from that file. Every output carries `drift` and `errors`; an entry under `errors` (e.g. Zammad without `ZAMMAD_TOKEN`) means that source is blind for this run: say so in one line at the top of the Lagebild and continue with the rest. Use live `basecamp` calls only for detail questions the cockpit does not answer (comments under an item, a card's history).
**Done when** the JSON is on disk and you know which sources are blind.
@@ -68,7 +69,7 @@ Open the mode's reference and follow it; it says which keys to read, how to judg
|---|---|---|
| `tag` | [references/tag.md](references/tag.md) | nothing |
| `freitag` | [references/freitag.md](references/freitag.md) | nothing |
| `meins` | [references/meins.md](references/meins.md) | doc in 🔒 Meins → `Wochenreviews` |
| `ich` | [references/ich.md](references/ich.md) | doc in 🔒 Meins → `Wochenreviews`; state row in `tools/it-cockpit/state/ich/` |
| `person <slug>` | [references/person.md](references/person.md) | nothing, by hard rule |
| `portfolio` | [references/portfolio.md](references/portfolio.md) | doc in 🔒 Meins → `02 Projekte & Initiativen` |
@@ -94,16 +95,16 @@ Follow [references/execute.md](references/execute.md): one command per change, t
### 5. Persist and report
For `meins` and `portfolio` write the document as the mode's reference describes, reflecting what was actually executed. Other modes write nothing.
For `ich` and `portfolio` write the document as the mode's reference describes, reflecting what was actually executed. Other modes write nothing.
Report in German: executed items with links, failed items with error, document URL (if any), open `Für dich:` points.
**Done when** the report is out and, for `meins`/`portfolio`, the document is readable in Basecamp.
**Done when** the report is out and, for `ich`/`portfolio`, the document is readable in Basecamp.
## Guardrails
- Every write waits for the batch approval; the approval covers exactly the numbered items shown.
- Proposals carry their reason; a bare "Termin verschieben" is incomplete.
- OKF holds goals, context, decisions and links; task state lives in Basecamp (spec §3.2). OKF fixes go through the same approval and end with the `validate` skill on the bundle.
- Process KPIs only: counts per list or per process, never per-person rankings.
- Process KPIs only: counts per list or per process, never per-person rankings. Scores, trends and persisted metrics exist only in mode `ich` and only about Sascha; the person lens stays score-free.
- Owner reminders belong to automation A3; the skill's output to colleagues is the comment on the object, nothing else.