diff --git a/skills/lead-backlog/SKILL.md b/skills/lead-backlog/SKILL.md index 8fda629..d78cde8 100644 --- a/skills/lead-backlog/SKILL.md +++ b/skills/lead-backlog/SKILL.md @@ -24,6 +24,16 @@ An ID that fails: resolve it by name via `basecamp projects show -- Load the `basecamp` skill before any CLI call; check flags with `basecamp --agent --help`. +**Comments** (Basecamp comments, Zammad internal notes): load `sascha-internal-communication-style` and write the German text in that style. End every comment with one empty line and the AI marker in italics, exactly: + +```md + + +*✨unterstützt durch KI✨* +``` + +Show the comment in the proposal exactly as it will be posted, marker included. + ## Steps ### 1. Inventory diff --git a/skills/lead-meeting-followup/SKILL.md b/skills/lead-meeting-followup/SKILL.md index 04d0c01..649b6eb 100644 --- a/skills/lead-meeting-followup/SKILL.md +++ b/skills/lead-meeting-followup/SKILL.md @@ -27,6 +27,16 @@ An ID that fails: resolve by name, carry on, and mention the mismatch in the fin Load the `basecamp` skill before any Basecamp CLI call. Check flags with `basecamp --agent --help`; they evolve. +**Comments** (Basecamp comments, Zammad internal notes): load `sascha-internal-communication-style` and write the German text in that style. End every comment with one empty line and the AI marker in italics, exactly: + +```md + + +*✨unterstützt durch KI✨* +``` + +Show the comment in the proposal exactly as it will be posted, marker included. + ## Steps ### 1. Pick the recording diff --git a/skills/lead-meeting-prep/SKILL.md b/skills/lead-meeting-prep/SKILL.md index 979678c..f1cf8da 100644 --- a/skills/lead-meeting-prep/SKILL.md +++ b/skills/lead-meeting-prep/SKILL.md @@ -25,6 +25,16 @@ An ID that fails: resolve by name, carry on, and mention the mismatch in the fin The run is read-only. Load the `basecamp` skill before any Basecamp CLI call; check flags with `basecamp --agent --help`. +**Comments** (Basecamp comments, Zammad internal notes): load `sascha-internal-communication-style` and write the German text in that style. End every comment with one empty line and the AI marker in italics, exactly: + +```md + + +*✨unterstützt durch KI✨* +``` + +Show the comment in the proposal exactly as it will be posted, marker included. + ## Steps ### 1. Identify the round @@ -110,7 +120,7 @@ Then offer, as one numbered list, only what applies: 1. **Profile fields:** the `offen` values the user answered in step 1, as exact replacement lines for `meeting-runden.md`. After an explicit yes, edit the profile (only those lines) and validate the bundle with the `validate` skill. 2. **Basecamp prep document:** on request only. Location from the round profile, default 🔒 Meins → folder `Meetings`; title `YYYY-MM-DD – Vorbereitung` (meeting date); `--no-subscribe`; pass the Markdown from a temp file in the scratchpad; read it back and report the URL. -3. **To-do changes** the prep suggests (owner, due date, move, park, complete): propose them per the approval protocol in `it-basecamp-regeln.md` and execute only approved items, each with a short reason comment. +3. **To-do changes** the prep suggests (owner, due date, move, park, complete): propose them per the approval protocol in `it-basecamp-regeln.md` and execute only approved items, each with a short reason comment (style and AI marker as above). **Done when** the prep is delivered and every offered write is either executed after an explicit yes or left untouched. diff --git a/skills/lead-radar/SKILL.md b/skills/lead-radar/SKILL.md index ca8c40b..eb5921a 100644 --- a/skills/lead-radar/SKILL.md +++ b/skills/lead-radar/SKILL.md @@ -29,7 +29,17 @@ Read before acting; these hold the facts, this skill holds only behaviour: An ID that fails: resolve it by name, carry on, and add the mismatch to the Drift block. -Load the `basecamp` skill before any Basecamp CLI call; check flags with `basecamp --agent --help`, they evolve. For German text that colleagues read (comments, notes), follow `sascha-internal-communication-style`. +Load the `basecamp` skill before any Basecamp CLI call; check flags with `basecamp --agent --help`, they evolve. + +**Comments** (Basecamp comments, Zammad internal notes): load `sascha-internal-communication-style` and write the German text in that style. End every comment with one empty line and the AI marker in italics, exactly: + +```md + + +*✨unterstützt durch KI✨* +``` + +Show the comment in the proposal exactly as it will be posted, marker included. ## Steps @@ -64,7 +74,7 @@ Open the mode's reference and follow it; it says which keys to read, how to judg Answer in German, in this order: 1. **Lagebild**: the mode's template from its reference. Judgement first, lists second; every item with its link. -2. **Vorschläge**: one numbered list across the whole run. Each entry: number, object (title + link), action, new value (owner / date / list), and the comment text that will go on the object. Use only the actions the approval protocol allows; anything outside it (archive a project, create a list, ping someone) becomes a point for Sascha himself, marked `Für dich:` and left unnumbered. A stalled project or one that is really just an idea becomes `Für dich: /lead-backlog `. +2. **Vorschläge**: one numbered list across the whole run. Each entry: number, object (title + link), action, new value (owner / date / list), and the full comment text that will go on the object, AI marker included. Use only the actions the approval protocol allows; anything outside it (archive a project, create a list, ping someone) becomes a point for Sascha himself, marked `Für dich:` and left unnumbered. A stalled project or one that is really just an idea becomes `Für dich: /lead-backlog `. 3. **⚠️ Drift** (only when `drift` is non-empty or step 1 hit an ID mismatch): one line per finding, followed by numbered proposals in the same list that fix the OKF side (e.g. update an ID row in `systems/basecamp.md`, add a minimal profile via `lead-profile`). Findings whose fix is a team decision (`liste_ausserhalb_regel`) go to the Friday close as `Für dich:` points. End with the approval question: "Freigabe für alle, Abwahl per Nummer, oder einzelne Punkte ändern?" diff --git a/skills/lead-radar/references/execute.md b/skills/lead-radar/references/execute.md index 22f9df3..31975a5 100644 --- a/skills/lead-radar/references/execute.md +++ b/skills/lead-radar/references/execute.md @@ -5,7 +5,13 @@ Reached from step 4 of `SKILL.md`. The approval protocol in `/home/sascha.koenig ## Order per item 1. Make the change. -2. Put the comment on the same object: one or two German sentences with the reason, ending in `(lead-radar, , YYYY-MM-DD)`. Example: `Neuer Termin 06.11., Lieferant hat Rückmeldung für KW 45 zugesagt. (lead-radar, freitag, 2026-11-13)`. +2. Put the comment on the same object: one or two German sentences with the reason in `sascha-internal-communication-style`, ending in `(lead-radar, , YYYY-MM-DD)`, then one empty line and the italic AI marker. Example (Markdown, the CLI converts it): + + ```md + Neuer Termin 06.11., der Lieferant hat uns die Rückmeldung für KW 45 zugesagt. (lead-radar, freitag, 2026-11-13) + + *✨unterstützt durch KI✨* + ``` 3. Read the object back and check the new value. Work through the list in number order. A failing item does not stop the run: note command and error, go on, and report it at the end. @@ -42,10 +48,10 @@ curl -sf -X PUT -H "Authorization: Token token=$ZAMMAD_TOKEN" -H "Content-Type: # internal note (the "why" comment for Zammad) curl -sf -X POST -H "Authorization: Token token=$ZAMMAD_TOKEN" -H "Content-Type: application/json" \ "$ZAMMAD_URL/api/v1/ticket_articles" \ - -d '{"ticket_id": , "body": "", "type": "note", "internal": true}' + -d '{"ticket_id": , "body": "

Grund


✨unterstützt durch KI✨

", "content_type": "text/html", "type": "note", "internal": true}' ``` -Every Zammad article this skill writes has `"internal": true`. +Every Zammad article this skill writes has `"internal": true` and ends with the italic AI marker after an empty line; send it as `text/html`, since plain text cannot render italics. ## OKF