tpierrain/kenjaku/prepare-1-1
Claude Code and agent skill by tpierrain/kenjaku
- community
Checking that the SKILL.md file is still in the repository.
Prepare a 1-1 with anyone, in both directions: with YOUR manager (the topics you want to raise, what has changed since last time) or with someone YOU manage (commitments made/delegated, operational topics, KPI review). Takes a name/alias, cross-references the person's profile, the last 1-1 and the delta of recent signals (via sync-sources, READ-ONLY). Meta skill: a structure that gives you ideas, to be refined to your own focus areas and KPIs (with /improve if needed).
Install
npx vskill@latest install tpierrain/kenjaku/prepare-1-1SKILL.md
/prepare-1-1 — Prepare a 1-1 (meta version)
Produces a briefing scannable in 2 minutes before your next 1-1. This is a meta skill: it lays out a structure that gives you ideas; you then refine it to your own focus areas, your KPIs and the way you run your 1-1s (edit this file, or ask /improve to help you).
Parameter
A name or alias of a person in $ARGUMENTS (e.g. /prepare-1-1 jane). Used to find vault/people/<firstname-lastname>.md (kebab-case, no accents) and the cache vault/backlog/<name>.md. If no profile matches, suggest the closest profiles from vault/people/ and stop.
Absolute constraint
READ-ONLY. Never send a message, email or reaction, never post anywhere. Produce only a local markdown file in the vault.
Step 0 — Direction of the 1-1 (determines the output structure)
Two cases, depending on your relationship with the person (infer it from their role in vault/people/<name>.md; when in doubt, ask):
- A · 1-1 with YOUR manager (you are the managee) → "what I want to raise" structure.
- B · 1-1 with someone YOU manage (a report, or a peer you coach) → "follow-up + operational + KPI"
structure.
Step 1 — Collection (fan-out, READ-ONLY)
In parallel (`sync-sources` architecture, ~500-token summaries):
- Backlog cache:
vault/backlog/<name>.md— open / recurring actions (a point raised
2+ times without closure is a priority).
- Last 1-1: the note in
vault/meetings/(or via your Calendar connector) — transcript read
by an isolated sub-agent (never raw transcript in the main context). Also note the next 1-1 (date of the output file; otherwise today's date).
- Delta since the last 1-1: messaging, email, shared meetings — depending on your connectors.
Step 2 — Writing the briefing
Write to vault/prep-1-1/YYYY-MM-DD-prep-1-1-<name>.md (date of the next 1-1; create the folder if needed), according to the case detected in step 0.
Case A — 1-1 with your manager (you carry the topics)
Case B — 1-1 with someone you manage (follow-up + operational + KPI)
In both cases, end with a collapsible "Full context" block (summary of the last 1-1, decisions, follow-up actions | # | Action | Who | When | Status |, verbatims, messaging/email/meeting activity with links, source quality).
Step 3 — Update the backlog
In vault/backlog/<name>.md: add the new actions, check off those with proof of completion, update the updated: date. Append-only on facts already recorded.
Writing rules
- English, direct and ultra-concise tone; bullet lists rather than paragraphs.
- Do not make things up; flag a partial or low-quality source.
- No empty section — omit it (except "KPI review" and "Recurring focus areas" in case B, to keep
as a reminder even when empty, since these are the sections you must make your own).
- Never a bare URL:
[text](url). Backlinks[[people/firstname-lastname]](never a first name alone).
Refining this skill (that's the point of a meta skill)
The structure above is a starting point. Make it yours: replace the example KPIs with your own, add/remove recurring focus areas, adjust the sections to the type of 1-1 you run. You can do it by hand (edit this file) or ask `/improve` to assist you.
Success criterion
In < 2 minutes of reading, you know what to address, why, with which opening question — and, on the manager side, where the commitments and the KPIs that matter stand.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingmaintainers/qa/release-fixtures/v3.6.0/.claude/skills/prepare-1-1/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tpierrain/kenjaku/prepare-1-1)