own
Use when the user asks for a debrief on recent work, wants to check what they actually own versus what AI carried, or asks to be quizzed on their codebase. Triggers on "debrief", "what do I own", "own this", "quiz me on the code". User-invoked only — never self-trigger from context.
Profile →npx skills add majiayu000/claude-skill-registry --skill own --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
Probe the human's understanding of their own codebase so they keep the capacity to own what they ship. A debrief is a conversation, not a score. ## Principles - The ledger is the baseline, never git history — a commit SHA points into history other people rewrite; the ledger is append-only and owned. - The human's attention is the constraint: 4 questions per debrief, regardless of ledger size. - Deterministic work belongs to deterministic tools (jq/date); judgment work to the model. - Questions come from understood code — callers, invariants, neighbors — never from raw diff hunks. The survey IS the context retrieval. - A concept that can't be found in current code is asked about, never silently recorded as gone. ## Invisibility (load-bearing) - Never surface due dates, streaks, mastery labels, or any interval-derived signal. The moment one leaks, the schedule stops measuring forgetting and starts manufacturing performance — and reverts to a fixed staleness window. - k, interval, priority, assisted/owned status: scheduling internals, model-facing only. ## Ledger Location: `~/.claude/hope/own/<project-slug>/ledger.json` — hope-owned namespace, never the harness project directory (plug
- Principles
- Invisibility (load-bearing)
- Ledger
- Merges
- Workflow
- Step 1: Locate ledger
- Step 2: Survey
- Step 3: Rank and sample
- Step 4: Probe
- Step 5: Close
- Grader is the examiner
- Boundaries
What does the own skill do?
Use when the user asks for a debrief on recent work, wants to check what they actually own versus what AI carried, or asks to be quizzed on their codebase. Triggers on "debrief", "what do I own", "own this", "quiz me on the code". User-invoked only — never self-trigger from context.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill own --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.