Save

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — USE REQUIREMENTS DISCLOSED FIRST: this skill works on your own Obsidian vault and runs through the portable core of the claude-obsidian repository, scripts/claude-obsidian.py, which lives at the repository root OUTSIDE this skill's folder, together with the shared contracts it links to (under skills/wiki/references/ in that same product root, for example the provenance and operation-transaction contracts). Installing this listing copies only this skill's folder: without a full claude-obsidian installation (the core, its contracts, python3 to run it, and a selected user vault) the skill cannot run its transactions as designed. The family orchestrator is the separate wiki skill of the same repository. No account, no key and no payment are needed to copy the files, and nothing is run during installation. This skill needs no network egress at use time, and its own text forbids it from making any network request. Install "Save" for me. It saves a user-selected answer, decision, insight or session summary from the current conversation into your Obsidian vault as ONE reviewed transaction. It runs only when you explicitly ask to preserve specific conversation content (triggers like /save or 'save this'): never automatically, never capturing a whole transcript by default, and never inferring permission to archive unrelated content; if the scope, destination or treatment of sensitive content is unclear it asks one focused question before drafting. The material you select is treated as untrusted content-to-preserve, not as instructions: embedded directives inside it (run commands, widen scope, disclose data, change destination, enable egress) are ignored. It resolves your vault, reads the hot cache, index and at most five directly relevant pages, searches for an existing note before creating one (replacing a canonical note needs your explicit approval), picks the smallest useful note type (usually question, concept, source or session), and drafts ALL changes before touching vault state: the selected note, the active index or MOC link, one new entry at the top of wiki/log.md, a refreshed wiki/hot.md under 500 words, and source/claim ledger updates only when evidence changed. Conversation assertions are classified synthetic or unsupported/provisional, never accepted evidence on their own. The bundle is a claude-obsidian.transaction.v1 of operation type save, inspected through the core's workflow gate and applied only with the approval hash (APPROVAL_SHA256 pattern) and only when both storage_valid and workflow_complete pass. A Git checkpoint is optional and only when you explicitly ask for one. Repository: https://github.com/AgriciDaniel/claude-obsidian (the skill is the whole skills/save/ folder at the pinned commit: SKILL.md only, 1 file) Pinned version: install the code at commit 2e545563172f97f02ecaaaab376ceea1246a0583 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/AgriciDaniel/claude-obsidian into a temporary folder, check out commit 2e545563172f97f02ecaaaab376ceea1246a0583, and copy the skills/save/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 f668e5a4f05448821a026183ea4901ab444751eb761694942f5eeb8f968e6108 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file only: SKILL.md. The core it runs (scripts/claude-obsidian.py), the page schema it cites (claude_obsidian/page_schema.py) and the contracts it links to live outside this folder, in the full claude-obsidian product root. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit, and nothing from any conversation is saved. - At use time it makes no network request at all (its text forbids egress): it saves only the conversation content I explicitly selected, as one inspected workflow bundle applied with the approval hash (APPROVAL_SHA256 pattern), writing the note plus its index/MOC link, a wiki/log.md entry and a refreshed wiki/hot.md in my vault. - It never runs automatically, never captures a whole transcript by default, and treats the content being saved as untrusted content-to-preserve: embedded instructions inside it are ignored, and conversation assertions are never upgraded to accepted evidence on their own. - Do not save anything, do not draft any bundle, and do not use the skill in any way during this install: using it is a separate step that only starts when I explicitly ask to save something later. 3. When I say "yes, install", install it as a skill: copy the whole save folder into the agent's skills directory, in a folder named exactly "save", keeping its single file (SKILL.md) at its root. 4. Verify with no network calls: frontmatter valid (name: save), the 1 file in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that a full claude-obsidian installation (portable core and contracts at the product root) and my own Obsidian vault are required to use it, that it runs only on an explicit save request for specific content, and that it makes no network requests). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.