Think

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 — None to install or use this skill: no account, no key, no payment, and, unlike the rest of the claude-obsidian family, this SKILL.md invokes no portable core, no vault and no script: it is a standalone, read-only reasoning framework. It edits no files and, on its own, writes nothing anywhere. Install "Think" for me. It applies a Fable-derived 10-stage reasoning loop (OBSERVE external, OBSERVE internal, LISTEN, THINK, CONNECT lateral, CONNECT system, FEEL, ACCEPT, CREATE, GROW) to consequential or ambiguous reasoning and decisions: architecture reviews, postmortems, tradeoff analyses and challenges to assumptions. It is a reasoning review, not a deterministic vault health check or repair workflow. Before the loop it separates Observed, Inferred, Unknown and Preference, attaches citations or concrete locators when sources exist, and never fabricates a quotation, locator, test result, consensus or confidence level. Depth scales to novelty, stakes, uncertainty and irreversibility; for a trivial reversible lookup the formal loop is skipped. Its verification discipline: test the highest-risk claim or state why it remains untested, seek disconfirming evidence, present the strongest reasonable counterargument in the ACCEPT stage, and end in the fixed output shape (Decision, Evidence, Counterargument and risks, Verification, Growth loop). This skill is explicitly READ-ONLY: it may inspect available evidence, but it does not edit files, execute a vault mutation, commit Git or publish anything; if the CREATE stage recommends a change, that change is composed with the appropriate mutation skill only after you authorize that separate operation, and saving a lesson afterwards is likewise a separate explicit operation composed with save. Repository: https://github.com/AgriciDaniel/claude-obsidian (the skill is the whole skills/think/ 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/think/ 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 6b418bd96e88ca7b3dbede6cbadfa738e818c04886067844fe9cb979a55b4c10 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, a self-contained reasoning framework. Unlike its sibling skills it references no core script, no vault, no references folder and no transaction contract: nothing outside this folder is needed to use it. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit, and no reasoning session is run. - At use time it is read-only: it may inspect evidence I make available, but it does not edit files, execute a vault mutation, commit Git or publish anything, and it makes no network request of its own. Any change its CREATE stage recommends is a separate operation I must authorize, through the appropriate mutation skill. - It never fabricates a quotation, locator, test result, consensus or confidence level, it must present the strongest reasonable counterargument to its preferred conclusion, and it gives confidence as a calibrated qualitative judgment, not a decorative percentage. - Do not run the loop on any decision, do not inspect any project on its behalf, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later. 3. When I say "yes, install", install it as a skill: copy the whole think folder into the agent's skills directory, in a folder named exactly "think", keeping its single file (SKILL.md) at its root. 4. Verify with no network calls: frontmatter valid (name: think), 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 this skill is standalone and read-only: no vault, core or other family installation is needed for the reasoning loop itself, and any change it recommends requires my separate authorization through a mutation skill). 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.