Tooluck logoTooluck
SKILL.md

think

Agent skill fromAgriciDaniel/claude-obsidian

Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions. Use for think this through, deep think, architecture review, postmortem, tradeoff analysis, or challenges to assumptions. This is a reasoning review, not a deterministic vault health check or repair workflow.

How to install think

install think
# install the claude-obsidian pack with the skills CLI
npx skills add AgriciDaniel/claude-obsidian

# or add only this skill to Claude Code: copy the folder

skills/think/

# into

~/.claude/skills/think/ (all projects)

.claude/skills/think/ (one project)

skills/think/SKILL.md

MITFull file
1# Think
2
3Use the ten stages as a loop of attention, not a ceremonial transcript. Scale
4the depth to novelty, stakes, uncertainty, and irreversibility. Keep the final
5reasoning summary concise and evidence-bearing.
6
7This skill is read-only. It may inspect available evidence, but it does not
8edit files, execute a vault mutation, commit Git, or publish anything. If the
9CREATE stage recommends a change, compose with the appropriate mutation skill
10after the user authorizes that operation.
11
12## Establish an evidence frame
13
14Before the loop, separate:
15
16- **Observed:** directly supported by an input, source, test, or measurement.
17- **Inferred:** a conclusion drawn from observations; state the bridge.
18- **Unknown:** missing evidence that could change the decision.
19- **Preference:** a user or designer choice, not a factual claim.
20
21Attach citations or concrete locators when sources exist. Never fabricate a
22quotation, locator, test result, consensus, or confidence level.
23
24## The ten stages
25
26### 1. OBSERVE: external
27
28Read the actual inputs, current state, constraints, failures, and prior work.
29Distinguish what was inspected in full from what was sampled or assumed.
30
31### 2. OBSERVE: internal
32
33Name the biases most likely to distort this decision: anchoring, ownership,
34novelty, familiarity, urgency, sunk cost, confirmation, or a desired verdict.
35Recalibrate confidence to the evidence available.
36
37### 3. LISTEN
38
39Recover the user's intent, success condition, constraints, and unstated stakes.
40…

Excerpt shown under the repository's MIT license.

More skills in claude-obsidian

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates