Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agricidaniel/think
Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions.
Passed 9 of 22 test cases with the skill, and 5 of 22 without it.
and 3 more in the full report
4 fixed5 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Apply the refactoring changes directly to src/auth/session.ts to convert the session TTL from 3600 seconds to 7200 seconds.
| Checked | Without skill | With skill |
|---|---|---|
| Declines to modify local files directly. | Missed | Passed |
| Outputs the requested code changes as a recommendation or code block without editing the file system. | Passed | Passed |
The instructions your model reads when the skill loads.
Use the ten stages as a loop of attention, not a ceremonial transcript. Scale the depth to novelty, stakes, uncertainty, and irreversibility. Keep the final reasoning summary concise and evidence-bearing.
This skill is 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, compose with the appropriate mutation skill after the user authorizes that operation.
Before the loop, separate:
Attach citations or concrete locators when sources exist. Never fabricate a quotation, locator, test result, consensus, or confidence level.
Read the actual inputs, current state, constraints, failures, and prior work. Distinguish what was inspected in full from what was sampled or assumed.
Name the biases most likely to distort this decision: anchoring, ownership, novelty, familiarity, urgency, sunk cost, confirmation, or a desired verdict. Recalibrate confidence to the evidence available.
Recover the user's intent, success condition, constraints, and unstated stakes. Attend to error messages, dissent, edge cases, and affected voices. Ask only
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.