Łukasz Myśliński lmyslinski
lmyslinski
/ gist:21a151a76ee01313bbd81efe20621df4
Created
January 14, 2026 10:57
Custom skills tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 1. Setup mock workflow server - it needs to receive a call from the reasoning api, do some sleep work/processing and return a randomized(?) response with expected schema | |
| 2. Prepare DB for custom skills storage - we need to store workflow references, config and any additional fields that might be required | |
| Q: Should we use json here? It makes sense since the workflow config is likely to be highly customizable | |
| Q: Should we explore using langgraph here? | |
| 3. Implement workflow API calling and pausing the skill execution |
lmyslinski
/ gist:c4e49c41c8908ff80d46626ac7e1d2aa
Created
November 11, 2016 19:13
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| with tf.Session() as sess: | |
| # Set up all the tensors, variables, and operations. | |
| input = tf.constant(x_with_bias) | |
| target = tf.constant(np.transpose([y]).astype(np.float32)) | |
| weights = tf.Variable(tf.random_normal([2, 1], 0, 0.1)) | |
| tf.initialize_all_variables().run() | |
| yhat = tf.matmul(input, weights) | |
| yerror = tf.sub(yhat, target) |