Repository navigation
docs: add a codebase-focused Tasksmith evaluation tutorial - #181
Merged
Merged
Conversation
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Readers can now follow a codebase-focused tutorial from choosing a merged PR to generating a Tasksmith task, reviewing its evidence, freezing a suite and comparing agent runs with Harbor.
Adds a Tutorials section to navigation and the homepage, a maintained Daytona/CPU options example, and a workflow diagram. Includes an original abstract thumbnail on the tutorial card, article and social-sharing preview, with its generation prompt recorded alongside the asset. The walkthrough separates task-quality checks from agent evaluation, explains the current input limits and budget boundaries, and grounds its case study in the recorded HF_ML_Tasksmith results.
Tutorials receive visible author/date/version metadata, canonical URLs, Article structured data, social previews, sitemap dates, search coverage and an RSS feed. A contributor guide documents future articles, and CI checks their exported metadata and discovery links.
Validation: static site build, TypeScript, Ruff, metrics consistency and 10,651 internal links pass. Options validate against the Tasksmith schema; Harbor commands parse without dispatching jobs. The suite-freezing snippet was exercised for identity/mode preservation, unready-task rejection and overwrite protection. Desktop/mobile rendering and interactive search were checked locally. No paid generation or cloud evaluation was run for this documentation change; indexing can be requested after deployment.