feat: Add experts system for auto-improving domain knowledge #192
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
nhorton
changed the title
Add specification for the experts system - auto-improving collections of domain knowledge that get exposed as Claude agents. - Add doc/experts_requirements.md with full specification: - Directory structure (.deepwork/experts/[name]/) - File formats (expert.yml, topics/*.md, learnings/*.md) - CLI commands (deepwork topics, deepwork learnings) - Sync behavior (generates agents in .claude/agents/) - Add initial "experts" standard expert in src/deepwork/standard/experts/: - Meta-expert for the experts system itself - Topics on design patterns and discovery descriptions - Update doc/architecture.md: - Add src/deepwork/standard/ directory to structure diagram - Add "Experts (Planned)" section Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove "(Planned)" from section heading and update status to reflect that the experts system implementation is now complete. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
nhorton
force-pushed
the
expert_support
branch
from
8fd479c to
cd3856c
Compare
nhorton
changed the title
- Add `agent: deepwork-jobs` to all 4 steps in deepwork_jobs job.yml - Remove misleading "Prerequisites" documentation from step files - Create new step_delegation.md topic explaining how to use expert delegation - Update job_yml_schema.md with "Agent Delegation" section - Key insight: "This is how you make a step 'run via' an expert" The deepwork_jobs steps now properly delegate to the deepwork-jobs expert, giving them access to job schema knowledge, best practices, and learnings. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add new review_pr job with 3 steps: check_relevance, deep_review, improve_and_rereview - Use inline bash completion $(gh pr diff) for efficient token usage in expert prompts - Experts focus only on their domain expertise for specialized feedback - Iterative improvement cycles until all experts approve or 3 max iterations - Add learnings: domain focus in expert prompts, efficiency improvements - Code cleanup: remove redundant try/except and unused context variables - Include PR review output files from workflow execution Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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.
Summary
doc/experts_requirements.mdExpertDefinition,Topic,Learning)deepwork topics,deepwork learnings)deepwork installdeepwork syncTest plan
deepwork installinstalling expertsdeepwork syncgenerating expert agents🤖 Generated with Claude Code