Conversation
15 increments across 3 phases: - Phase 1: Hub live counts, .STATUS next action, worktree-aware routing - Phase 2: Auto-git, CLAUDE.md sync, pipeline suggestion - Phase 3: Memory capture, insights, facets, learning loop Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…awareness - hub: replace hardcoded counts with dynamic discovery (stats, skills, agents, tests) - hub: add Step 1.5 to read .STATUS Next Action and display above command grid - do: add Step 0.5 worktree detection — skip branch prompts in worktrees - done: add Step 1.14 worktree status summary with ahead/behind and ORCHESTRATE progress - docs: sync Phase 1 changes to published docs, mkdocs build clean Increments 1-5 of ORCHESTRATE-workflow-enhancements.md complete. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…rees, pipeline - done: add Step 3.5 auto-git (commit + push after Option A, skip main, never force-push) - done: add Step 1.10 CLAUDE.md auto-sync (mechanical counts only, SYNCED in summary) - hub: add Step 1.6 worktree detection + WORKTREES section (ahead/behind, stale flag) - do: add Step 2.5 pipeline suggestion (brainstorm→spec→worktree for score>=6 features) - do: add Step 2.6 spec auto-load for agent delegation context - docs: sync Phase 2 to published docs, REFCARD updated, mkdocs build clean Increments 6-10 of ORCHESTRATE-workflow-enhancements.md complete. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…routing - Add Step 1.11 (Memory Capture) to /done: scan session for learnings, deduplicate against MEMORY.md, append confirmed entries - Add Step 1.13 (Insights Capture) to /done: write facet JSON with friction signals, auto-cleanup 90-day retention - Add Step 1.0 (Memory Lookup) to /do: check MEMORY.md for relevant past learnings before routing - Add Step 1.5 (Insights Check) to /do: review recent friction patterns from facets as advisory routing hints - Add Step 1.7 (Recent Usage) to /hub: load facet data for recently used commands footer - Sync all changes to published docs and REFCARD - All 62 tests passing, mkdocs build clean, counts validated Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Create docs/commands/workflow/done.md with full feature documentation - Add Unreleased section to both CHANGELOG.md files - Add /workflow:done nav entry to mkdocs.yml Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Guide: Learning Loop & Session Completion (memory, insights, auto-git) - Guide: Hub Live Dashboard (dynamic counts, next action, worktrees) - Cookbook: Session Wrap-Up Workflow (30-second /done recipe) - Cookbook: Memory-Aware Task Routing (/do memory + insights steps) - Add 4 nav entries to mkdocs.yml (2 guides, 2 cookbooks) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Change version annotations from v2.30.0 to v2.31.0 (v2.30.0 already released) - Remove ORCHESTRATE artifact (working file, not for dev branch) - Sync docs/CHANGELOG.md with source (was missing v2.27.0-v2.30.0) - Fix hub.md banner version from v2.29.0 to v2.30.0 - Fix memory path slug comment (hyphens not underscores) - Fix self-referential link in docs/CHANGELOG.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Data-Wise
force-pushed
the
feature/workflow-enhancements
branch
from
23e7f58 to
43f2e05
Compare
Data-Wise
pushed a commit
that referenced
this pull request
Feb 27, 2026
test_skill_count_matches_plugin_json now accepts both literal
"26 skill" and dynamic "{skill_count}" template variable in
hub.md, since PR #119 converted hub.md to use discovery engine.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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.
Summary
/workflow:donelearning loop — Memory capture (MEMORY.md), insights capture (facet JSON), auto-git (commit + push), CLAUDE.md sync, worktree status with ORCHESTRATE progress/craft:domemory-aware routing — Memory lookup, friction-aware insights check, worktree detection (skip branch prompts), pipeline suggestion (brainstorm→spec→worktree for complex features), spec auto-load for agents/craft:hublive dashboard — Dynamic counts from discovery engine, .STATUS next action, active worktree status with ahead/behind, recently used commands from facetsImplements all 15 increments from ORCHESTRATE-workflow-enhancements.md across 3 phases. All features are opt-out via env vars and degrade gracefully when data sources are missing.
Test plan
test_craft_plugin.py)test_plugin_e2e.py)test_plugin_dogfood.py)mkdocs build --strictclean (no warnings)./scripts/validate-counts.shall counts match🤖 Generated with Claude Code