Modernise and re-home PyAuto workflow skills for PyAutoBrain - #5
Merged
Conversation
Move the development-workflow skills here from PyAutoMind/skills/ and redesign them as thin organism entry points, preserving every command name and the start/ship lifecycle: - start_dev / start_dev_for_user route reasoning through the Brain Feature Agent (consulting PyAutoMemory for context); ship_library / ship_workspace gate through the Health Agent -> Heart readiness verdict before the dev workflow commits/pushes/opens the feature PR. ship_* is feature-dev work, NOT a Build task — Build is release/packaging only and is called solely for the release step. - plan_branches, start_library, start_workspace, register_and_iterate updated to the same organ-boundary framing. - "Remote / mobile mode" removed in favour of the general execution-environment model (local-dev / web-github / ci-only / analysis-only); no phone<->laptop handoff concept remains. - Shared context factored into skills/WORKFLOW.md and per-skill reference.md so every primary skill file stays under 200 lines. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012v2ZYN4RCib1252BEWBb4t
This was referenced Jun 29, 2026
Merged
Instead of re-implementing gh issue create + prompt move + push, start_dev now hands the classified repo/title/plan/branch to PyAutoMind's /create_issue primitive and keeps only the Brain-specific concerns: triage via the Feature Agent, conflict-aware registration (active.md vs planned.md), and routing to /start_library or /start_workspace. The duplicated issue-body template is replaced by a pointer to create_issue, retaining only start_dev's extra fields (Work Classification, Worktree root). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012v2ZYN4RCib1252BEWBb4t
Move repo_cleanup here from admin_jammy. Repo hygiene is the between-tasks counterpart to start_*/ship_*: Brain reasons about what is safe to remove and executes its own git mechanics (branch/stash deletes), exactly as ship_* executes commits/PRs. Heart only observes the hygiene signal (open PRs, worktree/dirty state) — it never mutates, so a destructive sweep cannot be a Heart skill; and cleanup is not release work, so it never touches Build. Notes the natural future home: a dedicated PyAutoBrain Cleanup Agent alongside Feature/Build/Health. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012v2ZYN4RCib1252BEWBb4t
Posting progress to a tracked issue is part of the development cycle (the start_* -> ship_* lifecycle; start_dev_for_user calls it at milestones), so it belongs with the Brain dev-workflow skills. Command name (/update-issue) preserved; organ-boundary note added. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012v2ZYN4RCib1252BEWBb4t
This was referenced Jul 28, 2026
Jammy2211
pushed a commit
that referenced
this pull request
Aug 10, 2026
…t on PyAutoMind REFERENCE.md states the contract: Intake persists Difficulty: from the shared sizing faculty "so the value shown up front is the one the Feature Agent later acts on". It was not acted on. _feature.py mentioned Difficulty once, where it PRINTED its own re-derived score, and read no header key at all — not Difficulty:, not Status:, not Priority:, not Blocked-by:/Closes-when:. The visible failure: `feature select` recommended a prompt declaring Status: blocked, Priority: low AND an explicit Blocked-by: gate whose body says "do not start before the queue runner has run cleanly". Parsing lands in the sizing faculty, beside the derivation it overrides, so declared and derived stay in one place and the bug/refactor conductors get the same reading for free: - declared_header() reads Difficulty/Status/Priority/Blocked-by/Closes-when, skipping fenced blocks. That skip is load-bearing, not tidiness: the bug prompt driving this fix QUOTES the offending header in a ```-block, so without it the bug report would declare itself blocked. Same rule and same reason as PyAutoMind lifecycle.py:draft_gate_refs. - trailing `# note` comments are stripped, splitting on " #" so a Repo#123 ref survives intact (the live backlog has both forms on one line). - an unrecognised Difficulty: value is ignored rather than trusted. The ranker then honours them: declared difficulty overrides derived (with the disagreement REPORTED, not silently resolved — the gap is evidence about the heuristic); Priority: orders the shortlist above the difficulty term; and a prompt declaring Status: blocked or an unresolved Blocked-by: sinks below everything and can never be the recommended pick. It stays listed in its own labelled band so a human can see and override, and next_action says do not start. declared_blocked() is deliberately conservative: this agent is offline and cannot tell whether a gate has since closed, so an unresolved Blocked-by: reads as blocked and the output points at `lifecycle.py issues --drafts`, which does resolve refs against GitHub. Being wrongly held back is cheap and visible; being wrongly recommended is the failure this exists to stop. Measured on the live backlog: the blocked prompt drops from rank 1 to last of 27, correctly labelled, and two further blocked prompts surface that had not been noticed by hand. draft_staleness_detection_signals moves from too-large #26 to medium #5 — it derived too-large purely on file length, and length is a bad size proxy because a prompt grows as it accumulates findings. New tests are hermetic and pin the regression by the offending prompt's HEADER SHAPE rather than the live file, so fixing the backlog cannot silently retire them. Verified they actually bite: reverting only _feature.py fails 7 of the 10. Fixtures use invented repo names, so the file adds no tenant-firewall instance facts. Prompt: PyAutoMind draft/bug/pyautobrain/feature_ranker_ignores_header_keys.md Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WSCA1h6cSKMNwFmWEsxuCL
Jammy2211
added a commit
that referenced
this pull request
Aug 10, 2026
…t on (#217) PyAutoMind REFERENCE.md states the contract: Intake persists Difficulty: from the shared sizing faculty "so the value shown up front is the one the Feature Agent later acts on". It was not acted on. _feature.py mentioned Difficulty once, where it PRINTED its own re-derived score, and read no header key at all — not Difficulty:, not Status:, not Priority:, not Blocked-by:/Closes-when:. The visible failure: `feature select` recommended a prompt declaring Status: blocked, Priority: low AND an explicit Blocked-by: gate whose body says "do not start before the queue runner has run cleanly". Parsing lands in the sizing faculty, beside the derivation it overrides, so declared and derived stay in one place and the bug/refactor conductors get the same reading for free: - declared_header() reads Difficulty/Status/Priority/Blocked-by/Closes-when, skipping fenced blocks. That skip is load-bearing, not tidiness: the bug prompt driving this fix QUOTES the offending header in a ```-block, so without it the bug report would declare itself blocked. Same rule and same reason as PyAutoMind lifecycle.py:draft_gate_refs. - trailing `# note` comments are stripped, splitting on " #" so a Repo#123 ref survives intact (the live backlog has both forms on one line). - an unrecognised Difficulty: value is ignored rather than trusted. The ranker then honours them: declared difficulty overrides derived (with the disagreement REPORTED, not silently resolved — the gap is evidence about the heuristic); Priority: orders the shortlist above the difficulty term; and a prompt declaring Status: blocked or an unresolved Blocked-by: sinks below everything and can never be the recommended pick. It stays listed in its own labelled band so a human can see and override, and next_action says do not start. declared_blocked() is deliberately conservative: this agent is offline and cannot tell whether a gate has since closed, so an unresolved Blocked-by: reads as blocked and the output points at `lifecycle.py issues --drafts`, which does resolve refs against GitHub. Being wrongly held back is cheap and visible; being wrongly recommended is the failure this exists to stop. Measured on the live backlog: the blocked prompt drops from rank 1 to last of 27, correctly labelled, and two further blocked prompts surface that had not been noticed by hand. draft_staleness_detection_signals moves from too-large #26 to medium #5 — it derived too-large purely on file length, and length is a bad size proxy because a prompt grows as it accumulates findings. New tests are hermetic and pin the regression by the offending prompt's HEADER SHAPE rather than the live file, so fixing the backlog cannot silently retire them. Verified they actually bite: reverting only _feature.py fails 7 of the 10. Fixtures use invented repo names, so the file adds no tenant-firewall instance facts. Prompt: PyAutoMind draft/bug/pyautobrain/feature_ranker_ignores_header_keys.md Claude-Session: https://claude.ai/code/session_01WSCA1h6cSKMNwFmWEsxuCL Co-authored-by: Claude <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
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
Lead PR of a 6-repo change that re-homes and redesigns the PyAuto development-workflow skills for the PyAutoBrain era, per
PyAutoMind/skills/OWNERSHIP.mdandPyAutoMind/autoprompt/skill_redesign.md.This repo is the home of the development-workflow skills, all command names preserved:
start_dev,start_dev_for_user,plan_branches,start_library,start_workspace,ship_library,ship_workspace,register_and_iterate— moved fromPyAutoMind/skills/.repo_cleanup— moved from admin_jammy; between-tasks git hygiene (Heart observes, Brain decides + executes; future Cleanup Agent is its natural home).update_issue— moved from admin_jammy; dev-progress posting in the start→ship cycle.Redesign
start_devroutes through the Brain Feature Agent (consulting PyAutoMemory) and delegates the issue write to the Mind primitive/create_issue.ship_library/ship_workspacegate through the Health Agent → Heart readiness verdict before the dev workflow commits/pushes/opens the feature PR.ship_*/repo_cleanuprun their own git mechanics; PyAutoBuild is the release/packaging executor and is reached only for the release step (it now has askills/root for release-execution skills likepre_build, but owns no dev-workflow skills).skills/WORKFLOW.md. Thehandoffskill is retired.skills/WORKFLOW.md; long-form detail in per-skillreference.md. Guard:admin_jammy/skills/check_skill_line_counts.sh(all 27 primary files pass).Companion PRs (branch
claude/pyauto-skills-modernize-l29hxr)create_issuemade the issue primitive;OWNERSHIP.md+ README;handoffretiredpre_build)profile_likelihoodValidation
bash admin_jammy/skills/install.sh→ every moved/commandresolves;handoffno longer installed; no dangling symlinks.bash admin_jammy/skills/check_skill_line_counts.sh→ all 27 primary files within 200 lines.🤖 Generated with Claude Code