Renames the skill directory to match the plan's architectural reshape.
Stacking is a GitHub feature (gh-stack extension, GitHub's stack UI),
not a git feature, and the ce- prefix matches the future convention
for plugin skills.
Narrows scope to decomposition only:
- Removes manage-mode operations. Push and submit are owned by
git-commit-push-pr now that it is stack-aware. Rebase, sync, view,
and navigation commands are one-line pass-throughs to gh stack with
no skill-scale value — invoked directly when needed.
- Removes the three-flavor invocation enumeration (manual / delegated
/ auto-invoked). Consent routing relies on the governing principle
that respects prior user decisions within the session, rather than
structured caller-side flags.
- Drops the delegated / stacking_declined / gh_stack_install_declined
signal plumbing from the SKILL.md. Agent context awareness is the
primary mechanism; the principle is documented at the bottom.
Narrows the CLI surface section: init, add, view, unstack --local for
rollback. Ship commands (push, submit) moved to git-commit-push-pr.
Rewrites splitting-workflow reference file: four phases collapsed to
three. Removes the submit phase entirely; phase 3 ends with a handoff
to git-commit-push-pr, which then runs gh stack push + gh stack
submit + per-PR description generation via ce-pr-description. Separating
decomposition from shipping bounds failure blast radius to local state.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Renames git-stack to ce-pr-stack — stacking is a GitHub feature, not a git
feature, and the ce- prefix matches the future convention for plugin skills.
Restructures responsibilities:
- ce-pr-stack: decomposition only (analyze + propose + create layers locally).
Manage mode removed; pure pass-throughs to gh stack commands do not warrant
a skill wrapper.
- git-commit-push-pr: single ship path for both monolithic and stacked cases,
with four explicit routing cases (already in stack, suggest stacking,
offer install, monolithic). Absorbs what was previously a duplicate submit
phase in ce-pr-stack.
- ce-pr-description (new Unit 5): focused skill for PR description writing,
invoked by git-commit-push-pr for each PR created or updated.
Drops the three-flavor invocation enumeration (manual/delegated/auto-invoked)
and the delegated: true flag. Consent routing now relies on the governing
principle that respects prior user decisions within the session — agent
context awareness handles it without structural signal plumbing.
Adds the --plan input for ce-pr-stack so ce:work's Phase 4 shipping delegation
can pass plan-unit boundaries as primary signal for candidate layers.
Adds R10 (ce-pr-description) and renumbers Units 5-10. Updates Requirements
Trace, Key Technical Decisions, System-Wide Impact, and Risks tables for
the new architecture.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Four-phase workflow for decomposing a feature branch into stacked PRs:
analyze (commit-based grouping as V1 strategy), propose layers with
mandatory user approval, create the stack locally using gh stack init
and gh stack add, submit via gh stack push plus gh stack submit. The
rollback protocol separates local construction from remote submission
so failures stay local. Workflow content verified against the installed
gh-stack CLI via --help on each command referenced.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Handles two operational modes (split to decompose a branch into stacked
PRs, manage to drive an existing stack via gh stack commands) with three
invocation flavors (manual, delegated, auto-invoked). Auto-invocation
runs an effectiveness-test gate before proposing a split; manual and
delegated entries go straight to layer proposal, which remains the
second gate for all modes. Availability gate offers to install gh-stack
and runs the command on consent, honoring the session-level governing
principle that respects prior user decisions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Emits parseable signals about gh-stack availability, current branch's
stack-membership state, and change summary vs a base branch. Supports
--mock and STACK_DETECT_MOCK for testing without a real stack. Reports
signals only — no "should stack" judgments, which belong in consuming
skills per the plan's governing principle.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Detection uses gh extension list because gh-stack is a gh CLI extension,
not a standalone binary. The check-health loop now handles gh-* entries
specially and skips them gracefully when gh itself is missing, avoiding
confusing "install gh extension" messaging in that case.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added Unit 7 (stack-aware resolve-pr-feedback), Unit 8 (ce:plan stack-
candidacy assessment), renumbered README unit to Unit 9. Replaced the
files+lines+concerns heuristic with a two-stage effectiveness test
(size/spread hint then independence/divergence/sequencing/mixed-kinds
signals) grounded in SmartBear/Cisco, Rigby & Bird, and practitioner
consensus. Added "Respect prior user decisions within the session" as
a governing principle. Corrected the gh-stack CLI surface against the
installed extension (added rebase, sync, merge, view, checkout, etc.
— the plan previously listed status which does not exist). Documented
offer-and-run install across all touchpoints.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Covers retroactive splitting, shipping-time suggestion, and
detection across ce-setup, git-commit-push-pr, ce-work, and a
new git-stack skill. Reviewed by 5 document-review personas
with 12 auto-fixes and 7 judgment findings addressed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Trevin Chow