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>
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>
Beta skills now use disable-model-invocation: true to prevent accidental
auto-triggering. Descriptions written as future stable descriptions with
[BETA] prefix for clean promotion. Updated solutions doc and AGENTS.md
promotion checklist to include removing the field.
New issue-intelligence-analyst agent that fetches GitHub issues via
gh CLI, clusters by root-cause themes, and returns structured analysis
with trend direction, confidence scores, and source mix. Designed for
both ce:ideate integration and standalone use.
Agent design:
- Priority-aware fetching with label scanning for focus targeting
- Truncated bodies (500 chars) in initial fetch to avoid N+1 calls
- Single gh call per fetch, no pipes or scripts (avoids permission spam)
- Built-in --jq for all field extraction and filtering
- Mandatory structured output with self-check checklist
- Accurate counts from actual data, not assumptions
- Closed issues as recurrence signal only, not standalone evidence
ce:ideate gains:
- Issue-tracker intent detection in Phase 0.2
- Conditional agent dispatch in Phase 1 (parallel with existing scans)
- Dynamic frame derivation from issue clusters in Phase 2
- Hybrid strategy: cluster-derived frames + default padding when < 4
- Resume awareness distinguishing issue vs non-issue ideation
- Numbered table format for rejection summary in ideation artifacts
Trevin Chow
Harold Hunt