docs(references): daily intelligence update 2026-04-18

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "aw-author",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "description": "Guided authoring, validation, and refinement of GitHub Agentic Workflow (gh-aw) markdown files. Includes fully autonomous daily intelligence pipeline (research, gap analysis, implementation, PR to develop), ecosystem monitoring, knowledge base management, and GitHub Discussions integration.",
   "author": {
     "name": "Robert Allen",

.claude/commands/aw-daily.md

@@ -1,34 +1,43 @@
 ---
-name: aw-daily
-description: >
-  Fully autonomous daily pipeline: research, discussion posting, gap analysis,
-  implementation, and PR to develop. Designed for unattended execution.
-  Use with: /aw-daily [--dry-run] [--skip-research] [--skip-implementation] [--no-merge]
-tools:
-  - WebSearch
-  - WebFetch
-  - Write
-  - Edit
-  - Bash
-  - Read
+description: Fully autonomous daily intelligence, gap analysis, implementation, and PR cycle
+argument-hint: "[--dry-run] [--skip-research] [--skip-implementation] [--no-merge]"
 ---
 
-Run the `aw-daily` skill to execute the full daily intelligence and update pipeline.
+# /aw-daily
+
+Fully autonomous daily pipeline: research the gh-aw ecosystem, post to Discussions, analyze gaps in reference files, implement fixes, create PR to `develop`, review, and merge. Designed for unattended execution.
+
+## Usage
+
+```
+/aw-daily                        → Full autonomous cycle
+/aw-daily --dry-run              → Research + gap analysis only, show diff, no commit
+/aw-daily --skip-research        → Start at gap analysis using latest report
+/aw-daily --skip-implementation  → Research + gap analysis + issues only, no file edits
+/aw-daily --no-merge             → Create PR but do not auto-merge
+```
 
 ## Flags
 
-Parse the argument string for these optional flags:
+- `--dry-run` — Run research and gap analysis, show what would change, do not commit or create PR
+- `--skip-research` — Skip intelligence sweep, start at gap analysis using the most recent report in `outputs/gh-aw-reports/`
+- `--skip-implementation` — Run research, gap analysis, and issue creation, but do not edit files or create PR
+- `--no-merge` — Create PR but do not auto-merge to `develop`
+
+## Workflow
 
-- `--dry-run` — Research + gap analysis only, show diff, no commit/PR
-- `--skip-research` — Start at gap analysis using latest report
-- `--skip-implementation` — Research + gap analysis + issues, no file edits/PR
-- `--no-merge` — Create PR but do not auto-merge
+You are an autonomous operations agent performing the daily intelligence and update cycle. Execute all phases without user prompting.
 
-## Steps
+**Do not prompt the user for input at any point.** This command is designed for scheduled unattended execution.
 
-1. Load the aw-daily skill by reading `skills/aw-daily/SKILL.md`.
-2. Follow the skill's 9-phase instructions exactly.
-3. Do not prompt the user for input at any point.
-4. Report the final summary table when complete.
+Load the **aw-daily** skill and execute all phases. The skill handles:
 
-This command is designed for scheduled unattended execution.
+1. Pre-flight checks and idempotency
+2. Intelligence sweep (8 web searches + GitHub activity queries on tracked repos)
+3. Knowledge base update
+4. Discussion posting to `project-news` category
+5. Gap analysis against reference files
+6. Issue creation for identified gaps
+7. Implementation on feature branch from `develop`
+8. PR creation to `develop`
+9. Review and auto-merge

.claude/commands/aw-merge.md

@@ -1,20 +1,99 @@
 ---
-name: aw-merge
-description: >
-  Weekly develop-to-main merge with PR, CI check, and squash merge.
-  Use with: /aw-merge [--dry-run] [--no-reset]
-tools:
-  - Bash
-  - Read
+description: Merge develop branch to main with PR, CI check, and squash merge
+argument-hint: "[--dry-run] [--no-reset]"
 ---
 
-Merge `develop` into `main` via PR.
+# /aw-merge
 
-1. Check if `develop` is ahead of `main`
-2. If so, create a PR from `develop` to `main`
-3. Wait for CI checks (max 5 minutes)
-4. Squash merge
-5. Unless `--no-reset`, reset `develop` to new `main` HEAD
+Weekly merge of `develop` into `main`. Creates a PR, waits for CI, squash merges, and resets `develop` to the new `main` HEAD.
 
-If `develop` is not ahead of `main`, report "Nothing to merge" and exit.
-If `--dry-run`, show what would be merged but take no action.
+## Usage
+
+```
+/aw-merge               → Full merge cycle
+/aw-merge --dry-run     → Show what would be merged, do not create PR
+/aw-merge --no-reset    → Merge but do not reset develop to main after
+```
+
+## Flags
+
+- `--dry-run` — Show commits on `develop` ahead of `main`, do not create PR or merge
+- `--no-reset` — After merge, do not reset `develop` to `main` HEAD (preserves divergent history)
+
+## Workflow
+
+You are an autonomous operations agent performing the weekly develop-to-main merge.
+
+**Do not prompt the user for input at any point.**
+
+### Phase 1: Check divergence
+
+```bash
+git fetch origin main develop
+AHEAD=$(git rev-list --count origin/main..origin/develop)
+```
+
+If `AHEAD` is 0: report "develop is up to date with main. Nothing to merge." and **exit**.
+
+If `--dry-run`: show `git log --oneline origin/main..origin/develop` and **exit**.
+
+### Phase 2: Create PR
+
+```bash
+gh pr create \
+  --draft \
+  --repo zircote/github-agentic-workflows \
+  --base main \
+  --head develop \
+  --title "chore: weekly develop merge $(date +%Y-%m-%d)" \
+  --body "## Summary
+
+Weekly merge of \`develop\` into \`main\`.
+
+**Commits:** $AHEAD commits since last merge.
+
+\`\`\`
+$(git log --oneline origin/main..origin/develop)
+\`\`\`
+
+---
+_Automated by /aw-merge_"
+```
+
+Mark PR ready:
+```bash
+gh pr ready <PR_NUMBER>
+```
+
+### Phase 3: CI and merge
+
+1. Wait for CI checks: poll `gh pr checks` every 15 seconds, max 5 minutes
+2. If CI passes (or no checks configured): squash merge
+```bash
+gh pr merge --squash --auto --delete-branch=false
+```
+3. If CI fails: leave PR open, report URL
+
+### Phase 4: Reset develop (unless `--no-reset`)
+
+After successful merge, reset `develop` to match `main`:
+```bash
+git checkout develop
+git reset --hard origin/main
+git push --force-with-lease origin develop
+git checkout main
+git pull
+```
+
+### Final Report
+
+```
+┌──────────────────────────────────────────┐
+│ /aw-merge complete                       │
+├──────────────────────────────────────────┤
+│ Commits merged:  N                       │
+│ PR:              URL                     │
+│ Merged:          yes/no                  │
+│ develop reset:   yes/no/skipped          │
+└──────────────────────────────────────────┘
+```

.claude/commands/aw-report.md

@@ -1,37 +1,53 @@
 ---
-name: aw-report
-description: >
-  Generate today's GitHub Agentic Workflows intelligence report. Searches the web
-  for the latest news, features, breaking changes, and community activity across
-  the gh-aw ecosystem, then produces and saves a structured Markdown report and
-  posts it to GitHub Discussions for historical record.
-  Use with: /aw-report [--deep] [--no-post] [--domains domain1,domain2]
-tools:
-  - WebSearch
-  - WebFetch
-  - Write
-  - Bash
-  - Read
+description: Run a full gh-aw ecosystem intelligence sweep and produce a dated report
+argument-hint: "[--deep] [--no-post] [--domains domain1,domain2]"
 ---
 
-Run the `gh-aw-report` skill to produce today's GitHub Agentic Workflows intelligence report.
+# /aw-report
 
-## Flags
+Runs a full intelligence sweep across the GitHub Agentic Workflows ecosystem — 8+ web searches — and produces a dated Markdown report saved to `outputs/gh-aw-reports/YYYY-MM-DD.md`. Updates the persistent knowledge base and posts to GitHub Discussions.
+
+## Usage
 
-Parse the argument string for these optional flags:
+```
+/aw-report                     → Full sweep, all domains, post to Discussions
+/aw-report --deep              → Extended sweep with deep-dive queries
+/aw-report --no-post           → Generate report without posting to Discussions
+/aw-report --domains gh-aw,mcp → Only sweep specified domains
+```
+
+## Flags
 
 - `--deep` — Run additional deep-dive queries from the extended query library beyond the 8 primary searches
 - `--no-post` — Skip posting to GitHub Discussions (still saves report locally and updates knowledge base)
-- `--domains` — Comma-separated list of domains to sweep. Valid: `gh-aw`, `actions`, `workspace`, `agent-mode`, `models`, `mcp-server`, `claude-code`, `community`
+- `--domains` — Comma-separated list of domains to sweep. Valid domains: `gh-aw`, `actions`, `workspace`, `agent-mode`, `models`, `mcp-server`, `claude-code`, `community`
+
+## Workflow
+
+You are an intelligence analyst for the gh-aw ecosystem. Load the **gh-aw-report** skill to execute the full intelligence cycle:
+
+1. Load context from the knowledge base and architecture reference
+2. Execute the primary sweep (8 targeted web searches)
+3. If `--deep` is passed, run additional deep-dive queries
+4. If `--domains` is passed, filter to only the specified domains
+5. Synthesize findings into a structured report
+6. Save the report to `outputs/gh-aw-reports/YYYY-MM-DD.md`
+7. Update the knowledge base with stable facts
+8. Unless `--no-post`, post the report to GitHub Discussions in the `project-news` category at `zircote/github-agentic-workflows`
+9. Print the final summary
+
+## Examples
+
+```
+/aw-report
+# → Full sweep, saves report, updates KB, posts to Discussions
 
-## Steps
+/aw-report --deep
+# → Extended sweep with deep-dive queries on rich domains
 
-1. Load the gh-aw-report skill by reading `skills/gh-aw-report/SKILL.md`.
-2. Follow the skill's instructions exactly — perform all 8 required web searches (or filtered if `--domains` specified), synthesize findings, and produce the full structured report.
-3. If `--deep` is passed, run additional deep-dive queries from `skills/gh-aw-report/references/search-queries.md`.
-4. Save the report to `outputs/gh-aw-reports/YYYY-MM-DD.md` (today's date).
-5. Update the knowledge base at `skills/gh-aw-report/knowledge-base.md`.
-6. Unless `--no-post`, post the report to GitHub Discussions in the `Project News` category at `zircote/github-agentic-workflows` using the GraphQL API (see skill Phase 6).
-7. Present the saved report link, discussion URL, and a 3-sentence summary of the most important findings.
+/aw-report --no-post --domains gh-aw,mcp-server
+# → Only sweep gh-aw core and MCP server, skip Discussions post
 
-Do not produce placeholder content. Every section must reflect real search results from today's run.
+/aw-report --deep --domains claude-code
+# → Deep dive on Claude Code × GitHub integrations only
+```

.claude/commands/aw-status.md

@@ -1,32 +1,60 @@
 ---
-name: aw-status
-description: >
-  Summarize the current state of the GitHub Agentic Workflows ecosystem from the
-  persistent knowledge base. Provides a quick briefing without running new web
-  searches. Use with: /aw-status [--domain domain] [--since YYYY-MM-DD]
-tools:
-  - Read
+description: Quick briefing on current gh-aw ecosystem state from the knowledge base
+argument-hint: "[--domain domain] [--since YYYY-MM-DD]"
 ---
 
-Read the knowledge base at `skills/gh-aw-report/knowledge-base.md`
-and provide a concise status briefing covering:
+# /aw-status
 
-## Flags
+Reads the persistent knowledge base and delivers a quick 300–400 word briefing on the current state of the gh-aw ecosystem. No web searches needed — this is a fast, offline status check.
+
+## Usage
+
+```
+/aw-status                      → Full briefing across all domains
+/aw-status --domain gh-aw       → Briefing focused on a specific domain
+/aw-status --since 2026-04-01   → Only entries since the given date
+```
 
-Parse the argument string for these optional flags:
+## Flags
 
 - `--domain` — Focus the briefing on a specific domain: `gh-aw`, `actions`, `workspace`, `agent-mode`, `models`, `mcp-server`, `claude-code`, `community`
 - `--since` — Only include knowledge base entries from this date forward
 
-## Briefing Format
+## Workflow
+
+You are a briefing analyst. Deliver a concise status report from the knowledge base.
+
+1. Read the knowledge base at `skills/gh-aw-report/knowledge-base.md`
+2. Read `skills/gh-aw-report/references/gh-aw-architecture.md` for architecture context
+3. If `--domain` is passed, filter entries to the specified domain
+4. If `--since` is passed, filter entries to those dated on or after the given date
+5. Synthesize a 300–400 word briefing covering:
+
+### Briefing Format
+
+```
+## gh-aw Ecosystem Status — YYYY-MM-DD
+
+### Current Versions
+- gh-aw CLI: vX.Y.Z
+- GitHub MCP Server: vX.Y.Z
+- [other tracked versions]
+
+### Active Deprecations
+- [deprecation with timeline and migration path]
+
+### Recent Changes (last 7 days)
+- [notable changes from knowledge base]
+
+### Recommended Actions
+- [specific actions for workflow maintainers]
+```
 
-1. **Current versions & GA status** — gh-aw CLI, Copilot CLI, Copilot Workspace, GitHub MCP Server
-2. **Active deprecations & breaking changes** — what needs migration now
-3. **Key architectural facts** — how the system works (safe outputs, AWF, MCP Gateway, etc.)
-4. **Last report date** — when the knowledge base was last updated
-5. **Recommended immediate actions** — top 2–3 things a practitioner should do right now
+6. If the knowledge base is empty or has no recent entries, report that and recommend running `/aw-report` to populate it.
 
-Keep the briefing to 300–400 words. If the knowledge base has not been updated in more
-than 3 days, note this and recommend running `/aw-report` to refresh.
+## Notes
 
-Entries marked `[SUPERSEDED]` should be excluded from the briefing.
+- This command does NOT perform web searches — it reads only from the knowledge base
+- For fresh intelligence, run `/aw-report` first
+- The knowledge base is updated by each `/aw-report` run
+- Entries marked `[SUPERSEDED]` are excluded from the briefing