@codyswann/lisa 2.119.1 → 2.121.1

package/plugins/lisa-agy/skills/github-add-journey/SKILL.md

@@ -0,0 +1,115 @@
+---
+name: github-add-journey
+description: "Add a Validation Journey section to an existing GitHub Issue by analyzing the change type and generating appropriate verification steps with evidence markers. The GitHub counterpart of lisa:jira-add-journey."
+allowed-tools: ["Bash", "Skill"]
+---
+
+# Add Validation Journey to Existing GitHub Issue
+
+Read an existing GitHub Issue, analyze the change type, and append a `## Validation Journey` markdown section with appropriate verification steps based on the project's verification patterns.
+
+## Arguments
+
+`$ARGUMENTS`: `<ISSUE_REF>`
+
+- `ISSUE_REF` (required): GitHub issue ref — `org/repo#<number>` or full GitHub issue URL.
+
+## Prerequisites
+
+- `gh` CLI authenticated (`gh auth status`).
+
+## Workflow
+
+### Step 1: Read the Issue
+
+```bash
+gh issue view <number> --repo <org>/<repo> --json number,title,body,labels,assignees,milestone,url
+```
+
+Extract: title, body, type (from `type:` label), components (from `component:` labels), assignees, linked PRs.
+
+### Step 2: Check for Existing Journey
+
+Parse the body for an existing `## Validation Journey` heading. If present and the section contains at least one `[EVIDENCE: <name>]` marker, the issue already has a journey — report this to the user and stop.
+
+### Step 3: Analyze the Change Type
+
+Examine the body, acceptance criteria, and codebase to determine the change type:
+
+1. **API/GraphQL changes** — New or modified endpoints, request/response schemas
+2. **Database migration** — Schema changes, new tables/columns, indexes
+3. **Background job/queue** — New job processors, queue consumers, event handlers
+4. **Library/utility** — Exported functions, shared modules, npm package changes
+5. **Security fix** — Auth, authorization, input validation, OWASP vulnerabilities
+6. **Authentication/authorization** — Role-based access, session management, tokens
+
+Use Explore agents or read the codebase directly to understand which files are affected.
+
+### Step 4: Map Change Type to Verification Pattern
+
+| Change Type | Verification Approach |
+|---|---|
+| API/GraphQL | curl commands verifying endpoints, status codes, response schemas |
+| Database migration | Migration execution + schema verification + rollback check |
+| Background job/queue | Enqueue + process + state change verification |
+| Library/utility | Test execution + build verification + export check |
+| Security fix | Exploit reproduction pre-fix + exploit failure post-fix |
+| Auth/authz | Multi-role verification with explicit status codes |
+
+### Step 5: Draft the Validation Journey
+
+Compose the journey with `[EVIDENCE: name]` markers at key verification points:
+
+```markdown
+## Validation Journey
+
+### Prerequisites
+- List required services, database, env vars
+
+### Steps
+1. Verify current state before changes
+2. Apply the change
+3. Verify expected new state [EVIDENCE: state-name]
+4. Test error/edge cases [EVIDENCE: error-case]
+5. Verify rollback if applicable [EVIDENCE: rollback]
+
+### Assertions
+- Describe what must be true after verification
+```
+
+### Guidelines for Drafting
+
+1. **2–5 evidence markers** — Focus on proving the change works and handles errors.
+2. **Concrete, runnable steps** — `Run \`curl -s localhost:3000/health | jq .status\`` not "Check the endpoint".
+3. **Include environment setup** — Database connection, running services, env vars.
+4. **Evidence names in kebab-case** — `api-response`, `schema-check`, `rate-limit-hit`.
+5. **Assertions are measurable** — `Returns 200 with {status: ok}` not "API works correctly".
+6. **Cover happy path AND error path** — At minimum, one success and one failure marker.
+7. **On a leaf work unit, the markers are binding** — For a Bug / Task / Sub-task / Improvement, every `[EVIDENCE: name]` here is the issue's evidence manifest: validation gate S14 requires at least one, and the issue cannot be closed until each named artifact is captured and attached (see the "Per-Work-Unit Evidence Contract" in the `verification` rule). Name only evidence you intend to capture — and name all of it.
+
+### Step 6: Present to User for Approval
+
+Display the drafted Validation Journey and ask for confirmation before appending it to the issue body. (If invoked from a parent skill running unattended — e.g., `lisa:github-write-issue` Phase 6 step 5 — proceed without the prompt.)
+
+### Step 7: Append to Issue Body
+
+After approval:
+
+```bash
+current_body=$(gh issue view <number> --repo <org>/<repo> --json body --jq '.body')
+# Compose new body: existing + "\n\n## Validation Journey\n..." (or replace if present)
+gh issue edit <number> --repo <org>/<repo> --body-file /tmp/updated-body.md
+```
+
+Preserve every other section verbatim — never re-render the body from parsed fields, since the issue may carry `extra_sections` we don't recognize.
+
+### Step 8: Verify
+
+Re-read the issue and confirm the `## Validation Journey` section is present and includes at least one `[EVIDENCE: <name>]` marker.
+
+## When to Use This Skill
+
+- Issue was created before the Validation Journey convention was established.
+- Issue was created manually without following `lisa:github-create` guidelines.
+- Issue needs a journey added or updated based on implementation progress.
+- Before starting work on an issue, to ensure verification steps are documented.

package/plugins/lisa-agy/skills/github-build-intake/SKILL.md

@@ -0,0 +1,377 @@
+---
+name: github-build-intake
+description: "GitHub counterpart to lisa:jira-build-intake. Scans a GitHub repository for issues carrying the configured `ready` build label, processes the first eligible issue, runs leaf work via lisa:github-agent, relabels to the configured `done` label on completion, then exits. Enforces the claim-time arm of the `leaf-only-lifecycle` rule: a parent/container with open child work (or a childless Epic/Story/Spike) that still carries a stale build-ready label is moved out of the ready pickup queue into the configured `claimed` label with a lifecycle-repair comment, never dispatched to lisa:github-agent. The `ready` label is the human-flipped signal that an issue is truly ready for direct development pickup — mirroring how Notion PRDs work product Draft → Ready → (us) In Review → Blocked|Ticketed."
+allowed-tools: ["Skill", "Bash"]
+---
+
+# GitHub Build Intake: $ARGUMENTS
+
+`$ARGUMENTS` is one of:
+
+1. A GitHub `org/repo` token (e.g., `acme/frontend-v2`).
+2. A full GitHub repo URL (e.g., `https://github.com/acme/frontend-v2`).
+3. The literal token `github` — falls back to `.lisa.config.json` (`github.org` / `github.repo`).
+
+Run one build-intake cycle. The first eligible issue in the configured `ready` build label is claimed, built via the `lisa:github-agent` flow, relabeled to the configured `done` label (env-aware — see Workflow resolution), then the cycle exits. Remaining ready issues stay queued for later scheduler invocations.
+
+This skill also accepts an optional `assignee=<github-login>` queue filter. Resolve it in this
+order:
+
+1. `$ARGUMENTS` `assignee=<login>`
+2. `.lisa.config.local.json` `intake.assignee`
+3. empty default
+
+When the resolved assignee is empty, scan the shared ready queue exactly as before. When it is
+non-empty, filter the ready-item query to issues already assigned to that login. This filter is
+selection-only: never assign or reassign issues as part of build intake.
+
+## Workflow resolution
+
+Build-queue label names are read from `.lisa.config.json` `github.labels.build.*`, falling back to defaults documented in the `config-resolution` rule. Bash pattern:
+
+```bash
+# Read role with default fallback. Local overrides global per-key.
+read_role() {
+  local role="$1" default="$2"
+  local local_v global_v
+  local_v=$(jq -r ".github.labels.build.${role} // empty" .lisa.config.local.json 2>/dev/null)
+  global_v=$(jq -r ".github.labels.build.${role} // empty" .lisa.config.json 2>/dev/null)
+  echo "${local_v:-${global_v:-$default}}"
+}
+
+READY=$(read_role ready "status:ready")
+CLAIMED=$(read_role claimed "status:in-progress")
+
+read_intake_assignee() {
+  local cli_value local_v
+  cli_value=$(printf '%s\n' "$ARGUMENTS" | sed -n 's/.*assignee=\([^[:space:]]*\).*/\1/p' | head -1)
+  local_v=$(jq -r '.intake.assignee // empty' .lisa.config.local.json 2>/dev/null)
+  echo "${cli_value:-${local_v:-}}"
+}
+
+ASSIGNEE=$(read_intake_assignee)
+```
+
+For env-keyed `done`, resolve the env first, then look up `done[<env>]`:
+
+1. Explicit caller arg (`target_env=staging`) wins.
+2. Otherwise, infer the env from the PR's base branch via `deploy.branches` (reverse lookup).
+3. If `done` is a **string** in config, use it directly regardless of env.
+4. If `done` is a **map** and env cannot be resolved, **fail loudly** — do not pick arbitrarily.
+
+```bash
+TARGET_ENV="${target_env:-}"
+if [ -z "$TARGET_ENV" ] && [ -n "$PR_BASE_BRANCH" ]; then
+  TARGET_ENV=$(jq -r --arg b "$PR_BASE_BRANCH" \
+    '.deploy.branches // {} | to_entries[] | select(.value == $b) | .key' \
+    .lisa.config.json 2>/dev/null | head -1)
+fi
+
+DONE_TYPE=$(jq -r '.github.labels.build.done | type' .lisa.config.json 2>/dev/null)
+if [ "$DONE_TYPE" = "string" ]; then
+  DONE=$(jq -r '.github.labels.build.done' .lisa.config.json)
+  DONE_LABELS_JSON=$(jq -c '[.github.labels.build.done]' .lisa.config.json)
+elif [ "$DONE_TYPE" = "object" ]; then
+  [ -z "$TARGET_ENV" ] && { echo "ERROR: github.labels.build.done is env-keyed but env not resolvable"; exit 1; }
+  DONE=$(jq -r --arg e "$TARGET_ENV" '.github.labels.build.done[$e] // empty' .lisa.config.json)
+  [ -z "$DONE" ] && { echo "ERROR: github.labels.build.done has no entry for env '$TARGET_ENV'"; exit 1; }
+  DONE_LABELS_JSON=$(jq -c '[.github.labels.build.done[]]' .lisa.config.json)
+else
+  case "$TARGET_ENV" in
+    dev) DONE="status:on-dev" ;;
+    staging) DONE="status:on-stg" ;;
+    production) DONE="status:done" ;;
+    *) echo "ERROR: cannot resolve done label without env"; exit 1 ;;
+  esac
+  DONE_LABELS_JSON=$(jq -cn --arg d "$DONE" '[$d]')
+fi
+```
+
+In prose below, the role names refer to the resolved labels: e.g. "the `ready` label" means whatever `github.labels.build.ready` resolves to (default: `status:ready`).
+
+## Confirmation policy
+
+Do NOT ask the caller whether to proceed. Once invoked with a repo, run the cycle to completion — claim and dispatch the first eligible issue through `lisa:github-agent`, relabel a successful build to `$DONE`, write the summary, and exit. The caller (a human or a cron) has already authorized the run by invoking the skill; re-prompting defeats the purpose of a background queue.
+
+Specifically forbidden:
+
+- Previewing projected scope (issue count, projected PR count, build duration) and asking whether to continue.
+- Offering A/B/C-style choices like "proceed / skip a few / dry-run only".
+- Pausing because the queue is large, issues look complex, or issues are likely to be `Blocked` by `lisa:github-agent`'s pre-flight gate. Pre-flight `Blocked` is a valid terminal state of the per-issue lifecycle, not a failure mode.
+- Pausing because the build flow looks expensive.
+
+The only legitimate reasons to stop early:
+
+- Missing repo or required configuration. Surface the missing value and exit.
+- Label namespace not adopted (no issue carries any of `$READY` / `$CLAIMED` / `$DONE`). Surface a label-convention error and exit (this is setup, not a normal idle cycle — see "Adoption" at the bottom).
+- Empty ready set. Exit cleanly with `"No GitHub issues labeled $READY in <org>/<repo>. Nothing to do."`
+
+## Lifecycle assumed
+
+The GitHub Issues build lifecycle uses **labels** (we deliberately do NOT key off open/closed alone — closed issues aren't always the right post-build state):
+
+```text
+ready → claimed → done(env-keyed)
+(human)  (us claim)  (us done; PR ready)
+```
+
+(Defaults: `status:ready` / `status:in-progress` / `status:on-dev`/`status:on-stg`/`status:done`.)
+
+This skill ONLY transitions:
+
+- `$READY` → `$CLAIMED` (claim)
+- `$CLAIMED` → `$DONE` (build complete, PR ready)
+
+A "transition" means: remove the old role label and add the new one, in two `gh issue edit` calls (`--remove-label` + `--add-label`) or one combined call. The skill MUST verify exactly one build-lifecycle label (from the resolved `$READY`/`$CLAIMED`/`$DONE` set) is present after the update — having two simultaneously breaks idempotency.
+
+**Pre-flight check**: at the start of each cycle, confirm at least one of the resolved role labels (`$READY`, `$CLAIMED`, or any `$DONE` value) exists on the repo via `gh label list --repo <org>/<repo> --json name`. If none exist, the convention has not been adopted — surface the label-convention error and exit.
+
+## Phases
+
+### Phase 1 — Resolve the repo
+
+1. Parse `$ARGUMENTS`:
+   - `org/repo` token → use as-is.
+   - GitHub URL → extract `org` and `repo`.
+   - Literal `github` → resolve from `.lisa.config.json` (`github.org`, `github.repo`); error if not set.
+2. Confirm `gh auth status` succeeds.
+3. Confirm the repo is reachable: `gh repo view <org>/<repo> --json name --jq '.name'`.
+
+### Phase 2 — Find ready issues
+
+```bash
+if [ -n "$ASSIGNEE" ]; then
+  gh issue list --repo <org>/<repo> --label "$READY" --assignee "$ASSIGNEE" --state open \
+    --json number,title,labels,assignees,milestone,createdAt --limit 100
+else
+  gh issue list --repo <org>/<repo> --label "$READY" --state open \
+    --json number,title,labels,assignees,milestone,createdAt --limit 100
+fi
+```
+
+If empty, run a secondary check to distinguish a genuinely empty queue from an unconfigured repo:
+
+```bash
+gh label list --repo <org>/<repo> --json name \
+  | jq -r --arg r "$READY" --arg c "$CLAIMED" --argjson d "$DONE_LABELS_JSON" \
+      '[.[] | .name | select(. == $r or . == $c or (. as $n | $d | index($n)))] | length'
+```
+
+If none of the configured role labels exist on the repo → label convention not adopted, surface a setup error and exit. If the role labels exist but none are `$READY` on any open issue matching the resolved assignee filter (or any open issue when the filter is empty) → genuinely empty queue, exit cleanly with `"No GitHub issues labeled $READY. Nothing to do."`
+
+### Phase 3 — Process the first eligible ready issue
+
+#### 3a.0 Repo-scope gate (claim only current-repo issues)
+
+GitHub Issues live in one repo by definition, so the scanned repo's issues are usually inherently current-repo. But a planning/umbrella repo's issues can target sibling repos, so this skill still claims only issues for the repo it is running in. Run this gate **before** the leaf-only gate (3a) and the claim (3b), per the `repo-scope-split` rule's "Claim-time repo scoping" section (cite it by slug; do not restate its decision table).
+
+1. **Resolve the current repo** per `config-resolution` "Repo scoping" (`.repo` → `.github.repo` → `git remote get-url origin` basename). If unresolvable, stop and report.
+2. **Cheap path first.** Prefer candidates already carrying the `repo:<current>` label. Keep the Phase 2 scan broad so unlabeled issues are still seen, determined, and stamped.
+3. **Per candidate, apply the repo-scope decision (`repo-scope-split`):**
+   - Carries `repo:<other>` → **skip** (leave it `ready` for that repo's own intake); next candidate.
+   - **Unlabeled** → determine the target repo(s) from the issue + code surfaces, then **stamp** `repo:<name>` via `gh issue edit <n> --add-label "repo:<name>"` (create the label lazily) so later cycles filter cheaply; re-apply with the now-known repo. (An issue whose work is entirely in the scanned repo is simply labeled `repo:<current>`.)
+   - **Container visibility is allowed.** A multi-repo Epic / Story / Spike may legitimately carry multiple `repo:<name>` labels for operator visibility. Do not split or claim it here; leave the repo markers intact and fall through to the leaf-only gate, which repairs the stale build-ready label instead of dispatching the container.
+   - **Multi-repo leaf → split, never claim.** Run the `repo-scope-split` work-time procedure into single-repo siblings, each created **build-ready** (`build_ready: true`) and stamped with its own `repo:<name>`; the current repo's sibling becomes a normal candidate.
+   - **Single-repo leaf for the current repo** → fall through to 3a (leaf-only gate) and 3b (claim).
+4. Continue until a claimable current-repo leaf is found (claim it; one per cycle) or the ready set is exhausted — exit cleanly with `"No ready issues for repo <current>. Nothing to do."`.
+
+#### 3a. Leaf-only claim gate (repair containers)
+
+Build intake dispatches **only independently implementable leaf work units** to the build agent. This enforces the claim-time arm of the vendor-neutral `leaf-only-lifecycle` rule: a parent/container that still carries a stale build-ready role (e.g. `status:ready` applied before this rule existed, or hand-applied to an Epic/Story) is **never dispatched** — intake moves it out of the pickup queue by replacing `$READY` with `$CLAIMED`, then posts a clear lifecycle-repair message. It is the claim-time complement to the write-time labeling in `lisa:github-write-issue` and the validate-time S15 gate in `lisa:github-validate-issue`; all three cite the same rule so the classification never drifts. **Never silently implement a container.**
+
+Run this gate **before** the leaf claim relabel, starting with the oldest/highest-priority ready candidate. Do NOT comment "Claimed" or invoke `lisa:github-agent` for an issue that fails the gate. A container repair still changes labels: remove `$READY`, add `$CLAIMED`, explain that parent/container `$CLAIMED` means rollup/build-lane progress through child/leaf work rather than direct implementation, record it, and end the cycle.
+
+**Resolve container vs. leaf — structural first, then nominal.** Per `leaf-only-lifecycle` the classification is structural: an issue is a **container** if it has **open** child work, whatever its declared type; otherwise the **type label** decides. Resolve child work using the same hierarchy `lisa:github-read-issue` uses — native sub-issues first, then body parentage (task-list checkboxes referencing other issues, `Parent: #<n>` references). Dependency links such as `Blocked by:` are not parentage; they are handled by the active dependency hold gate below.
+
+```bash
+# Native sub-issues via GraphQL (same query lisa:github-read-issue uses).
+SUBS=$(gh api graphql -f query='
+query($org:String!,$repo:String!,$number:Int!){
+  repository(owner:$org,name:$repo){
+    issue(number:$number){
+      subIssues(first: 100) {
+        nodes { number state }
+      }
+    }
+  }
+}' -F org=<org> -F repo=<repo> -F number=<number> 2>/dev/null)
+
+# Count children still OPEN — a parent whose children are all closed is no longer
+# holding open work and rolls up via lisa:github-read-issue's rollup, not here.
+OPEN_CHILDREN=$(echo "$SUBS" | jq -r '[.data.repository.issue.subIssues.nodes[]? | select(.state == "OPEN")] | length' 2>/dev/null)
+OPEN_CHILDREN=${OPEN_CHILDREN:-0}
+```
+
+If the GraphQL `subIssues` field is unavailable (older GHES), fall back to parsing the body for child references exactly as `lisa:github-read-issue` does, and treat the issue as a container if any referenced child issue is open. Note "GraphQL sub-issues unavailable" so the operator knows parentage was text-derived.
+
+Classify and act (first match wins). `type:` is read from the issue's labels (`type:Epic`, `type:Story`, `type:Spike`, `type:Bug`, `type:Task`, `type:Sub-task`, `type:Improvement`):
+
+| Condition | Class | Action |
+|---|---|---|
+| `OPEN_CHILDREN > 0` (open child work, any type) | **Container** | **Move to `$CLAIMED` as lifecycle repair — do NOT dispatch** |
+| no open children AND `type ∈ {Epic, Story, Spike}` | **Childless container-type** | **Move to `$CLAIMED` as lifecycle repair — do NOT dispatch** |
+| no open children AND `type ∈ {Bug, Task, Sub-task, Improvement}` (or no `type:` label) | **Leaf work unit** | **Proceed to 3b claim** |
+
+The childless-parent exception is narrow: childlessness enables direct build-agent dispatch **only** for types that are leaf work units to begin with. A childless Epic/Story/Spike is an incomplete decomposition, not an implementable unit — it is moved out of the ready pickup queue for repair/rollup and never dispatched.
+
+**Lifecycle repair (default action for a flagged container).** Move the issue out of the pickup queue by removing `$READY` and adding `$CLAIMED`, post a single lifecycle-repair comment, and record the issue under "Repaired (container)" in the summary. Do NOT invoke `lisa:github-agent`. Keep the comment idempotent — skip posting if an identical `[claude-build-intake]` lifecycle-repair comment already exists on the issue, so a re-entrant cycle doesn't spam it.
+
+```bash
+gh issue edit <number> --repo <org>/<repo> --remove-label "$READY" --add-label "$CLAIMED"
+gh issue comment <number> --repo <org>/<repo> --body "[claude-build-intake] Lifecycle repair: this issue carried the build-ready role ($READY) but is a parent/container with open child work (or a childless Epic/Story/Spike). I moved it to $CLAIMED without invoking the build agent. For parent/container issues, $CLAIMED means rollup/build-lane progress through child/leaf work; direct implementation must happen on leaf issues. Build-ready is leaf-only per leaf-only-lifecycle — move $READY onto its leaf children, or decompose/reclassify a childless Epic/Story/Spike."
+```
+
+This gate never blocks a legitimate flat Task/Bug: those have no open children and a leaf `type:`, so they fall straight through to the claim in 3b.
+
+**Active dependency hold gate.** After the leaf-only gate passes, but still before the claim relabel, parse explicit blocker relationships from the issue body and durable Lisa relationship sections. Support these forms at minimum:
+
+- `Blocked by: #123`
+- `Blocked by: #123, #456`
+- `Blocked by: owner/repo#123`
+- `Blocked by: https://github.com/owner/repo/issues/123`
+
+Resolve local `#123` references against the candidate issue's repo. Resolve qualified refs and GitHub issue URLs against their named repo. For each blocker, read the blocker issue's status labels with `gh issue view <number> --repo <owner>/<repo> --json labels,state`.
+
+Default cleared blocker labels for GitHub build intake are:
+
+- `status:code-review`
+- `status:on-dev`
+- `status:on-stg`
+- `status:done`
+
+A blocker is active if it is open and has no cleared status label. Treat `status:ready`, `status:in-progress`, missing status labels, and inaccessible blockers as active. Closed blockers are cleared. If any blocker is active, skip the candidate without changing lifecycle labels, without posting "Claimed", and without invoking `lisa:github-agent`. Record it under "Skipped (active blockers)" in the summary and include the active blocker refs. Keep any dependency-hold comment idempotent with a `[claude-build-intake]` prefix.
+
+#### 3b. Claim
+
+```bash
+gh issue edit <number> --repo <org>/<repo> --remove-label "$READY" --add-label "$CLAIMED"
+gh issue comment <number> --repo <org>/<repo> --body "[claude-build-intake] Claimed by Claude. Starting build."
+```
+
+This is the idempotency lock — a re-entrant cycle's `--label $READY` filter will not see this issue again.
+
+If the relabel fails (permission, race), log under "Errors" in the cycle summary and skip this issue. **Do not invoke the build flow on an issue you didn't successfully claim.**
+
+#### 3c. Run the build flow
+
+Invoke `lisa:github-agent` (the per-issue lifecycle agent) with the issue ref. `lisa:github-agent` owns:
+- Reading the full issue graph (`lisa:github-read-issue`)
+- Running its own pre-flight quality gate (`lisa:github-verify`)
+- Running issue triage (`lisa:ticket-triage`)
+- Routing to the appropriate flow (Build / Fix / Investigate / Improve based on `type:` label)
+- Posting progress comments via `lisa:github-sync`
+- Posting evidence via `lisa:github-evidence`
+
+Wait for `lisa:github-agent` to return. Capture its outcome:
+
+- **Success** — PR is ready (open or merged); evidence posted; ready for next status.
+- **Blocked by github-verify pre-flight gate** — `lisa:github-agent` itself relabels the issue to `status:blocked` (or removes `$CLAIMED` and reassigns to the original author). This is correct and expected — let it stand. Record and move on.
+- **Blocked by ticket-triage ambiguities** — `lisa:github-agent` posts findings and stops. The issue stays in `$CLAIMED`. Surface to human; do not auto-relabel. Record under "Errors".
+- **Errored** — exception, missing config, etc. Leave the issue in `$CLAIMED` for human investigation. Record under "Errors".
+
+#### 3d. Transition to $DONE (only on Success)
+
+If `lisa:github-agent` returned Success:
+
+1. Resolve `$DONE` for this issue's PR base branch using the Workflow resolution algorithm above. If env can't be resolved and `done` is env-keyed, record an Error and skip this transition — never guess.
+2. Determine whether `$DONE` is the true terminal done value per the `leaf-only-lifecycle` rule's Terminal native closure section:
+   - If `github.labels.build.done` is a string, that string is terminal.
+   - If `github.labels.build.done` is an object, only the production/final environment value is terminal (default: `status:done`). Intermediate env values such as `status:on-dev` and `status:on-stg` are not terminal and must stay open.
+   - If the project uses a different final environment name, resolve it from the configured deployment topology; if ambiguous, record an Error and do not close.
+
+```bash
+gh issue edit <number> --repo <org>/<repo> --remove-label "$CLAIMED" --add-label "$DONE"
+gh issue comment <number> --repo <org>/<repo> --body "[claude-build-intake] Build complete. PR <URL>. Transitioned to $DONE."
+```
+
+If `$DONE` is terminal, immediately close the native GitHub issue:
+
+```bash
+gh issue close <number> --repo <org>/<repo> --reason completed
+```
+
+This close is idempotent: if the issue is already closed, record that native closure was already satisfied and continue. If `$DONE` is an intermediate env state, leave the issue open by design.
+
+For any non-Success outcome, do NOT transition. The issue sits in `$CLAIMED` (or wherever `lisa:github-agent` left it) — humans take it from there.
+
+#### 3e. Stop
+
+Stop immediately after the first claimed, skipped, blocked, held, or errored issue. Later scheduler invocations process the remaining ready issues.
+
+### Phase 4 — Summary report
+
+```text
+## github-build-intake summary
+
+Repo: <org>/<repo>
+Cycle started: <ISO timestamp>
+Cycle completed: <ISO timestamp>
+
+Issues processed: <n>
+- $DONE (build complete, PR ready): <n>
+  - <org>/<repo>#<number> <title> → PR <URL>
+- Repaired (container — leaf-only-lifecycle): <n>
+  - <org>/<repo>#<number> <title> — build-ready on a parent/container; moved $READY → $CLAIMED without invoking lisa:github-agent; lifecycle-repair comment posted
+- Skipped (active blockers): <n>
+  - <org>/<repo>#<number> <title> — waiting on <blocker refs>
+- Blocked (pre-flight verify failed): <n>
+  - <org>/<repo>#<number> <title> — see issue comments
+- Held (triage found ambiguities): <n>
+  - <org>/<repo>#<number> <title> — see issue comments
+- Errors: <n>
+  - <org>/<repo>#<number> <title> — <reason>
+
+Total PRs opened: <n>
+```
+
+## Idempotency & safety
+
+- **Leaf-only claim gate runs first**: Phase 3a classifies each candidate before any leaf claim; a container with open child work (or a childless Epic/Story/Spike) is moved `$READY` → `$CLAIMED` as lifecycle repair and never dispatched. The lifecycle-repair comment is idempotent — a re-entrant cycle does not re-post it.
+- **Dependency hold runs before leaf claim**: explicit `Blocked by:` relationships are resolved after container repair is ruled out but before `$READY → $CLAIMED`; active blockers leave the leaf candidate in `$READY` and are reported as skipped, not blocked.
+- **Claim-first ordering**: `$CLAIMED` set BEFORE `lisa:github-agent` invocation for leaves; containers are also moved to `$CLAIMED` to leave the ready pickup queue, but are not dispatched.
+- **No writes outside the lifecycle**: this skill only relabels `$READY → $CLAIMED` and `$CLAIMED → $DONE`. For containers, `$READY → $CLAIMED` is a lifecycle repair, not a direct build claim. Every other label change is owned by `lisa:github-agent`.
+- **Terminal native closure**: after `$CLAIMED → $DONE`, close the GitHub issue only when `$DONE` is the true terminal done value per `leaf-only-lifecycle`; intermediate env labels stay open.
+- **One item per cycle**: per-issue exceptions are caught and recorded, then the cycle exits. The scheduler owns retrying or moving on to the next ready item.
+- **Single cycle per repo**: do not run two `lisa:github-build-intake` cycles in parallel against the same repo — concurrent claims could race. The scheduling layer is responsible for serialization.
+- **Single-label invariant**: after every transition, verify exactly one `status:*` label is present on the issue. If two are present (rare race), surface as an Error and skip — do NOT auto-resolve.
+- **Never pick an arbitrary env for `$DONE`**. If `done` is a map and env is ambiguous, fail loudly.
+
+## Configuration
+
+| Variable | Default | Purpose |
+|----------|---------|---------|
+| `.lisa.config.json` `github.org` | (from `$ARGUMENTS`) | GitHub org for the default queue |
+| `.lisa.config.json` `github.repo` | (from `$ARGUMENTS`) | GitHub repo for the default queue |
+| `.lisa.config.json` `github.labels.build.ready` | `status:ready` | The label that signals "human says this is buildable" |
+| `.lisa.config.json` `github.labels.build.claimed` | `status:in-progress` | The label set on pickup |
+| `.lisa.config.json` `github.labels.build.done` | env-keyed map or string | The label set after a successful build; env-aware |
+| `.lisa.config.json` `deploy.branches` | — | Reverse-lookup map for env inference from PR base branch |
+
+If the repo has not adopted the `status:*` label namespace, this skill cannot run. The remediation is to create the labels — `gh label create status:ready --color FBCA04 --description "Ready for build"` and similar — typically a one-time setup. See "Adoption" below for the full command set using the defaults; if your project overrides the role names, substitute accordingly.
+
+## Rules
+
+- **Dispatch leaves only.** Per the `leaf-only-lifecycle` rule, never dispatch a container — an issue with open child work, or a childless Epic/Story/Spike — even if it carries the build-ready role. Move it `$READY → $CLAIMED` as lifecycle repair (Phase 3a); never silently implement a container.
+- Never relabel an issue outside the cycle's allowed transitions. The `$CLAIMED` label is the signature of cycle ownership for leaves, and the parent/container progress state for lifecycle repairs.
+- Never bypass `lisa:github-agent` to do build work directly. `lisa:github-agent` owns the per-issue lifecycle.
+- Never auto-transition past `$DONE`. Downstream labels (terminal `status:done`, etc.) are owned by QA / PM / merge automation.
+- Never close a GitHub issue at intermediate env states (`status:on-dev`, `status:on-stg`, or configured equivalents). Native close happens only at the terminal `done` value.
+- If the issue has no Validation Journey or no sign-in credentials, `lisa:github-agent`'s pre-flight verify will catch it — **don't try to fix the issue from here**.
+- On any unexpected response from `lisa:github-agent` (status it doesn't claim, missing PR URL on success), record as Error and surface — never assume.
+- Never pick an arbitrary env for `$DONE` resolution. If `done` is a map and env is ambiguous, fail loudly.
+
+## Adoption (one-time per repo)
+
+Before this skill can run, the repo must adopt the `status:*` label namespace. Using the defaults:
+
+1. Create the labels:
+   ```bash
+   gh label create status:ready --color FBCA04 --description "Ready for build" --repo <org>/<repo>
+   gh label create status:in-progress --color 0E8A16 --description "Build in progress" --repo <org>/<repo>
+   gh label create status:on-dev --color 1D76DB --description "Built, deployed to dev" --repo <org>/<repo>
+   gh label create status:done --color 0E8A16 --description "Shipped" --repo <org>/<repo>
+   ```
+   If your project overrides any `github.labels.build.*` role name in config, substitute the actual label names you configured.
+2. Apply the `$READY` label to issues that are ready for development.
+3. Reserve `$CLAIMED`, `$DONE` for this skill — humans should not set them manually except to recover from an error.
+4. PRD-source labels (defaults: `prd-ready`, `prd-in-review`, etc.) are a SEPARATE namespace owned by `lisa:github-prd-intake`. Don't conflate.

package/plugins/lisa-agy/skills/github-create/SKILL.md

@@ -0,0 +1,101 @@
+---
+name: github-create
+description: This skill should be used when creating GitHub Issue Epics, Stories, and Sub-tasks from code files or descriptions. It analyzes the provided input, determines the appropriate issue hierarchy, and creates issues with comprehensive quality requirements including test-first development and documentation. The GitHub counterpart of lisa:jira-create.
+allowed-tools: ["Read", "Glob", "LS", "Skill", "Bash"]
+---
+
+# Create GitHub Issues from $ARGUMENTS
+
+Analyze the provided file(s) and plan a GitHub Issue hierarchy. **This skill plans structure only — every individual issue write is delegated to `lisa:github-write-issue` (which itself goes through the `lisa:tracker-write` shim when invoked from a vendor-neutral caller).** Do not call `gh issue create` from this skill; the necessary write invocations belong to the writer skill so the gates can never be bypassed.
+
+## Process
+
+1. **Analyze**: Read `$ARGUMENTS` to understand scope.
+2. **Extract source artifacts**: invoke the `lisa:tracker-source-artifacts` skill (vendor-neutral), then enumerate every external URL, embed, attachment, or example payload in the input and classify each by domain per its rules. Build the `artifacts` map (one entry per artifact: url, title, domain, source page, classification reason).
+3. **Walk the live product** (when applicable): if the work touches existing user-facing surfaces, invoke the `lisa:product-walkthrough` skill.
+4. **Determine structure**:
+   - Epic needed if: multiple features, major changes, >3 related files.
+   - Direct Tasks if: bug fix, single file, minor change.
+5. **Plan hierarchy**:
+
+   ```text
+   Epic → Story → Sub-tasks (test, implement, document, cleanup)
+   ```
+
+6. **Delegate every write to `lisa:github-write-issue`** in dependency order (Epic first, then Stories with the Epic as parent sub-issue, then Sub-tasks with their Story as parent). Pass artifacts (filtered by domain per `lisa:tracker-source-artifacts` inheritance rules) and walkthrough findings (under `## Current Product`).
+7. **Run the artifact preservation gate** (`lisa:tracker-source-artifacts` §8): after all writes complete, build the preservation matrix and verify every extracted artifact is reachable from the created issues. Fail loudly if anything was dropped.
+
+## Mandatory for Every Code Issue
+
+**Test-First**: Write tests before implementation
+**Quality Gates**: All tests/checks must pass, no SonarCloud violations
+**Documentation**: Check existing, update/create new, remove obsolete
+**Cleanup**: Remove temporary code, scripts, dev configs
+
+## Validation Journey
+
+Issues that change runtime behavior should include a `## Validation Journey` section. This section is consumed by `lisa:github-journey` to automate verification. Use `lisa:github-add-journey` to draft + append the section after creation.
+
+## Source Artifacts
+
+If `$ARGUMENTS` references any external artifact — PRD, design doc, Figma URL, Lovable prototype, Loom walkthrough, screenshot, example payload — those references MUST be preserved as `## Links` and `## Source Artifacts` sections on the created issues. Silent artifact loss is the single most common quality failure in this pipeline.
+
+**Invoke `lisa:tracker-source-artifacts`** for the canonical rules: domains, per-tool classification, source precedence, conflict handling under `## Open Questions`, inheritance from epic → story → sub-task, and the existing-component reuse expectation. This skill is vendor-neutral and used by both the JIRA and the GitHub paths.
+
+When delegating actual writes to `lisa:github-write-issue`, pass the extracted artifact list so its Phase 4c (Remote Links / Source Artifacts) step attaches them.
+
+## Live Product Walkthrough
+
+When the work touches existing user-facing surfaces, invoke `lisa:product-walkthrough` before drafting issues. The findings become inputs to the issue plan and surface under `## Current Product` on the resulting issues.
+
+## Issue Requirements
+
+Each issue must clearly communicate to:
+
+- **Coding Assistants**: Implementation requirements
+- **Developers**: Technical approach
+- **Stakeholders**: Business value
+
+Default repo: from `.lisa.config.json` `github.org` / `github.repo` (override via arguments).
+
+## Delegation to github-write-issue
+
+**Mandatory.** Every issue created by this skill MUST go through `lisa:github-write-issue`. This skill never calls `gh issue create` itself — that invocation belongs to the writer.
+
+`lisa:github-write-issue` enforces:
+- 3-audience description (Context / Technical Approach / Acceptance Criteria)
+- Gherkin acceptance criteria
+- Parent sub-issue validation (non-bug, non-epic types)
+- Explicit relationship discovery (`Blocks` / `Blocked by` / `Relates to` / `Duplicates` / `Cloned from`)
+- Remote links (PRs, Confluence, dashboards)
+- Single-repo scope check for Bug / Task / Sub-task
+- Sign-in account and target environment recorded in body
+- Post-create verification
+
+### Invocation order
+
+Issues must be created in parent-before-child order:
+
+1. Invoke `lisa:github-write-issue` for the Epic. Capture the returned issue number.
+2. For each Story, invoke `lisa:github-write-issue` with the Epic ref as `parent_ref`. Capture each Story number.
+3. For each Sub-task, invoke `lisa:github-write-issue` with the Story ref as `parent_ref`.
+
+### What to pass to each invocation
+
+For every delegated write, pass:
+- The summary, issue type, repo (org/repo), and priority you decided
+- The body with all sections drafted (Context / Technical Approach / Acceptance Criteria / Out of Scope / etc.)
+- Gherkin acceptance criteria
+- `parent_ref` (Epic ref for Stories; Story ref for Sub-tasks)
+- The artifact list extracted in "Source Artifacts", filtered by domain per the inheritance rules — `lisa:github-write-issue` Phase 4c attaches them
+- For runtime-behavior issues: instruct the writer to call `lisa:github-add-journey` after create
+
+### What this skill is responsible for
+
+- Deciding the *shape* of the hierarchy (what's an Epic vs. Story vs. Sub-task).
+- Drafting the body and acceptance criteria from the input.
+- Extracting and classifying source artifacts.
+- Threading parent refs through subsequent writes.
+- Running the preservation check after all writes complete.
+
+It does not own the actual `gh issue create` call — that's `lisa:github-write-issue`'s job.