@drafthq/draft 2.7.0

package/skills/graph/SKILL.md

@@ -0,0 +1,107 @@
+---
+name: graph
+description: Initialize or refresh the knowledge-graph snapshot for a repository. Ensures the codebase-memory-mcp engine is present (fetching it if needed), then builds draft/graph/ and reports engine, counts, hotspots, and cycles. Accepts an optional repo path.
+---
+
+# Draft Graph
+
+Initialize or refresh the `draft/graph/` knowledge-graph snapshot for a repository. This is the narrow "give me a fresh structural graph" command — it does **not** generate `architecture.md`/`.ai-context.md` (that is `/draft:init`) and does **not** re-inject doc diagram slots (that is `/draft:index`).
+
+## Red Flags - STOP if you're:
+
+- Reporting counts without actually running `graph-snapshot.sh`
+- Claiming the graph is built when the engine was unavailable
+- Treating an engine-unavailable result as a hard failure (it degrades gracefully)
+- Running against a path that isn't a directory
+
+**Build, then report what the tools actually returned.**
+
+---
+
+## Step 1: Resolve the target repo
+
+The command takes an optional path argument: `/draft:graph [path]`.
+
+- No argument → use the current directory (`.`).
+- With a path → use it as the repo root.
+
+```bash
+REPO="${1:-.}"
+if [ ! -d "$REPO" ]; then
+  echo "ERROR: '$REPO' is not a directory."
+  exit 1
+fi
+REPO_ABS="$(cd "$REPO" && pwd)"
+echo "Target repo: $REPO_ABS"
+```
+
+## Step 2: Ensure the engine is present
+
+Resolve the engine; if it is missing, fetch it once, then re-check. If it is still unavailable (e.g. offline, opted out via `DRAFT_MEMORY_DISABLE`), report and stop gracefully — graph features are optional everywhere in Draft.
+
+```bash
+if ! scripts/tools/verify-graph-binary.sh --repo "$REPO_ABS" --json 2>/dev/null | grep -q '"status":"ok"'; then
+  echo "Graph engine not found — attempting to fetch it..."
+  scripts/fetch-memory-engine.sh || true
+fi
+
+ENGINE="$(scripts/tools/verify-graph-binary.sh --repo "$REPO_ABS" --json 2>/dev/null || true)"
+if ! echo "$ENGINE" | grep -q '"status":"ok"'; then
+  echo "Graph engine unavailable — skipping. Install with scripts/fetch-memory-engine.sh, or unset DRAFT_MEMORY_DISABLE."
+  exit 0
+fi
+echo "Engine: $ENGINE"
+```
+
+## Step 3: Build / refresh the snapshot
+
+One call resolves the engine, indexes the repo (incrementally on refresh), and writes the committed snapshot under `<repo>/draft/graph/` — `schema.yaml`, `architecture.json`, `hotspots.jsonl`, `module-deps.mermaid`, `proto-map.mermaid`.
+
+```bash
+scripts/tools/graph-snapshot.sh --repo "$REPO_ABS"
+```
+
+If this exits non-zero, the engine became unavailable mid-run — report it and stop; do not fabricate results.
+
+## Step 4: Report
+
+Summarize what the snapshot contains. Read `draft/graph/schema.yaml` for engine/version/counts, and use the live tools for a quick health view:
+
+```bash
+echo "--- Snapshot ---"
+cat "$REPO_ABS/draft/graph/schema.yaml"
+
+echo "--- Top hotspots ---"
+scripts/tools/hotspot-rank.sh --repo "$REPO_ABS" --top 5
+
+echo "--- Cycles ---"
+scripts/tools/cycle-detect.sh --repo "$REPO_ABS"
+
+echo "--- Snapshot state ---"
+git -C "$REPO_ABS" rev-parse --short HEAD 2>/dev/null \
+  && { git -C "$REPO_ABS" diff --quiet 2>/dev/null || echo "(working tree dirty — snapshot reflects uncommitted changes)"; }
+```
+
+Present a concise summary:
+
+- **Engine**: version + resolution source (path / managed / bundled / override)
+- **Graph**: node and edge counts (from `schema.yaml`)
+- **Top hotspots**: the highest fan-in symbols
+- **Cycles**: count, or `None ✓`
+- **Freshness**: the commit the snapshot reflects, and whether the tree was dirty
+
+Then point the user at the natural next steps:
+
+- To re-inject the refreshed diagrams/hotspot tables into `architecture.md` / `.ai-context.md`: run `/draft:index`.
+- For a first-time full context bootstrap (architecture + profiles): run `/draft:init`.
+
+## Graceful Degradation
+
+| Scenario | Behavior |
+|----------|----------|
+| Engine resolvable | Build snapshot, report counts/hotspots/cycles |
+| Engine missing, fetch succeeds | Build proceeds after fetch |
+| Engine missing, fetch fails / `DRAFT_MEMORY_DISABLE=1` | Report unavailable and exit 0 — no error, no partial snapshot |
+| Path not a directory | Exit 1 with a clear message |
+
+See `core/shared/graph-query.md` and `bin/README.md` for the query contract and engine resolution.

package/skills/impact/SKILL.md

@@ -0,0 +1,86 @@
+---
+name: impact
+description: Generate a project-wide impact report on Draft track delivery — pace, phase duration, completion rate, friction hotspots, ADR/guardrail/decomposition adoption — by parsing track metadata, git revert history, and phase timestamps. Use when measuring CDD effectiveness ("show project impact", "where are bottlenecks", "measure track delivery").
+---
+
+# Draft Impact: Track Telemetry & Analytics
+
+Generate a project-wide impact report measuring Context-Driven Development effectiveness across all tracks.
+
+## Red Flags - STOP if you're:
+- Profiling code coverage instead of measuring track-level impact.
+- Rewriting tracker logic when local state objects are available for inspection.
+- Generating reports without reading existing track metadata first.
+
+---
+
+## Execution Constraints
+
+1. **Load Track State:**
+   - Read all `draft/tracks.md` entries.
+   - For each track, read `metadata.json` to extract: `created_at`, `updated`, `status`, phase counts, task counts, `scope_includes`, `scope_excludes`.
+   - If no tracks exist, report "No tracks found. Run `/draft:new-track` to create your first track."
+   - Run `scripts/tools/check-scope-conflicts.sh` to surface adjacent
+     tracks sharing scope tags — duplicate effort signals in impact
+     reporting. Schema:
+     [core/shared/template-contract.md](../../core/shared/template-contract.md).
+
+2. **Compute Metrics:**
+   - **Delivery Pace:** Average elapsed time from track creation to completion (planning → implementation → review).
+   - **Phase Duration:** Time spent in each phase (planning, implementation, review). Flag any phase exceeding 14 days without updates.
+   - **Completion Rate:** Ratio of completed tracks to total tracks.
+   - **Task Granularity:** Average tasks per track. Flag tracks with fewer than 3 tasks (under-decomposed) or more than 30 (over-decomposed).
+
+3. **Friction Detection:**
+   - Scan `git log` for revert commits associated with each track.
+   - High revert count (>2 per track) signals unclear specification boundaries.
+   - Flag tracks that moved backward (e.g., from implementation back to planning).
+
+4. **Architectural Impact:**
+   - Count ADRs created (`draft/adrs/`).
+   - Count guardrail entries added via `/draft:learn`.
+   - Count modules decomposed via `/draft:decompose`.
+
+5. **Report Output:**
+   Generate a Markdown report with sections shown below. The shape is fixed so reports diff cleanly across runs.
+
+   ```markdown
+   # Draft Impact Report — {YYYY-MM-DD}
+
+   ## Summary
+   - Total tracks: 12   (Completed: 7, In-progress: 3, Abandoned: 2)
+
+   ## Delivery Pace
+   - Average track duration: 8.4 days   |   Median: 6 days
+   - Phases exceeding 14d without update: <list track IDs or "none">
+
+   ## Friction Hotspots
+   | Track | Reverts | Stall (days) | Notes |
+   |---|---|---|---|
+   | track-042 | 3 | 9 | Reverted after review; spec scope unclear |
+
+   ## CDD Adoption
+   - ADRs: 4   |   Guardrail entries: 11   |   Decomposed modules: 6
+
+   ## Recommendations
+   - <one actionable suggestion per detected pattern>
+   ```
+
+---
+
+## Report Closing: Next Actions (REQUIRED)
+
+Every impact/telemetry report must end with a `## Next Actions` section listing the smallest set of follow-ups in execution order. Use this exact shape:
+
+```markdown
+## Next Actions
+
+| # | Action | Owner | Blocker? | Skill / Command |
+|---|---|---|---|---|
+| 1 | <imperative one-liner> | <team-lead|TBD> | no | `/draft:<skill> <args>` or `n/a` |
+```
+
+Rules:
+- Impact reports are advisory — `Blocker? = no` is the default; mark `yes` only when a metric breach demands immediate process change.
+- Suggest `/draft:tech-debt` for systemic friction, `/draft:adr` for methodology adjustments, `/draft:tour` for onboarding gaps.
+- Cap at 7 actions.