bigpowers 2.26.0 → 2.28.0

package/skills-lock.json

@@ -16,6 +16,11 @@
       "sha256": "8192ebe6f66a9f91",
       "path": "audit-code/SKILL.md"
     },
+    "audit-plan": {
+      "description": "Evaluate an incoming project plan against bigpowers principles and conventions, surface gaps, and produce a READY/NOT READY verdict before engagement begins. Use when a new project arrives, when adapting a foreign plan, or before running seed-conventions on an unfamiliar codebase.",
+      "sha256": "3e88b606fc8e886c",
+      "path": "audit-plan/SKILL.md"
+    },
     "build-epic": {
       "description": "Eight-step epic build cycle — reads state.yaml, execution-status.yaml, and one epic capsule; updates status via bp-yaml-set or direct edit. Resume mode runs one step per invocation. Use instead of ad-hoc execute-plan for release work.",
       "sha256": "7a376ef092fde9cc",
@@ -93,7 +98,7 @@
     },
     "elaborate-spec": {
       "description": "Refine a rough idea into a clear, detailed specification through dialogue. Does not produce code. Use when user has a vague idea, wants to think through a feature before planning, or needs to turn \"I want X\" into a concrete spec.",
-      "sha256": "6d60cffd5139347e",
+      "sha256": "9edc17057449444d",
       "path": "elaborate-spec/SKILL.md"
     },
     "enforce-first": {
@@ -103,7 +108,7 @@
     },
     "evolve-skill": {
       "description": "Benchmark-gated skill evolution — consume bigpowers-benchmark report, propose plan-work change, edit skill via craft-skill, re-run benchmark, record ADR. Use when a skill underperforms on benchmark or stocktake finds systemic gap.",
-      "sha256": "3582333ff9b15942",
+      "sha256": "e2d127c4ae0b5af7",
       "path": "evolve-skill/SKILL.md"
     },
     "execute-plan": {
@@ -198,7 +203,7 @@
     },
     "quick-fix": {
       "description": "\"Streamlined fast-path for trivial data-only fixes — no TDD, no branching ceremony. Collapses 6 skills into 2 for changes that are purely data with no logic risk. Aborts with fallback to investigate-bug if guardrails trigger.\"",
-      "sha256": "6b83f22481ff4995",
+      "sha256": "2b9f1cd6557b6256",
       "path": "quick-fix/SKILL.md"
     },
     "release-branch": {
@@ -226,6 +231,11 @@
       "sha256": "c16bbe4854a0d665",
       "path": "respond-review/SKILL.md"
     },
+    "run-benchmark": {
+      "description": "Run skill quality benchmarks from specs/benchmarks/ definitions and write pass@k reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions.",
+      "sha256": "e27f4e682e505b19",
+      "path": "run-benchmark/SKILL.md"
+    },
     "run-evals": {
       "description": "Eval-Driven Development — define capability and regression evals before building; code graders use verify commands, model graders use explicit rubrics; log pass@k. Use before develop-tdd on new features, or when measuring agent capability over runs.",
       "sha256": "b3cd89a7e440c94f",
@@ -233,12 +243,12 @@
     },
     "run-planning": {
       "description": "\"DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only.\"",
-      "sha256": "eb6c9d3c0e26b7fc",
+      "sha256": "a2e7c028e7f817de",
       "path": "run-planning/SKILL.md"
     },
     "scope-work": {
       "description": "\"PLANNING SPINE STEP 1 of 3 — Scope the work: define what is in and out of scope and save as specs/product/SCOPE_LATEST.yaml. Use before slice-tasks or plan-release on any new initiative. Not a substitute for slice-tasks (step 2) or plan-work (step 3).\"",
-      "sha256": "3d333e2bfa5f9998",
+      "sha256": "d3cb167d8a5296be",
       "path": "scope-work/SKILL.md"
     },
     "search-skills": {
@@ -268,7 +278,7 @@
     },
     "slice-tasks": {
       "description": "\"PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.\"",
-      "sha256": "bda9db54dbe791b5",
+      "sha256": "7948164e218541ea",
       "path": "slice-tasks/SKILL.md"
     },
     "smoke-test": {
@@ -283,7 +293,7 @@
     },
     "stocktake-skills": {
       "description": "Sequential subagent batch audit of the bigpowers skill catalog — Quick Scan (changed only) or Full (all skills). Use during sustain phase, before a major release, or when catalog drift is suspected.",
-      "sha256": "c58bf4f70ff02cd3",
+      "sha256": "6e73b2d2cf0cfbe1",
       "path": "stocktake-skills/SKILL.md"
     },
     "survey-context": {

package/slice-tasks/SKILL.md

@@ -18,6 +18,12 @@ Produce **epic capsule story tasks** in `specs/epics/eNN-slug/` — vertical sli
 
 ## Process
 
+0. **Read planning-context.yaml** — If `specs/planning-context.yaml` exists, read it first:
+   ```bash
+   test -f specs/planning-context.yaml && echo "Context found" || echo "No context — starting fresh"
+   ```
+   Use `feature_name`, `constraints`, and `out_of_scope` to inform slice boundaries. `key_decisions` in the file may constrain how stories are cut (e.g., "no external deps" constrains slice 2). If absent, proceed normally.
+
 1. **Read context** — Read `specs/product/SCOPE_LATEST.yaml` and/or `specs/release-plan.yaml`. Understand what the epic delivers end-to-end.
 
 2. **Cut tracer-bullet slices** — Identify the thinnest possible vertical path through the stack that delivers user value. Start with this slice; it will catch integration issues first. For example:

package/stocktake-skills/SKILL.md

@@ -15,7 +15,8 @@ Audit SKILL.md catalog for drift, stale triggers, missing HARD GATEs, and INDEX
 | Mode | Scope |
 |------|-------|
 | **Quick Scan** | Skills changed since last tag or in current diff |
-| **Full** | All 62 skills per SKILL-INDEX.md + catalog audit |
+| **Full** | All skills per SKILL-INDEX.md + catalog audit |
+| **--verify** | Run `bash scripts/run-skill-verify.sh` and append health results to the stocktake report |
 
 ## Process
 
@@ -27,6 +28,7 @@ Audit SKILL.md catalog for drift, stale triggers, missing HARD GATEs, and INDEX
    - Skills with zero calls (potential dead weight)
    - Skills with high average time (candidates for `evolve-skill`)
 5. Critical findings → `plan-work` story; cosmetic → `evolve-skill` candidate.
+6. **--verify mode:** Run `bash scripts/run-skill-verify.sh` and append a `## Verify Health` section to the stocktake report: `"N/68 PASS, M FAIL, K SKIP"`. FAIL skills are critical findings and go straight to `plan-work`.
 
 ### Skill timing data (`metrics.skill_timings`)