bigpowers 2.25.0 → 2.27.0

package/skills-lock.json

@@ -18,7 +18,7 @@
     },
     "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": "b7049084cd180053",
+      "sha256": "7a376ef092fde9cc",
       "path": "build-epic/SKILL.md"
     },
     "change-request": {
@@ -33,7 +33,7 @@
     },
     "compose-workflow": {
       "description": "Chain multiple bigpowers skills into a custom workflow recipe saved in specs/. Use when a project repeats a non-standard skill sequence, or user wants a documented playbook beyond orchestrate-project modes.",
-      "sha256": "4d498c0c6975cbce",
+      "sha256": "854e272ca7bd6e3a",
       "path": "compose-workflow/SKILL.md"
     },
     "craft-skill": {
@@ -73,7 +73,7 @@
     },
     "develop-tdd": {
       "description": "Test-driven development with red-green-refactor loop using vertical slices. Use for features (epic tasks) or bugs (specs/bugs/BUG-*.md).",
-      "sha256": "6ace47f7db4642d4",
+      "sha256": "e050f400da14eff3",
       "path": "develop-tdd/SKILL.md"
     },
     "diagnose-root": {
@@ -93,7 +93,7 @@
     },
     "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 +103,7 @@
     },
     "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": {
@@ -148,7 +148,7 @@
     },
     "kickoff-branch": {
       "description": "Create a git worktree and feature branch, then verify a clean test baseline before any code is written. Use when starting a new feature or task, when user wants to work in isolation from main, or mentions \"start a branch\" or \"new worktree\".",
-      "sha256": "77864a4086f91f60",
+      "sha256": "d3c74c05a8d790c0",
       "path": "kickoff-branch/SKILL.md"
     },
     "map-codebase": {
@@ -198,7 +198,7 @@
     },
     "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 +226,11 @@
       "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 +238,12 @@
     },
     "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 +273,7 @@
     },
     "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 +288,7 @@
     },
     "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": {
@@ -318,7 +323,7 @@
     },
     "verify-work": {
       "description": "Multi-phase UAT gate — cold-start smoke, build, typecheck, lint, tests, step-by-step manual verification, gaps-closure loop. Use after execute-plan or develop-tdd, before audit-code.",
-      "sha256": "d1aeab669a9c5621",
+      "sha256": "44f96eac8380c15b",
       "path": "verify-work/SKILL.md"
     },
     "visual-dashboard": {

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`)
 

package/verify-work/SKILL.md

@@ -16,6 +16,7 @@ Review answers "is the code good?"; Verify answers "does the built thing do what
 
 - Default: full UAT plus gaps loop
 - --smoke: Cold-start only plus one happy-path flow. Use for hotfixes.
+- --cli: CLI tool verification — replaces cold-start with binary smoke checklist. Use for CLI tools with no server process.
 
 ## Process
 
@@ -24,6 +25,12 @@ Review answers "is the code good?"; Verify answers "does the built thing do what
 0. **Branch check** — must not be `main`/`master`.
 
 1. Read active story tasks from `specs/epics/<capsule>/eNNsYY-tasks.yaml` and story spec from `specs/epics/<capsule>/eNNsYY-<slug>.md` (countable-story-format, Gherkin in §17).
+1a. **Pre-UAT verify validation** — for each task's `verify:` command, run it and detect pattern mismatches before UAT begins. If a grep/awk/jq command fails, check whether the pattern is wrong vs. a genuine failure:
+    ```bash
+    # For a failing grep -q 'PATTERN' FILE, check what is actually in FILE
+    grep 'PATTERN' FILE || grep -n '' FILE | head -20   # show nearest lines
+    ```
+    Report: `"Pattern 'X' not found. Nearest match: 'Y' at line N"` and ask `"Update verify command? [Y/n]"`. Fix before proceeding — a mismatched verify command produces false failures during UAT.
 2. **Cold-start smoke** (if app): stop server, clear caches, boot from scratch.
 3. **AGENTS.md preflight** — before running default checks, call `bash scripts/bp-read-agents.sh` to detect project-specific commands. If `BP_PREFLIGHT` is set, run it instead of the default mechanical gates (or in addition to them if the project requires both). Output: `"Using preflight from AGENTS.md: <cmd>"`. Fall back to `CLAUDE.md` commands if AGENTS.md is absent.
 4. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md` or AGENTS.md).
@@ -91,6 +98,29 @@ phases:
 
 > **HARD GATE** — Verification evidence MUST be persisted before marking the story done. No evidence = not verified.
 
+## --cli mode
+
+For CLI tools where cold-start smoke (stop server / clear caches) does not apply. Auto-detected when the project has no server process (no `listen()`, no `server.js`, no blocking `main()`); or explicitly activated with `--cli`.
+
+**Auto-detect binary name:**
+```bash
+# Cargo.toml
+BINARY=$(grep '^name' Cargo.toml | head -1 | awk -F'"' '{print $2}')
+# package.json
+BINARY=$(node -e "console.log(require('./package.json').bin && Object.keys(require('./package.json').bin)[0] || '')" 2>/dev/null)
+# Makefile
+BINARY=$(grep '^BIN\s*=' Makefile 2>/dev/null | awk '{print $3}')
+```
+
+**CLI verification checklist (replaces cold-start smoke):**
+
+1. `--help` smoke: `$BINARY --help` → assert output contains "Usage"
+2. `--version` check: `$BINARY --version` → assert version matches manifest (Cargo.toml / package.json)
+3. Happy-path: run documented example command from README.md → assert non-empty output
+4. Edge case: `$BINARY --invalid-flag` → assert exit code ≠ 0 and error message printed
+
+No "stop server" or "clear caches" steps are executed in `--cli` mode. Steps 3–6 of the default process (mechanical gates, UAT, gaps loop) still run unchanged.
+
 ## Verify
 
 → verify: `test -f specs/verifications/<story_id>-verify.yaml && echo "Evidence persisted"`