bigpowers 2.17.0 → 2.18.0

package/.pi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.17.0",
+  "version": "2.18.0",
   "description": "67 skills — 61 agent skills for spec-driven, test-first software development by solo developers",
   "keywords": [
     "pi-package"

package/.pi/prompts/stocktake-skills.md

@@ -21,7 +21,30 @@ Audit SKILL.md catalog for drift, stale triggers, missing HARD GATEs, and INDEX
 1. Run `bash scripts/audit-catalog.sh` to verify pi/skills ↔ source SKILL.md sync. Mismatch is a critical finding.
 2. Run mode; for each skill check: exists, verb-noun, <300 lines total, HARD GATE present, INDEX row matches.
 3. Write `specs/STOCKTAKE-<date>.md` with findings table (skill, issue, severity).
-4. Critical findings → `plan-work` story; cosmetic → `evolve-skill` candidate.
+4. **Effectiveness report (--full mode only):** Read `specs/state.yaml` `metrics.skill_timings` and report:
+   - Top 5 most-used skills (by calls, total_seconds)
+   - 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.
+
+### Skill timing data (`metrics.skill_timings`)
+
+In `--full` mode, read `specs/state.yaml` `metrics.skill_timings` for per-skill usage stats:
+
+```yaml
+metrics:
+  skill_timings:
+    survey-context:
+      calls: 12
+      total_seconds: 180
+      avg_seconds: 15.0
+    develop-tdd:
+      calls: 30
+      total_seconds: 5400
+      avg_seconds: 180.0
+```
+
+Timing data is populated by `scripts/bp-timing.sh start|end <skill>` calls within critical-path skills.
 
 ## Verify
 

package/.pi/skills/stocktake-skills/SKILL.md

@@ -23,7 +23,30 @@ Audit SKILL.md catalog for drift, stale triggers, missing HARD GATEs, and INDEX
 1. Run `bash scripts/audit-catalog.sh` to verify pi/skills ↔ source SKILL.md sync. Mismatch is a critical finding.
 2. Run mode; for each skill check: exists, verb-noun, <300 lines total, HARD GATE present, INDEX row matches.
 3. Write `specs/STOCKTAKE-<date>.md` with findings table (skill, issue, severity).
-4. Critical findings → `plan-work` story; cosmetic → `evolve-skill` candidate.
+4. **Effectiveness report (--full mode only):** Read `specs/state.yaml` `metrics.skill_timings` and report:
+   - Top 5 most-used skills (by calls, total_seconds)
+   - 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.
+
+### Skill timing data (`metrics.skill_timings`)
+
+In `--full` mode, read `specs/state.yaml` `metrics.skill_timings` for per-skill usage stats:
+
+```yaml
+metrics:
+  skill_timings:
+    survey-context:
+      calls: 12
+      total_seconds: 180
+      avg_seconds: 15.0
+    develop-tdd:
+      calls: 30
+      total_seconds: 5400
+      avg_seconds: 180.0
+```
+
+Timing data is populated by `scripts/bp-timing.sh start|end <skill>` calls within critical-path skills.
 
 ## Verify
 

package/CHANGELOG.md

@@ -1,3 +1,10 @@
+# [2.18.0](https://github.com/danielvm-git/bigpowers/compare/v2.17.0...v2.18.0) (2026-06-21)
+
+
+### Features
+
+* **e18s05:** auto-timing helper + stocktake effectiveness ([1542bb7](https://github.com/danielvm-git/bigpowers/commit/1542bb7652c7ba1edb893260c7e586f63e416259))
+
 # [2.17.0](https://github.com/danielvm-git/bigpowers/compare/v2.16.0...v2.17.0) (2026-06-21)
 
 

package/SKILL-INDEX.md

@@ -3,7 +3,7 @@
 > **DO NOT EDIT** — This file is auto-generated by `scripts/generate-skill-index.sh`.
 > Edit `SKILL.md` source files or `skills-lock.json` instead. Run `bash scripts/sync-skills.sh` to regenerate.
 
-**Generated:** 2026-06-21T21:41:36Z
+**Generated:** 2026-06-21T21:42:28Z
 **Skills:** 67
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.17.0",
+  "version": "2.18.0",
   "description": "61 agent skills for spec-driven, test-first software development by solo developers",
   "main": "index.js",
   "scripts": {

package/scripts/bp-timing.sh

@@ -0,0 +1,74 @@
+#!/usr/bin/env bash
+# bp-timing.sh — Record skill invocation timings for stocktake effectiveness analysis.
+# Usage: bash scripts/bp-timing.sh start <skill-name>
+#        bash scripts/bp-timing.sh end <skill-name>
+# Requires: python3 (for YAML-safe state updates)
+set -euo pipefail
+
+STATE_YAML="specs/state.yaml"
+TIMINGS_KEY="metrics.skill_timings"
+
+usage() {
+  echo "Usage: $0 start|end <skill-name>" >&2
+  exit 1
+}
+
+[ $# -ne 2 ] && usage
+
+ACTION="$1"
+SKILL="$2"
+
+case "$ACTION" in
+  start)
+    STAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+    python3 -c "
+import yaml, sys
+try:
+    with open('$STATE_YAML') as f:
+        data = yaml.safe_load(f) or {}
+except: data = {}
+
+metrics = data.setdefault('metrics', {})
+timings = metrics.setdefault('skill_timings', {})
+
+if '$SKILL' not in timings:
+    timings['$SKILL'] = {'calls': 0, 'total_seconds': 0, 'avg_seconds': 0}
+
+timings['$SKILL']['_start'] = '$STAMP'
+with open('$STATE_YAML', 'w') as f:
+    yaml.dump(data, f, default_flow_style=False, sort_keys=False, allow_unicode=True)
+" 2>/dev/null || echo "WARN: timing start failed (yaml tools missing?)" >&2
+    ;;
+
+  end)
+    STAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+    python3 -c "
+import yaml
+from datetime import datetime
+
+with open('$STATE_YAML') as f:
+    data = yaml.safe_load(f) or {}
+
+metrics = data.setdefault('metrics', {})
+timings = metrics.setdefault('skill_timings', {})
+
+if '$SKILL' in timings and '_start' in timings['$SKILL']:
+    start_t = datetime.fromisoformat(timings['$SKILL']['_start'].replace('Z','+00:00'))
+    end_t = datetime.fromisoformat('$STAMP'.replace('Z','+00:00'))
+    elapsed = (end_t - start_t).total_seconds()
+
+    entry = timings['$SKILL']
+    entry['calls'] = entry.get('calls', 0) + 1
+    entry['total_seconds'] = entry.get('total_seconds', 0) + elapsed
+    entry['avg_seconds'] = entry['total_seconds'] / entry['calls']
+    del entry['_start']
+
+with open('$STATE_YAML', 'w') as f:
+    yaml.dump(data, f, default_flow_style=False, sort_keys=False, allow_unicode=True)
+" 2>/dev/null || echo "WARN: timing end failed" >&2
+    ;;
+
+  *)
+    usage
+    ;;
+esac

package/skills-lock.json

@@ -278,7 +278,7 @@
     },
     "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": "84a4cba67602028f",
+      "sha256": "c58bf4f70ff02cd3",
       "path": "stocktake-skills/SKILL.md"
     },
     "survey-context": {

package/stocktake-skills/SKILL.md

@@ -22,7 +22,30 @@ Audit SKILL.md catalog for drift, stale triggers, missing HARD GATEs, and INDEX
 1. Run `bash scripts/audit-catalog.sh` to verify pi/skills ↔ source SKILL.md sync. Mismatch is a critical finding.
 2. Run mode; for each skill check: exists, verb-noun, <300 lines total, HARD GATE present, INDEX row matches.
 3. Write `specs/STOCKTAKE-<date>.md` with findings table (skill, issue, severity).
-4. Critical findings → `plan-work` story; cosmetic → `evolve-skill` candidate.
+4. **Effectiveness report (--full mode only):** Read `specs/state.yaml` `metrics.skill_timings` and report:
+   - Top 5 most-used skills (by calls, total_seconds)
+   - 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.
+
+### Skill timing data (`metrics.skill_timings`)
+
+In `--full` mode, read `specs/state.yaml` `metrics.skill_timings` for per-skill usage stats:
+
+```yaml
+metrics:
+  skill_timings:
+    survey-context:
+      calls: 12
+      total_seconds: 180
+      avg_seconds: 15.0
+    develop-tdd:
+      calls: 30
+      total_seconds: 5400
+      avg_seconds: 180.0
+```
+
+Timing data is populated by `scripts/bp-timing.sh start|end <skill>` calls within critical-path skills.
 
 ## Verify