bigpowers 2.74.0 → 2.74.2

package/.pi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.74.0",
+  "version": "2.74.2",
   "description": "77 skills — 73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
   "keywords": [
     "pi-package"

package/.pi/prompts/build-epic.md

@@ -3,6 +3,8 @@ description: Eight-step epic build cycle — reads state.yaml, execution-status.
 ---
 
 
+# story: e20s05
+
 # Build Epic
 
 Scope: one story. Called by orchestrate-project Phase 4. Not a replacement for orchestrate-project.
@@ -87,3 +89,6 @@ Write `handoff.next_skill` and `handoff.context` in `state.yaml` when pausing mi
 ## Verify
 
 → verify: `test -f specs/state.yaml && test -f specs/execution-status.yaml && test -f specs/release-plan.yaml && test -d skills/assess-impact && test -d skills/audit-code && test -d skills/security-review && echo "OK: build-epic dependencies present" || echo "FAIL"`
+
+
+<!-- story: e38s02 -->

package/.pi/prompts/change-request.md

@@ -4,6 +4,7 @@ description: Add a new requirement or reorder epics by WSJF against specs/releas
 
 
 # story: e45s29
+# story: e20s01
 
 # Change Request
 

package/.pi/prompts/compose-workflow.md

@@ -3,7 +3,9 @@ description: Chain multiple bigpowers skills into a custom workflow recipe saved
 ---
 
 
+# story: e09s01
 # story: e45s27
+# story: e21s04
 
 # Compose Workflow
 > **HARD GATE** — **HARD GATE** — Workflows are orchestration, not automation. Do NOT create workflows for tasks that should be single skills. Workflow complexity must be justified.

package/.pi/prompts/dispatch-agents.md

@@ -3,6 +3,11 @@ description: Dispatch multiple subagents in parallel on independent tasks. No wa
 ---
 
 
+# story: e09s04
+# story: e45s38
+<!-- story: e45s11 -->
+
+
 # story: e45s30
 
 # Dispatch Agents
@@ -109,5 +114,4 @@ Merge accepted results. Resolve conflicts manually; note in summary.
 Report: which tasks succeeded, which need revision, overall verify status.
 
 ## Verify
-
 → verify: `grep -q 'circuit_open' skills/dispatch-agents/SKILL.md && grep -q 'task_brief' skills/dispatch-agents/SKILL.md && echo OK || echo FAIL`

package/.pi/prompts/evolve-skill.md

@@ -2,6 +2,10 @@
 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.
 ---
 
+# story: e23s03
+
+# story: e09s01
+# story: e09s05
 
 # Evolve Skill
 
@@ -30,6 +34,9 @@ description: Benchmark-gated skill evolution — consume bigpowers-benchmark rep
 
 See [REFERENCE.md](REFERENCE.md) for ADR template.
 
+
+<!-- story: e31s07 -->
+
 ---
 
 # Evolve Skill — ADR snippet

package/.pi/prompts/kickoff-branch.md

@@ -3,6 +3,10 @@ description: Create a git worktree and feature branch, then verify a clean test
 ---
 
 
+# story: e51s03
+# story: e20s03
+
+
 # Kickoff Branch
 
 > **HARD GATE** — Direct work on `main` or `master` is PROHIBITED. Every task MUST start with this skill to create a feature branch or worktree.

package/.pi/prompts/migrate-spec.md

@@ -2,6 +2,12 @@
 description: Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs.
 ---
 
+# story: e25s01
+# story: e25s02
+# story: e25s03
+# story: e25s04
+# story: e25s05
+# story: e25s06
 
 # Migrate Spec
 

package/.pi/prompts/release-branch.md

@@ -3,6 +3,13 @@ description: Make the merge/PR/keep/discard decision for a feature branch, verif
 ---
 
 
+<!-- story: e38s07 -->
+<!-- story: e45s15 -->
+<!-- story: e45s32 -->
+<!-- story: e45s39 -->
+<!-- story: e20s02 -->
+
+
 # Release Branch
 
 > **HARD GATE** — Do NOT merge or release if tests fail or if coverage gates are not met. If the branch is red, return to `develop-tdd` to fix regressions or add missing tests before proceeding.

package/.pi/prompts/research-first.md

@@ -3,6 +3,9 @@ description: Look-before-build — search registries, repo, existing skills, and
 ---
 
 
+# story: e03s01
+# story: e21s02
+
 # Research First
 
 > **HARD GATE** — Do NOT implement until prior art is searched. Minimum outcome: adopt, extend, compose, or build — with evidence.

package/.pi/prompts/run-planning.md

@@ -2,6 +2,7 @@
 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."
 ---
 
+# story: e24s03
 
 # Run Planning
 

package/.pi/prompts/scope-work.md

@@ -3,6 +3,9 @@ description: "PLANNING SPINE STEP 1 of 3 — Scope the work: define what is in a
 ---
 
 
+# story: e03s01
+# story: e24s02
+
 # Scope Work
 
 > **Spine position:** Step 1 — scope-work → slice-tasks → plan-work.

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

@@ -3,6 +3,9 @@ description: Find the right bigpowers skill from natural-language intent using a
 ---
 
 
+# story: e09s01
+# story: e21s01
+
 # Search Skills
 
 > **HARD GATE** — Search results must be ranked by relevance. Do NOT return all matches without prioritization. Use skill metadata (phase, purpose, frequency) to rank.

package/.pi/prompts/security-review.md

@@ -3,6 +3,15 @@ description: >
 ---
 
 
+# story: e45s41
+<!-- story: e45s18 -->
+# story: e26s01
+# story: e26s02
+# story: e26s03
+# story: e26s04
+# story: e26s05
+# story: e26s06
+# story: e26s07
 # story: e45s26
 
 # Security Review
@@ -99,11 +108,8 @@ Each finding: **`File:Line` — Severity — Category**
 
 ## Verify
 
-
-
 ```bash
-test -d specs/security && echo "OK: specs/security/ exists" || mkdir -p specs/security
-grep -q "Merge-base\|merge.base\|git diff" SKILL.md && echo "OK: git context verified"
+test -d specs/security && echo "OK: specs/security/ exists" || mkdir -p specs/security; grep -q "Merge-base\|merge.base\|git diff" SKILL.md && echo "OK: git context verified"
 ```
 
 ---

package/.pi/prompts/seed-conventions.md

@@ -3,6 +3,13 @@ description: Generate CLAUDE.md and CONVENTIONS.md for a brand-new project throu
 ---
 
 
+# story: e10s01
+# story: e47s02
+# story: e10s02
+# story: e51s02
+# story: e45s21
+
+
 # Seed Conventions
 > **HARD GATE** — Before any new code lands, confirm the project conventions are understood. Ask: 'What does a good commit message look like in this project?'
 

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

@@ -3,6 +3,10 @@ description: Sequential subagent batch audit of the bigpowers skill catalog —
 ---
 
 
+# story: e09s01
+<!-- story: e45s12 -->
+
+
 # Stocktake Skills
 > **HARD GATE** — **HARD GATE** — Skill inventory must be current. Missing HARD GATEs, stale descriptions, or broken verify commands are defects, not cosmetic. Fix them in `evolve-skill`.
 

package/.pi/prompts/verify-work.md

@@ -3,6 +3,17 @@ description: Multi-phase UAT gate — cold-start smoke, build, typecheck, lint,
 ---
 
 
+<!-- story: e02s01 e46s03 -->
+<!-- story: e38s05 -->
+<!-- story: e45s05 -->
+<!-- story: e45s09 -->
+<!-- story: e45s13 -->
+<!-- story: e45s40 -->
+<!-- story: e51s03 -->
+<!-- story: e20s04 -->
+<!-- story: e20s06 -->
+
+
 # Verify Work
 
 > **HARD GATE** — No story is "done" until manual UAT for the active story is confirmed with evidence.

package/.pi/skills/build-epic/SKILL.md

@@ -5,6 +5,8 @@ model: sonnet
 ---
 
 
+# story: e20s05
+
 # Build Epic
 
 Scope: one story. Called by orchestrate-project Phase 4. Not a replacement for orchestrate-project.
@@ -89,3 +91,6 @@ Write `handoff.next_skill` and `handoff.context` in `state.yaml` when pausing mi
 ## Verify
 
 → verify: `test -f specs/state.yaml && test -f specs/execution-status.yaml && test -f specs/release-plan.yaml && test -d skills/assess-impact && test -d skills/audit-code && test -d skills/security-review && echo "OK: build-epic dependencies present" || echo "FAIL"`
+
+
+<!-- story: e38s02 -->

package/.pi/skills/change-request/SKILL.md

@@ -6,6 +6,7 @@ model: sonnet
 
 
 # story: e45s29
+# story: e20s01
 
 # Change Request
 

package/.pi/skills/compose-workflow/SKILL.md

@@ -5,7 +5,9 @@ model: sonnet
 ---
 
 
+# story: e09s01
 # story: e45s27
+# story: e21s04
 
 # Compose Workflow
 > **HARD GATE** — **HARD GATE** — Workflows are orchestration, not automation. Do NOT create workflows for tasks that should be single skills. Workflow complexity must be justified.

package/.pi/skills/dispatch-agents/SKILL.md

@@ -5,6 +5,11 @@ model: sonnet
 ---
 
 
+# story: e09s04
+# story: e45s38
+<!-- story: e45s11 -->
+
+
 # story: e45s30
 
 # Dispatch Agents
@@ -111,5 +116,4 @@ Merge accepted results. Resolve conflicts manually; note in summary.
 Report: which tasks succeeded, which need revision, overall verify status.
 
 ## Verify
-
 → verify: `grep -q 'circuit_open' skills/dispatch-agents/SKILL.md && grep -q 'task_brief' skills/dispatch-agents/SKILL.md && echo OK || echo FAIL`

package/.pi/skills/evolve-skill/SKILL.md

@@ -4,6 +4,10 @@ description: "Benchmark-gated skill evolution — consume bigpowers-benchmark re
 model: opus
 ---
 
+# story: e23s03
+
+# story: e09s01
+# story: e09s05
 
 # Evolve Skill
 
@@ -32,6 +36,9 @@ model: opus
 
 See [REFERENCE.md](REFERENCE.md) for ADR template.
 
+
+<!-- story: e31s07 -->
+
 ---
 
 # Evolve Skill — ADR snippet

package/.pi/skills/kickoff-branch/SKILL.md

@@ -5,6 +5,10 @@ model: haiku
 ---
 
 
+# story: e51s03
+# story: e20s03
+
+
 # Kickoff Branch
 
 > **HARD GATE** — Direct work on `main` or `master` is PROHIBITED. Every task MUST start with this skill to create a feature branch or worktree.

package/.pi/skills/migrate-spec/SKILL.md

@@ -4,6 +4,12 @@ description: "Detect GSD, spec-kit, or BMAD spec artifacts and transform them in
 model: sonnet
 ---
 
+# story: e25s01
+# story: e25s02
+# story: e25s03
+# story: e25s04
+# story: e25s05
+# story: e25s06
 
 # Migrate Spec
 

package/.pi/skills/release-branch/SKILL.md

@@ -5,6 +5,13 @@ model: haiku
 ---
 
 
+<!-- story: e38s07 -->
+<!-- story: e45s15 -->
+<!-- story: e45s32 -->
+<!-- story: e45s39 -->
+<!-- story: e20s02 -->
+
+
 # Release Branch
 
 > **HARD GATE** — Do NOT merge or release if tests fail or if coverage gates are not met. If the branch is red, return to `develop-tdd` to fix regressions or add missing tests before proceeding.

package/.pi/skills/research-first/SKILL.md

@@ -5,6 +5,9 @@ model: sonnet
 ---
 
 
+# story: e03s01
+# story: e21s02
+
 # Research First
 
 > **HARD GATE** — Do NOT implement until prior art is searched. Minimum outcome: adopt, extend, compose, or build — with evidence.

package/.pi/skills/run-planning/SKILL.md

@@ -4,6 +4,7 @@ description: "\"DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (
 model: sonnet
 ---
 
+# story: e24s03
 
 # Run Planning
 

package/.pi/skills/scope-work/SKILL.md

@@ -5,6 +5,9 @@ model: sonnet
 ---
 
 
+# story: e03s01
+# story: e24s02
+
 # Scope Work
 
 > **Spine position:** Step 1 — scope-work → slice-tasks → plan-work.

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

@@ -5,6 +5,9 @@ model: haiku
 ---
 
 
+# story: e09s01
+# story: e21s01
+
 # Search Skills
 
 > **HARD GATE** — Search results must be ranked by relevance. Do NOT return all matches without prioritization. Use skill metadata (phase, purpose, frequency) to rank.

package/.pi/skills/security-review/SKILL.md

@@ -5,6 +5,15 @@ model: sonnet
 ---
 
 
+# story: e45s41
+<!-- story: e45s18 -->
+# story: e26s01
+# story: e26s02
+# story: e26s03
+# story: e26s04
+# story: e26s05
+# story: e26s06
+# story: e26s07
 # story: e45s26
 
 # Security Review
@@ -101,11 +110,8 @@ Each finding: **`File:Line` — Severity — Category**
 
 ## Verify
 
-
-
 ```bash
-test -d specs/security && echo "OK: specs/security/ exists" || mkdir -p specs/security
-grep -q "Merge-base\|merge.base\|git diff" SKILL.md && echo "OK: git context verified"
+test -d specs/security && echo "OK: specs/security/ exists" || mkdir -p specs/security; grep -q "Merge-base\|merge.base\|git diff" SKILL.md && echo "OK: git context verified"
 ```
 
 ---

package/.pi/skills/seed-conventions/SKILL.md

@@ -5,6 +5,13 @@ model: sonnet
 ---
 
 
+# story: e10s01
+# story: e47s02
+# story: e10s02
+# story: e51s02
+# story: e45s21
+
+
 # Seed Conventions
 > **HARD GATE** — Before any new code lands, confirm the project conventions are understood. Ask: 'What does a good commit message look like in this project?'
 

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

@@ -5,6 +5,10 @@ model: sonnet
 ---
 
 
+# story: e09s01
+<!-- story: e45s12 -->
+
+
 # Stocktake Skills
 > **HARD GATE** — **HARD GATE** — Skill inventory must be current. Missing HARD GATEs, stale descriptions, or broken verify commands are defects, not cosmetic. Fix them in `evolve-skill`.
 

package/.pi/skills/verify-work/SKILL.md

@@ -5,6 +5,17 @@ model: haiku
 ---
 
 
+<!-- story: e02s01 e46s03 -->
+<!-- story: e38s05 -->
+<!-- story: e45s05 -->
+<!-- story: e45s09 -->
+<!-- story: e45s13 -->
+<!-- story: e45s40 -->
+<!-- story: e51s03 -->
+<!-- story: e20s04 -->
+<!-- story: e20s06 -->
+
+
 # Verify Work
 
 > **HARD GATE** — No story is "done" until manual UAT for the active story is confirmed with evidence.

package/CHANGELOG.md

@@ -1,3 +1,18 @@
+## [2.74.2](https://github.com/danielvm-git/bigpowers/compare/v2.74.1...v2.74.2) (2026-07-07)
+
+
+### Bug Fixes
+
+* **sync-skills:** regenerate artifacts after main merge ([6f37c8a](https://github.com/danielvm-git/bigpowers/commit/6f37c8acdc56862792fbcebcaae32f0662e0b3f7))
+
+## [2.74.1](https://github.com/danielvm-git/bigpowers/compare/v2.74.0...v2.74.1) (2026-07-07)
+
+
+### Bug Fixes
+
+* **planning:** resolve yaml status drift for implemented epics ([fd06c68](https://github.com/danielvm-git/bigpowers/commit/fd06c68fc491746b7b7ff283fa561fce72ebb883))
+* **traceability:** backfill story tags for e01-e29, fix YAML/size issues ([cca4942](https://github.com/danielvm-git/bigpowers/commit/cca494288a4c2e90a2dc871d46acefacf50ccf0b))
+
 # [2.74.0](https://github.com/danielvm-git/bigpowers/compare/v2.73.9...v2.74.0) (2026-07-07)
 
 

package/CONVENTIONS.md

@@ -1,3 +1,6 @@
+# story: e05s01 e46s04
+# story: e06s02
+# story: e07s01
 # story: e30s02
 # story: e30s03
 # story: e38s08
@@ -5,6 +8,8 @@
 # story: e51s01
 # story: e45s25
 # story: e45s36
+# story: e27s01
+# story: e29s03
 
 # Conventions
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.74.0",
+  "version": "2.74.2",
   "description": "73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
   "main": "index.js",
   "scripts": {

package/scripts/bp-read-agents.sh

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# story: e21s03
 # bp-read-agents.sh — Extract preflight/test/build/lint/deploy commands from AGENTS.md.
 # Outputs env-var exports: BP_PREFLIGHT, BP_TEST, BP_BUILD, BP_LINT, BP_DEPLOY
 # Usage: eval "$(bash scripts/bp-read-agents.sh)"  # imports env vars

package/scripts/run-skill-verify.sh

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# story: e22s01
 # Run all SKILL.md → verify: commands and report PASS/FAIL/SKIP.
 # Exit 0 only when zero FAILs.
 # Usage: bash scripts/run-skill-verify.sh [skill-name]

package/scripts/sync-skills.sh

@@ -1,5 +1,16 @@
 #!/usr/bin/env bash
-# story: e13s03 e28s03 e39s04
+# story: e05s01
+# story: e12s01
+# story: e12s02
+# story: e12s03
+# story: e12s04
+# story: e12s06
+# story: e13s03
+# story: e28s02
+# story: e28s03
+# story: e39s04
+# story: e29s01
+# story: e29s02
 # sync-skills.sh — generate Cursor, Gemini CLI, pi, and OKF artifacts from SKILL.md source files
 # Architecture: Parse→IR→Render. Each target is its own render_<target>() function.
 # Run this after adding or updating any skill. Symlinks carry changes through automatically.

package/skills/build-epic/SKILL.md

@@ -1,11 +1,13 @@
 ---
 name: build-epic
-# story: e38s02
+# story: e18s01 e18s02 e18s03 e38s02
 model: sonnet
 effort: standard
 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.
 ---
 
+# story: e20s05
+
 # Build Epic
 
 Scope: one story. Called by orchestrate-project Phase 4. Not a replacement for orchestrate-project.
@@ -90,3 +92,6 @@ Write `handoff.next_skill` and `handoff.context` in `state.yaml` when pausing mi
 ## Verify
 
 → verify: `test -f specs/state.yaml && test -f specs/execution-status.yaml && test -f specs/release-plan.yaml && test -d skills/assess-impact && test -d skills/audit-code && test -d skills/security-review && echo "OK: build-epic dependencies present" || echo "FAIL"`
+
+
+<!-- story: e38s02 -->

package/skills/change-request/SKILL.md

@@ -6,6 +6,7 @@ description: Add a new requirement or reorder epics by WSJF against specs/releas
 ---
 
 # story: e45s29
+# story: e20s01
 
 # Change Request
 

package/skills/compose-workflow/SKILL.md

@@ -5,7 +5,9 @@ model: sonnet
 effort: standard
 ---
 
+# story: e09s01
 # story: e45s27
+# story: e21s04
 
 # Compose Workflow
 > **HARD GATE** — **HARD GATE** — Workflows are orchestration, not automation. Do NOT create workflows for tasks that should be single skills. Workflow complexity must be justified.

package/skills/dispatch-agents/SKILL.md

@@ -1,5 +1,3 @@
-# story: e45s38
-<!-- story: e45s11 -->
 ---
 name: dispatch-agents
 model: sonnet
@@ -7,6 +5,11 @@ effort: standard
 description: Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).
 ---
 
+# story: e09s04
+# story: e45s38
+<!-- story: e45s11 -->
+
+
 # story: e45s30
 
 # Dispatch Agents
@@ -113,6 +116,5 @@ Merge accepted results. Resolve conflicts manually; note in summary.
 Report: which tasks succeeded, which need revision, overall verify status.
 
 ## Verify
-
 → verify: `grep -q 'circuit_open' skills/dispatch-agents/SKILL.md && grep -q 'task_brief' skills/dispatch-agents/SKILL.md && echo OK || echo FAIL`
 

package/skills/elaborate-spec/SKILL.md

@@ -3,6 +3,7 @@ name: elaborate-spec
 model: opus
 effort: standard
 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.
+# story: e24s01
 ---
 
 # Elaborate Spec

package/skills/evolve-skill/SKILL.md

@@ -4,6 +4,10 @@ description: Benchmark-gated skill evolution — consume bigpowers-benchmark rep
 model: opus
 effort: standard
 ---
+# story: e23s03
+
+# story: e09s01
+# story: e09s05
 
 # Evolve Skill
 
@@ -31,3 +35,6 @@ effort: standard
 → verify: `grep -c 'run-benchmark\|pass_at_k\|BASELINE-' skills/evolve-skill/SKILL.md | awk '{if($1>=2) print "OK"; else print "FAIL"}'`
 
 See [REFERENCE.md](REFERENCE.md) for ADR template.
+
+
+<!-- story: e31s07 -->

package/skills/kickoff-branch/SKILL.md

@@ -1,4 +1,3 @@
-# story: e51s03
 ---
 name: kickoff-branch
 model: haiku
@@ -6,6 +5,10 @@ effort: standard
 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".
 ---
 
+# story: e51s03
+# story: e20s03
+
+
 # Kickoff Branch
 
 > **HARD GATE** — Direct work on `main` or `master` is PROHIBITED. Every task MUST start with this skill to create a feature branch or worktree.

package/skills/migrate-spec/SKILL.md

@@ -4,6 +4,12 @@ model: sonnet
 effort: standard
 description: Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs.
 ---
+# story: e25s01
+# story: e25s02
+# story: e25s03
+# story: e25s04
+# story: e25s05
+# story: e25s06
 
 # Migrate Spec
 

package/skills/release-branch/SKILL.md

@@ -1,14 +1,18 @@
-<!-- story: e38s07 -->
-<!-- story: e45s15 -->
-<!-- story: e45s32 -->
-<!-- story: e45s39 -->
 ---
 name: release-branch
+# story: e14s01 e15s03
 model: haiku
 effort: standard
 description: Make the merge/PR/keep/discard decision for a feature branch, verify coverage gates, create the PR with gh, and clean up the worktree. Use when a feature is done and ready to ship, or when user says "release", "merge", or "open a PR".
 ---
 
+<!-- story: e38s07 -->
+<!-- story: e45s15 -->
+<!-- story: e45s32 -->
+<!-- story: e45s39 -->
+<!-- story: e20s02 -->
+
+
 # Release Branch
 
 > **HARD GATE** — Do NOT merge or release if tests fail or if coverage gates are not met. If the branch is red, return to `develop-tdd` to fix regressions or add missing tests before proceeding.

package/skills/research-first/SKILL.md

@@ -5,6 +5,9 @@ model: sonnet
 effort: standard
 ---
 
+# story: e03s01
+# story: e21s02
+
 # Research First
 
 > **HARD GATE** — Do NOT implement until prior art is searched. Minimum outcome: adopt, extend, compose, or build — with evidence.

package/skills/run-benchmark/SKILL.md

@@ -4,6 +4,7 @@ name: run-benchmark
 model: haiku
 effort: standard
 description: Run skill quality benchmarks from specs/benchmarks/ definitions — N-run with/without-skill delta grading, train/validation split, pass@k + benchmark.json reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions.
+# story: e23s02
 ---
 
 # Run Benchmark

package/skills/run-planning/SKILL.md

@@ -4,6 +4,7 @@ model: sonnet
 effort: standard
 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."
 ---
+# story: e24s03
 
 # Run Planning
 

package/skills/scope-work/SKILL.md

@@ -5,6 +5,9 @@ model: sonnet
 effort: standard
 ---
 
+# story: e03s01
+# story: e24s02
+
 # Scope Work
 
 > **Spine position:** Step 1 — scope-work → slice-tasks → plan-work.

package/skills/search-skills/SKILL.md

@@ -5,6 +5,9 @@ model: haiku
 effort: standard
 ---
 
+# story: e09s01
+# story: e21s01
+
 # Search Skills
 
 > **HARD GATE** — Search results must be ranked by relevance. Do NOT return all matches without prioritization. Use skill metadata (phase, purpose, frequency) to rank.

package/skills/security-review/SKILL.md

@@ -1,5 +1,3 @@
-# story: e45s41
-<!-- story: e45s18 -->
 ---
 name: security-review
 model: sonnet
@@ -12,6 +10,15 @@ description: >
   the user says "security review" or "scan for vulns".
 ---
 
+# story: e45s41
+<!-- story: e45s18 -->
+# story: e26s01
+# story: e26s02
+# story: e26s03
+# story: e26s04
+# story: e26s05
+# story: e26s06
+# story: e26s07
 # story: e45s26
 
 # Security Review
@@ -108,9 +115,6 @@ Each finding: **`File:Line` — Severity — Category**
 
 ## Verify
 
-
-
 ```bash
-test -d specs/security && echo "OK: specs/security/ exists" || mkdir -p specs/security
-grep -q "Merge-base\|merge.base\|git diff" SKILL.md && echo "OK: git context verified"
+test -d specs/security && echo "OK: specs/security/ exists" || mkdir -p specs/security; grep -q "Merge-base\|merge.base\|git diff" SKILL.md && echo "OK: git context verified"
 ```

package/skills/seed-conventions/SKILL.md

@@ -1,5 +1,3 @@
-# story: e51s02
-# story: e45s21
 ---
 name: seed-conventions
 model: sonnet
@@ -7,6 +5,13 @@ effort: standard
 description: Generate CLAUDE.md and CONVENTIONS.md for a brand-new project through a brief interview, and create the specs/ directory with evolved bigpowers structure (product/, tech-architecture/, verifications/, epics/archive/). Entry point for greenfield projects. Use when starting a new project from scratch, when user asks to set up AI agent conventions, or when there is no CLAUDE.md yet.
 ---
 
+# story: e10s01
+# story: e47s02
+# story: e10s02
+# story: e51s02
+# story: e45s21
+
+
 # Seed Conventions
 > **HARD GATE** — Before any new code lands, confirm the project conventions are understood. Ask: 'What does a good commit message look like in this project?'
 

package/skills/stocktake-skills/SKILL.md

@@ -1,11 +1,16 @@
-<!-- story: e45s12 -->
 ---
 name: stocktake-skills
+# story: e18s05
 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.
+# story: e22s02
 model: sonnet
 effort: standard
 ---
 
+# story: e09s01
+<!-- story: e45s12 -->
+
+
 # Stocktake Skills
 > **HARD GATE** — **HARD GATE** — Skill inventory must be current. Missing HARD GATEs, stale descriptions, or broken verify commands are defects, not cosmetic. Fix them in `evolve-skill`.
 

package/skills/verify-work/SKILL.md

@@ -1,9 +1,3 @@
-<!-- story: e38s05 -->
-<!-- story: e45s05 -->
-<!-- story: e45s09 -->
-<!-- story: e45s13 -->
-<!-- story: e45s40 -->
-<!-- story: e51s03 -->
 ---
 name: 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.
@@ -11,6 +5,17 @@ model: haiku
 effort: standard
 ---
 
+<!-- story: e02s01 e46s03 -->
+<!-- story: e38s05 -->
+<!-- story: e45s05 -->
+<!-- story: e45s09 -->
+<!-- story: e45s13 -->
+<!-- story: e45s40 -->
+<!-- story: e51s03 -->
+<!-- story: e20s04 -->
+<!-- story: e20s06 -->
+
+
 # Verify Work
 
 > **HARD GATE** — No story is "done" until manual UAT for the active story is confirmed with evidence.

package/skills-lock.json

@@ -23,12 +23,12 @@
     },
     "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": "230ac9d30cae1a63",
+      "sha256": "85275fd5f2f5664f",
       "path": "skills/build-epicSKILL.md"
     },
     "change-request": {
       "description": "Add a new requirement or reorder epics by WSJF against specs/release-plan.yaml and epic capsule directories. Modes Add and Reorder. Use when a new requirement arrives mid-release or the plan needs prioritization.",
-      "sha256": "92edb0a1bd19b528",
+      "sha256": "51804487e854d6c0",
       "path": "skills/change-requestSKILL.md"
     },
     "commit-message": {
@@ -38,7 +38,7 @@
     },
     "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": "197a5220ccb3d74f",
+      "sha256": "2ea1448c65074036",
       "path": "skills/compose-workflowSKILL.md"
     },
     "context7-mcp": {
@@ -98,7 +98,7 @@
     },
     "dispatch-agents": {
       "description": "Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).",
-      "sha256": "7f5e21affed8f000",
+      "sha256": "296a7e548e0b5567",
       "path": "skills/dispatch-agentsSKILL.md"
     },
     "edit-document": {
@@ -108,7 +108,7 @@
     },
     "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": "5ac7ddd5b35cc749",
+      "sha256": "62ebfca87e6d0162",
       "path": "skills/elaborate-specSKILL.md"
     },
     "enforce-first": {
@@ -118,7 +118,7 @@
     },
     "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": "db153994fb656052",
+      "sha256": "ac463a2a725271a2",
       "path": "skills/evolve-skillSKILL.md"
     },
     "execute-plan": {
@@ -173,7 +173,7 @@
     },
     "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": "c9bed1e15d6df733",
+      "sha256": "256eefc13f0ec022",
       "path": "skills/kickoff-branchSKILL.md"
     },
     "maintain-wiki": {
@@ -188,7 +188,7 @@
     },
     "migrate-spec": {
       "description": "Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs.",
-      "sha256": "074c94f8dab39be0",
+      "sha256": "2f33c843e0c1f85a",
       "path": "skills/migrate-specSKILL.md"
     },
     "model-domain": {
@@ -238,7 +238,7 @@
     },
     "release-branch": {
       "description": "Make the merge/PR/keep/discard decision for a feature branch, verify coverage gates, create the PR with gh, and clean up the worktree. Use when a feature is done and ready to ship, or when user says \"release\", \"merge\", or \"open a PR\".",
-      "sha256": "c07d9efcb1d4e79b",
+      "sha256": "5da46a5b7aa7403f",
       "path": "skills/release-branchSKILL.md"
     },
     "request-review": {
@@ -248,7 +248,7 @@
     },
     "research-first": {
       "description": "Look-before-build — search registries, repo, existing skills, and web for prior art before implementing. Appends Prior Art to the spec. Use after survey-context and before elaborate-spec, when adding dependencies, or when the task may already be solved.",
-      "sha256": "5ca85e90a08b43e0",
+      "sha256": "22d8daca5171d683",
       "path": "skills/research-firstSKILL.md"
     },
     "reset-baseline": {
@@ -263,7 +263,7 @@
     },
     "run-benchmark": {
       "description": "Run skill quality benchmarks from specs/benchmarks/ definitions — N-run with/without-skill delta grading, train/validation split, pass@k + benchmark.json reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions.",
-      "sha256": "ad0c0eebf819f036",
+      "sha256": "0f47ed3ef681a6c6",
       "path": "skills/run-benchmarkSKILL.md"
     },
     "run-evals": {
@@ -273,27 +273,27 @@
     },
     "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": "6ed38edebc9b5523",
+      "sha256": "8db3e4ed9334a3a3",
       "path": "skills/run-planningSKILL.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": "9a162a9abb0deed7",
+      "sha256": "549cb6605f4b9256",
       "path": "skills/scope-workSKILL.md"
     },
     "search-skills": {
       "description": "Find the right bigpowers skill from natural-language intent using a local lexical index over SKILL.md frontmatter. Use when unsure which skill to invoke, or at start of research-first.",
-      "sha256": "cd70e1d872881e87",
+      "sha256": "c8600e446b2fd8c5",
       "path": "skills/search-skillsSKILL.md"
     },
     "security-review": {
       "description": ">",
-      "sha256": "8063dcca13bba46b",
+      "sha256": "7734fc00b0cf34f6",
       "path": "skills/security-reviewSKILL.md"
     },
     "seed-conventions": {
       "description": "Generate CLAUDE.md and CONVENTIONS.md for a brand-new project through a brief interview, and create the specs/ directory with evolved bigpowers structure (product/, tech-architecture/, verifications/, epics/archive/). Entry point for greenfield projects. Use when starting a new project from scratch, when user asks to set up AI agent conventions, or when there is no CLAUDE.md yet.",
-      "sha256": "e995b42dda1cfd23",
+      "sha256": "35c335385c4ad48b",
       "path": "skills/seed-conventionsSKILL.md"
     },
     "session-state": {
@@ -328,7 +328,7 @@
     },
     "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": "82d6399aba8eeea2",
+      "sha256": "6833c900df48a98a",
       "path": "skills/stocktake-skillsSKILL.md"
     },
     "survey-context": {
@@ -363,7 +363,7 @@
     },
     "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": "8d0d7eddbca1bdb0",
+      "sha256": "1fbd5eedbf6e341f",
       "path": "skills/verify-workSKILL.md"
     },
     "visual-dashboard": {