bigpowers 2.74.2 → 2.74.4

package/.pi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.74.2",
+  "version": "2.74.4",
   "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/audit-code.md

@@ -134,6 +134,11 @@ In `--gate` mode, print one summary line per checklist section (`PASS Supply Cha
 Gate: READY -> next: commit-message
 Writes: state.yaml handoff.next_skill = commit-message
 
+
+<!-- story: e01s02 -->
+<!-- story: e06s03 -->
+<!-- story: e07s01 -->
+
 ---
 
 # Clean Code Heuristics (Chapter 17)

package/.pi/prompts/deepen-architecture.md

@@ -111,6 +111,10 @@ Run the check before proposing cross-module `source` edges. Convention docs alon
 
 → verify: `test -f specs/import-boundaries.json && bash scripts/check-import-boundaries.sh && echo OK || echo FAIL`
 
+
+
+<!-- story: e07s02 -->
+
 ---
 
 # Deepening

package/.pi/prompts/develop-tdd.md

@@ -118,6 +118,9 @@ Writes: state.yaml handoff.next_skill = verify-work
 
 At story completion, if the story was sized with BCP Plus (13-dimension breakdown), log the `bcp_plus.total` alongside the standard `bcps:` count in the story's tasks.yaml. The breakdown is available from the epic capsule's `bcp_plus_breakdown` field. See `docs/references/bcp-plus.md` for the full methodology and NFR Gate pattern.
 
+
+<!-- story: e02s04 -->
+
 ---
 
 # Develop TDD — Reference

package/.pi/prompts/execute-plan.md

@@ -52,3 +52,9 @@ Suggest: `verify-work` → `run-evals` → `audit-code` → `simulate-agents`
 ## Rules
 
 - **Loop until behavioral correctness is verified**: if a verify command passes but the observed behavior is still wrong, return to step 1 and run the execution cycle again.
+
+
+
+<!-- story: e02s03 -->
+<!-- story: e05s02 -->
+<!-- story: e08s01 -->

package/.pi/prompts/grill-with-docs.md

@@ -28,6 +28,9 @@ description: Doc-grounded variant of grill-me — stress-tests plan assumptions
 
 See [REFERENCE.md](REFERENCE.md) for question templates.
 
+
+<!-- story: e03s01 -->
+
 ---
 
 # Grill With Docs — Question templates

package/.pi/prompts/guard-git.md

@@ -42,6 +42,10 @@ To add or remove patterns or protected branches, edit `pre-tool-use.sh`.
 
 Full JSON examples, merge rules, Antigravity deny-list entries, and test commands: [REFERENCE.md](REFERENCE.md).
 
+
+
+<!-- story: e01s03 -->
+
 ---
 
 # Git guardrails — reference

package/.pi/prompts/model-domain.md

@@ -96,6 +96,10 @@ When the plan touches shared state, async, or multi-threaded code:
 - [ ] Flag **race risks** (check-then-act, non-atomic read-modify-write) with severity.
 - [ ] Record findings in `specs/tech-architecture/tech-stack.md` under `## Concurrency` or in an ADR if architectural.
 
+
+
+<!-- story: e07s03 -->
+
 ---
 
 # ADR Format

package/.pi/prompts/orchestrate-project.md

@@ -66,6 +66,10 @@ All phases complete with artifacts:
 verify: test -f specs/state.yaml && test -f specs/release-plan.yaml && test -f specs/product/SCOPE_LATEST.yaml && ls specs/epics/*.yaml 1>/dev/null && echo "✅ All phases complete"
 ```
 
+
+
+<!-- story: e05s03 -->
+
 ---
 
 # Orchestrate Reference: Phases, Modes, and Workflows

package/.pi/prompts/organize-workspace.md

@@ -75,6 +75,10 @@ Do this when the repo is under Git and the cleanup surfaced **untracked** noise:
 
 See [REFERENCE.md](REFERENCE.md) for shell patterns, `.gitignore` mechanics, and safety checks.
 
+
+
+<!-- story: e04s03 -->
+
 ---
 
 # clean-my-room — reference patterns

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

@@ -92,6 +92,12 @@ After writing capsule tasks, suggest `kickoff-branch` (if not already on a featu
 Gate: READY -> next: kickoff-branch
 Writes: state.yaml handoff.next_skill = kickoff-branch
 
+
+<!-- story: e01s01 -->
+<!-- story: e02s02 -->
+<!-- story: e06s01 -->
+<!-- story: e06s02 -->
+
 ---
 
 # Plan Work — Reference

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

@@ -35,6 +35,9 @@ description: Eval-Driven Development — define capability and regression evals
 
 → verify: `find specs/verifications -name "*-eval-report.md" | wc -l | awk '{if($1>0) print "OK: "$1" eval reports"; else print "MISSING"}'`
 
+
+<!-- story: e02s01 -->
+
 ---
 
 # Run Evals — Reference

package/.pi/prompts/session-state.md

@@ -139,3 +139,7 @@ handoff:
 - **Duplicate Plan**: Don't copy `release-plan.yaml` or epic shards into `state.yaml`.
 - **Stale State**: Forgetting to update `state.yaml` after a major refactor or decision.
 - **Status in release-plan**: Story/epic status lives only in `execution-status.yaml`.
+
+
+<!-- story: e03s03 -->
+<!-- story: e04s01 -->

package/.pi/prompts/slice-tasks.md

@@ -62,3 +62,6 @@ Produce **epic capsule story tasks** in `specs/epics/eNN-slug/` — vertical sli
 ## Verify
 
 → verify: `find specs/epics -name "*-tasks.yaml" | wc -l | awk '{if($1>0) print "OK: "$1" task files"; else print "MISSING"}'`
+
+
+<!-- story: e03s01 -->

package/.pi/prompts/survey-context.md

@@ -129,3 +129,6 @@ Print the current `active_flow` from `specs/state.yaml`, run `bash scripts/valid
 
 Gate: READY -> next: plan-work
 Writes: state.yaml handoff.next_skill = plan-work
+
+
+<!-- story: e03s03 -->

package/.pi/prompts/terse-mode.md

@@ -35,3 +35,7 @@ Example — destructive op:
 > ```
 >
 > Terse resume. Verify backup exist first.
+
+
+
+<!-- story: e04s02 -->

package/.pi/prompts/using-bigpowers.md

@@ -104,3 +104,7 @@ Start the HTTP dashboard with `visual-dashboard` → `GET /api/status?projectDir
 ## After this
 
 Call `survey-context` to read your project's current state and get a personalized recommendation for where to go next.
+
+
+
+<!-- story: e03s02 -->

package/.pi/skills/audit-code/SKILL.md

@@ -136,6 +136,11 @@ In `--gate` mode, print one summary line per checklist section (`PASS Supply Cha
 Gate: READY -> next: commit-message
 Writes: state.yaml handoff.next_skill = commit-message
 
+
+<!-- story: e01s02 -->
+<!-- story: e06s03 -->
+<!-- story: e07s01 -->
+
 ---
 
 # Clean Code Heuristics (Chapter 17)

package/.pi/skills/deepen-architecture/SKILL.md

@@ -113,6 +113,10 @@ Run the check before proposing cross-module `source` edges. Convention docs alon
 
 → verify: `test -f specs/import-boundaries.json && bash scripts/check-import-boundaries.sh && echo OK || echo FAIL`
 
+
+
+<!-- story: e07s02 -->
+
 ---
 
 # Deepening

package/.pi/skills/develop-tdd/SKILL.md

@@ -120,6 +120,9 @@ Writes: state.yaml handoff.next_skill = verify-work
 
 At story completion, if the story was sized with BCP Plus (13-dimension breakdown), log the `bcp_plus.total` alongside the standard `bcps:` count in the story's tasks.yaml. The breakdown is available from the epic capsule's `bcp_plus_breakdown` field. See `docs/references/bcp-plus.md` for the full methodology and NFR Gate pattern.
 
+
+<!-- story: e02s04 -->
+
 ---
 
 # Develop TDD — Reference

package/.pi/skills/execute-plan/SKILL.md

@@ -54,3 +54,9 @@ Suggest: `verify-work` → `run-evals` → `audit-code` → `simulate-agents`
 ## Rules
 
 - **Loop until behavioral correctness is verified**: if a verify command passes but the observed behavior is still wrong, return to step 1 and run the execution cycle again.
+
+
+
+<!-- story: e02s03 -->
+<!-- story: e05s02 -->
+<!-- story: e08s01 -->

package/.pi/skills/grill-with-docs/SKILL.md

@@ -30,6 +30,9 @@ model: opus
 
 See [REFERENCE.md](REFERENCE.md) for question templates.
 
+
+<!-- story: e03s01 -->
+
 ---
 
 # Grill With Docs — Question templates

package/.pi/skills/guard-git/SKILL.md

@@ -44,6 +44,10 @@ To add or remove patterns or protected branches, edit `pre-tool-use.sh`.
 
 Full JSON examples, merge rules, Antigravity deny-list entries, and test commands: [REFERENCE.md](REFERENCE.md).
 
+
+
+<!-- story: e01s03 -->
+
 ---
 
 # Git guardrails — reference

package/.pi/skills/model-domain/SKILL.md

@@ -98,6 +98,10 @@ When the plan touches shared state, async, or multi-threaded code:
 - [ ] Flag **race risks** (check-then-act, non-atomic read-modify-write) with severity.
 - [ ] Record findings in `specs/tech-architecture/tech-stack.md` under `## Concurrency` or in an ADR if architectural.
 
+
+
+<!-- story: e07s03 -->
+
 ---
 
 # ADR Format

package/.pi/skills/orchestrate-project/SKILL.md

@@ -68,6 +68,10 @@ All phases complete with artifacts:
 verify: test -f specs/state.yaml && test -f specs/release-plan.yaml && test -f specs/product/SCOPE_LATEST.yaml && ls specs/epics/*.yaml 1>/dev/null && echo "✅ All phases complete"
 ```
 
+
+
+<!-- story: e05s03 -->
+
 ---
 
 # Orchestrate Reference: Phases, Modes, and Workflows

package/.pi/skills/organize-workspace/SKILL.md

@@ -77,6 +77,10 @@ Do this when the repo is under Git and the cleanup surfaced **untracked** noise:
 
 See [REFERENCE.md](REFERENCE.md) for shell patterns, `.gitignore` mechanics, and safety checks.
 
+
+
+<!-- story: e04s03 -->
+
 ---
 
 # clean-my-room — reference patterns

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

@@ -94,6 +94,12 @@ After writing capsule tasks, suggest `kickoff-branch` (if not already on a featu
 Gate: READY -> next: kickoff-branch
 Writes: state.yaml handoff.next_skill = kickoff-branch
 
+
+<!-- story: e01s01 -->
+<!-- story: e02s02 -->
+<!-- story: e06s01 -->
+<!-- story: e06s02 -->
+
 ---
 
 # Plan Work — Reference

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

@@ -37,6 +37,9 @@ model: sonnet
 
 → verify: `find specs/verifications -name "*-eval-report.md" | wc -l | awk '{if($1>0) print "OK: "$1" eval reports"; else print "MISSING"}'`
 
+
+<!-- story: e02s01 -->
+
 ---
 
 # Run Evals — Reference

package/.pi/skills/session-state/SKILL.md

@@ -141,3 +141,7 @@ handoff:
 - **Duplicate Plan**: Don't copy `release-plan.yaml` or epic shards into `state.yaml`.
 - **Stale State**: Forgetting to update `state.yaml` after a major refactor or decision.
 - **Status in release-plan**: Story/epic status lives only in `execution-status.yaml`.
+
+
+<!-- story: e03s03 -->
+<!-- story: e04s01 -->

package/.pi/skills/slice-tasks/SKILL.md

@@ -64,3 +64,6 @@ Produce **epic capsule story tasks** in `specs/epics/eNN-slug/` — vertical sli
 ## Verify
 
 → verify: `find specs/epics -name "*-tasks.yaml" | wc -l | awk '{if($1>0) print "OK: "$1" task files"; else print "MISSING"}'`
+
+
+<!-- story: e03s01 -->

package/.pi/skills/survey-context/SKILL.md

@@ -131,3 +131,6 @@ Print the current `active_flow` from `specs/state.yaml`, run `bash scripts/valid
 
 Gate: READY -> next: plan-work
 Writes: state.yaml handoff.next_skill = plan-work
+
+
+<!-- story: e03s03 -->

package/.pi/skills/terse-mode/SKILL.md

@@ -37,3 +37,7 @@ Example — destructive op:
 > ```
 >
 > Terse resume. Verify backup exist first.
+
+
+
+<!-- story: e04s02 -->

package/.pi/skills/using-bigpowers/SKILL.md

@@ -106,3 +106,7 @@ Start the HTTP dashboard with `visual-dashboard` → `GET /api/status?projectDir
 ## After this
 
 Call `survey-context` to read your project's current state and get a personalized recommendation for where to go next.
+
+
+
+<!-- story: e03s02 -->

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+## [2.74.4](https://github.com/danielvm-git/bigpowers/compare/v2.74.3...v2.74.4) (2026-07-07)
+
+
+### Bug Fixes
+
+* **sync-skills:** regenerate artifacts after story tag backfill ([35a0455](https://github.com/danielvm-git/bigpowers/commit/35a04555a3067ff3820580c2f08d3d2c071bfd87))
+
+## [2.74.3](https://github.com/danielvm-git/bigpowers/compare/v2.74.2...v2.74.3) (2026-07-07)
+
+
+### Bug Fixes
+
+* **traceability:** backfill story tags for e01 e02 e03 e04 e05 e06 e07 e08 e10 ([2926f8f](https://github.com/danielvm-git/bigpowers/commit/2926f8f49304fa28f09e8eb0c2b63f1c405c4d94))
+
 ## [2.74.2](https://github.com/danielvm-git/bigpowers/compare/v2.74.1...v2.74.2) (2026-07-07)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.74.2",
+  "version": "2.74.4",
   "description": "73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
   "main": "index.js",
   "scripts": {

package/profiles/node-service.md

@@ -26,3 +26,6 @@ Opt-in conventions fragment for `seed-conventions`.
 
 - Never log secrets or full auth tokens
 - Never use `any` on public API types
+
+
+<!-- story: e10s01 -->

package/profiles/solo-git.md

@@ -37,3 +37,6 @@ Run `compose-workflow` or copy `specs/WORKFLOW-solo-git.md` and note in `specs/S
 - Never land without `release-branch` §1–3 gates (tests, coverage, diff review)
 - Never commit on `main` outside `land-branch.sh`
 - Never skip `kickoff-branch` for feature work
+
+
+<!-- story: e10s01 -->

package/profiles/swift.md

@@ -25,3 +25,6 @@ Opt-in conventions fragment for `seed-conventions`. Core bigpowers skills stay l
 
 - Never force-unwrap (`!`) in production paths without documented invariant
 - Never commit `DerivedData/` or `.build/`
+
+
+<!-- story: e10s01 -->

package/profiles/typescript-vue.md

@@ -26,3 +26,6 @@ Opt-in conventions fragment for `seed-conventions`.
 
 - Never use Options API for new components unless extending legacy
 - Never commit `dist/`, `node_modules/`, `.env`
+
+
+<!-- story: e10s01 -->

package/skills/audit-code/SKILL.md

@@ -138,3 +138,8 @@ In `--gate` mode, print one summary line per checklist section (`PASS Supply Cha
 
 Gate: READY -> next: commit-message
 Writes: state.yaml handoff.next_skill = commit-message
+
+
+<!-- story: e01s02 -->
+<!-- story: e06s03 -->
+<!-- story: e07s01 -->

package/skills/deepen-architecture/SKILL.md

@@ -115,3 +115,6 @@ Run the check before proposing cross-module `source` edges. Convention docs alon
 
 → verify: `test -f specs/import-boundaries.json && bash scripts/check-import-boundaries.sh && echo OK || echo FAIL`
 
+
+
+<!-- story: e07s02 -->

package/skills/develop-tdd/SKILL.md

@@ -123,3 +123,6 @@ Writes: state.yaml handoff.next_skill = verify-work
 ## BCP Plus Integration
 
 At story completion, if the story was sized with BCP Plus (13-dimension breakdown), log the `bcp_plus.total` alongside the standard `bcps:` count in the story's tasks.yaml. The breakdown is available from the epic capsule's `bcp_plus_breakdown` field. See `docs/references/bcp-plus.md` for the full methodology and NFR Gate pattern.
+
+
+<!-- story: e02s04 -->

package/skills/execute-plan/SKILL.md

@@ -55,3 +55,8 @@ Suggest: `verify-work` → `run-evals` → `audit-code` → `simulate-agents`
 
 - **Loop until behavioral correctness is verified**: if a verify command passes but the observed behavior is still wrong, return to step 1 and run the execution cycle again.
 
+
+
+<!-- story: e02s03 -->
+<!-- story: e05s02 -->
+<!-- story: e08s01 -->

package/skills/grill-with-docs/SKILL.md

@@ -29,3 +29,6 @@ effort: standard
 → verify: `grep -c 'https\?://' skills/grill-with-docs/SKILL.md | awk '{if($1>=2) print "OK"; else print "NEEDS DOCS"}'`
 
 See [REFERENCE.md](REFERENCE.md) for question templates.
+
+
+<!-- story: e03s01 -->

package/skills/guard-git/SKILL.md

@@ -44,3 +44,6 @@ To add or remove patterns or protected branches, edit `pre-tool-use.sh`.
 
 Full JSON examples, merge rules, Antigravity deny-list entries, and test commands: [REFERENCE.md](REFERENCE.md).
 
+
+
+<!-- story: e01s03 -->

package/skills/model-domain/SKILL.md

@@ -98,3 +98,6 @@ When the plan touches shared state, async, or multi-threaded code:
 - [ ] Flag **race risks** (check-then-act, non-atomic read-modify-write) with severity.
 - [ ] Record findings in `specs/tech-architecture/tech-stack.md` under `## Concurrency` or in an ADR if architectural.
 
+
+
+<!-- story: e07s03 -->

package/skills/orchestrate-project/SKILL.md

@@ -68,3 +68,6 @@ All phases complete with artifacts:
 verify: test -f specs/state.yaml && test -f specs/release-plan.yaml && test -f specs/product/SCOPE_LATEST.yaml && ls specs/epics/*.yaml 1>/dev/null && echo "✅ All phases complete"
 ```
 
+
+
+<!-- story: e05s03 -->

package/skills/organize-workspace/SKILL.md

@@ -77,3 +77,6 @@ Do this when the repo is under Git and the cleanup surfaced **untracked** noise:
 
 See [REFERENCE.md](REFERENCE.md) for shell patterns, `.gitignore` mechanics, and safety checks.
 
+
+
+<!-- story: e04s03 -->

package/skills/plan-work/SKILL.md

@@ -98,3 +98,9 @@ After writing capsule tasks, suggest `kickoff-branch` (if not already on a featu
 
 Gate: READY -> next: kickoff-branch
 Writes: state.yaml handoff.next_skill = kickoff-branch
+
+
+<!-- story: e01s01 -->
+<!-- story: e02s02 -->
+<!-- story: e06s01 -->
+<!-- story: e06s02 -->

package/skills/run-evals/SKILL.md

@@ -37,3 +37,6 @@ effort: standard
 ## Verify
 
 → verify: `find specs/verifications -name "*-eval-report.md" | wc -l | awk '{if($1>0) print "OK: "$1" eval reports"; else print "MISSING"}'`
+
+
+<!-- story: e02s01 -->

package/skills/session-state/SKILL.md

@@ -141,3 +141,7 @@ handoff:
 - **Duplicate Plan**: Don't copy `release-plan.yaml` or epic shards into `state.yaml`.
 - **Stale State**: Forgetting to update `state.yaml` after a major refactor or decision.
 - **Status in release-plan**: Story/epic status lives only in `execution-status.yaml`.
+
+
+<!-- story: e03s03 -->
+<!-- story: e04s01 -->

package/skills/slice-tasks/SKILL.md

@@ -64,3 +64,6 @@ Produce **epic capsule story tasks** in `specs/epics/eNN-slug/` — vertical sli
 ## Verify
 
 → verify: `find specs/epics -name "*-tasks.yaml" | wc -l | awk '{if($1>0) print "OK: "$1" task files"; else print "MISSING"}'`
+
+
+<!-- story: e03s01 -->

package/skills/survey-context/SKILL.md

@@ -131,3 +131,6 @@ Print the current `active_flow` from `specs/state.yaml`, run `bash scripts/valid
 
 Gate: READY -> next: plan-work
 Writes: state.yaml handoff.next_skill = plan-work
+
+
+<!-- story: e03s03 -->

package/skills/terse-mode/SKILL.md

@@ -38,3 +38,6 @@ Example — destructive op:
 >
 > Terse resume. Verify backup exist first.
 
+
+
+<!-- story: e04s02 -->

package/skills/using-bigpowers/SKILL.md

@@ -107,3 +107,6 @@ Start the HTTP dashboard with `visual-dashboard` → `GET /api/status?projectDir
 
 Call `survey-context` to read your project's current state and get a personalized recommendation for where to go next.
 
+
+
+<!-- story: e03s02 -->

package/skills-lock.json

@@ -13,7 +13,7 @@
     },
     "audit-code": {
       "description": "Self-review checklist for the coding agent to run before dispatching a reviewer. Checks CONVENTIONS.md compliance, Boy Scout Rule, test coverage, types, and SOLID. Produces a pass/fail checklist. Use before request-review, before committing, or when user asks for a code quality check.",
-      "sha256": "b4d70ad39eca5902",
+      "sha256": "bbb128254464f8f4",
       "path": "skills/audit-codeSKILL.md"
     },
     "audit-plan": {
@@ -53,7 +53,7 @@
     },
     "deepen-architecture": {
       "description": "Find deepening opportunities in a codebase, informed by the domain language in specs/tech-architecture/tech-stack.md and the decisions in specs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.",
-      "sha256": "591441a980d0447c",
+      "sha256": "a31de1fbd4800060",
       "path": "skills/deepen-architectureSKILL.md"
     },
     "define-language": {
@@ -83,7 +83,7 @@
     },
     "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": "1989004e232bb4be",
+      "sha256": "91928da1d9757094",
       "path": "skills/develop-tddSKILL.md"
     },
     "diagnose-root": {
@@ -123,7 +123,7 @@
     },
     "execute-plan": {
       "description": "Batch-execute tasks from the active epic capsule sequentially, with a human checkpoint after each step. Use when user has an approved plan and wants step-by-step oversight.",
-      "sha256": "259833a91f470ac3",
+      "sha256": "9d6d2bf18e58dafd",
       "path": "skills/execute-planSKILL.md"
     },
     "extract-design": {
@@ -148,12 +148,12 @@
     },
     "grill-with-docs": {
       "description": "Doc-grounded variant of grill-me — stress-tests plan assumptions by fetching and citing real library or API documentation. Every challenge must cite a real URL. Use when the plan depends on a specific library or external API.",
-      "sha256": "e78bea0ebcd9ae9b",
+      "sha256": "bd4267952e492f9c",
       "path": "skills/grill-with-docsSKILL.md"
     },
     "guard-git": {
       "description": "Block dangerous git commands (push, force push, reset --hard, clean, branch -D, checkout/restore .) and enforce Conventional Commits & Branch Protection before an AI agent runs them. Installs hook scripts for Claude Code, Cursor, Cursor CLI, and Gemini CLI; documents Google Antigravity Terminal deny lists. Use when the user wants git safety hooks, to block git push or destructive git in agents, or to mirror the same policy across AI coding tools.",
-      "sha256": "1386000c275dc9ef",
+      "sha256": "9ee881df89273b00",
       "path": "skills/guard-gitSKILL.md"
     },
     "hook-commits": {
@@ -193,17 +193,17 @@
     },
     "model-domain": {
       "description": "Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates specs/tech-architecture/tech-stack.md and specs/adr/ inline as decisions crystallise. Use when user wants to stress-test a plan against their project's domain language and documented decisions.",
-      "sha256": "982bf9996a89183e",
+      "sha256": "857d86ccd37236eb",
       "path": "skills/model-domainSKILL.md"
     },
     "orchestrate-project": {
       "description": "Meta-skill that enforces the 6-phase core loop (discover → elaborate → plan → build → verify → release) with hard gates. Use to coordinate multi-phase projects with guaranteed quality checkpoints. One-time command for the entire project lifecycle.",
-      "sha256": "4e53cd83ac296735",
+      "sha256": "e38e21bb3ad47734",
       "path": "skills/orchestrate-projectSKILL.md"
     },
     "organize-workspace": {
       "description": "Scans the active workspace for disposable artifacts—logs, caches, stale build output, and stray draft markdown—and proposes consolidation of scattered assets. Produces a reviewable list, asks for explicit confirmation before any delete or move, and optionally revises .gitignore. Use when the user says \"clean my room\", \"organize workspace\", \"workspace cleanup\", \"remove temp files\", \"organize assets\", \"gitignore\", or wants a safe tidy pass.",
-      "sha256": "d98b8d6312d94a20",
+      "sha256": "8295d674c2cd461e",
       "path": "skills/organize-workspaceSKILL.md"
     },
     "plan-refactor": {
@@ -223,7 +223,7 @@
     },
     "plan-work": {
       "description": "\"PLANNING SPINE STEP 3 of 3 — Plan the work: write detailed implementation tasks into the active epic capsule (specs/epics/eNN-slug/). Produces countable-story-format .md specs and runnable -tasks.yaml files. Use after slice-tasks (step 2). Not a substitute for scope-work (step 1) or slice-tasks (step 2).\"",
-      "sha256": "4cc87b8c2ae13dae",
+      "sha256": "aabc7f15b46525c2",
       "path": "skills/plan-workSKILL.md"
     },
     "publish-package": {
@@ -268,7 +268,7 @@
     },
     "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": "2fd60cbf4a4e1c63",
+      "sha256": "928eb6bcc1176a40",
       "path": "skills/run-evalsSKILL.md"
     },
     "run-planning": {
@@ -298,7 +298,7 @@
     },
     "session-state": {
       "description": "Track implementation decisions and progress in specs/state.yaml to prevent context rot. Use at the start of a session to load context, and whenever a significant decision is made or a milestone is reached.",
-      "sha256": "4b607fee350390c6",
+      "sha256": "943075be867cd50e",
       "path": "skills/session-stateSKILL.md"
     },
     "setup-environment": {
@@ -313,7 +313,7 @@
     },
     "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": "b89b61159fc619e5",
+      "sha256": "b60f861b88387e4d",
       "path": "skills/slice-tasksSKILL.md"
     },
     "smoke-test": {
@@ -333,12 +333,12 @@
     },
     "survey-context": {
       "description": "Per-task context bootstrap — reads existing specs/ and tech-architecture docs to map the current lifecycle phase and suggest the next skill. Use at the start of any task, when returning after a break, or when unsure what to do next. For deriving a tech-stack doc from scratch, use map-codebase first.",
-      "sha256": "eab179b810784ef4",
+      "sha256": "8beae3b8b7eab0f7",
       "path": "skills/survey-contextSKILL.md"
     },
     "terse-mode": {
       "description": "Fallback ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions, unique names, headless tests), not terser prompts. Use when user says \"caveman mode\", \"terse mode\", \"less tokens\", \"be brief\", or invokes /terse-mode.",
-      "sha256": "bb6fce40d59044a5",
+      "sha256": "952aa309f6287804",
       "path": "skills/terse-modeSKILL.md"
     },
     "trace-requirement": {
@@ -348,7 +348,7 @@
     },
     "using-bigpowers": {
       "description": "One-time bootstrap that introduces the bigpowers skills system, the PMBOK lifecycle arc, and tells you which skill to call first for your situation. Use when starting with bigpowers for the first time, when user asks \"where do I start?\", or when the skills system needs to be explained.",
-      "sha256": "c910fc0ed3482341",
+      "sha256": "332d6468868b759b",
       "path": "skills/using-bigpowersSKILL.md"
     },
     "validate-contracts": {