bigpowers 2.14.0 → 2.15.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/.pi/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bigpowers",
3
- "version": "2.14.0",
3
+ "version": "2.15.0",
4
4
  "description": "67 skills — 61 agent skills for spec-driven, test-first software development by solo developers",
5
5
  "keywords": [
6
6
  "pi-package"
@@ -43,6 +43,7 @@ After step 5 (verify-work) completes successfully, step 6 runs `audit-code` auto
43
43
  2. **Pass (exit 0):** All checklist sections pass → advance to step 7 (commit-message). Record `epic_cycle.audit_result: pass` in `state.yaml`.
44
44
  3. **Fail (exit 1):** One or more checklist sections fail → **reset `epic_cycle.current_step` to `4`** (develop-tdd) and add the failing section IDs to `completed_steps` as `"1,2,3,4,5,6(fail: ...)"`. Record `epic_cycle.audit_result: fail` in `state.yaml`. Do NOT advance past step 6 until audit passes.
45
45
  4. **Audit artifact:** Full audit report saved to `specs/verifications/AUDIT-<epic>-<story>.md` regardless of pass/fail, for reviewer traceability.
46
+ 5. **Enforce F.I.R.S.T:** After audit-code passes, run `enforce-first --quick` on new/modified tests. Append F.I.R.S.T violations (if any) to the audit report. Failing F.I.R.S.T criteria trigger the same loop-back to step 4.
46
47
 
47
48
  ## Handoff
48
49
 
@@ -11,6 +11,11 @@ Apply the F.I.R.S.T rubric (Uncle Bob, Clean Code Chapter 9) to evaluate and imp
11
11
 
12
12
  This skill is typically invoked internally by `develop-tdd` during the test-writing phase. It can also be run standalone on an existing test suite.
13
13
 
14
+ ## Modes
15
+
16
+ - Default: full F.I.R.S.T audit (all 5 criteria)
17
+ - --quick: Check F (Fast), I (Independent), and S (Self-Validating) only. Used by build-epic step 6 as a mechanical gate after audit-code. Skips R (Repeatable) and T (Timely) which require contextual judgment.
18
+
14
19
  ## The F.I.R.S.T Rubric
15
20
 
16
21
  ### F — Fast
@@ -45,6 +45,7 @@ After step 5 (verify-work) completes successfully, step 6 runs `audit-code` auto
45
45
  2. **Pass (exit 0):** All checklist sections pass → advance to step 7 (commit-message). Record `epic_cycle.audit_result: pass` in `state.yaml`.
46
46
  3. **Fail (exit 1):** One or more checklist sections fail → **reset `epic_cycle.current_step` to `4`** (develop-tdd) and add the failing section IDs to `completed_steps` as `"1,2,3,4,5,6(fail: ...)"`. Record `epic_cycle.audit_result: fail` in `state.yaml`. Do NOT advance past step 6 until audit passes.
47
47
  4. **Audit artifact:** Full audit report saved to `specs/verifications/AUDIT-<epic>-<story>.md` regardless of pass/fail, for reviewer traceability.
48
+ 5. **Enforce F.I.R.S.T:** After audit-code passes, run `enforce-first --quick` on new/modified tests. Append F.I.R.S.T violations (if any) to the audit report. Failing F.I.R.S.T criteria trigger the same loop-back to step 4.
48
49
 
49
50
  ## Handoff
50
51
 
@@ -13,6 +13,11 @@ Apply the F.I.R.S.T rubric (Uncle Bob, Clean Code Chapter 9) to evaluate and imp
13
13
 
14
14
  This skill is typically invoked internally by `develop-tdd` during the test-writing phase. It can also be run standalone on an existing test suite.
15
15
 
16
+ ## Modes
17
+
18
+ - Default: full F.I.R.S.T audit (all 5 criteria)
19
+ - --quick: Check F (Fast), I (Independent), and S (Self-Validating) only. Used by build-epic step 6 as a mechanical gate after audit-code. Skips R (Repeatable) and T (Timely) which require contextual judgment.
20
+
16
21
  ## The F.I.R.S.T Rubric
17
22
 
18
23
  ### F — Fast
package/CHANGELOG.md CHANGED
@@ -1,3 +1,10 @@
1
+ # [2.15.0](https://github.com/danielvm-git/bigpowers/compare/v2.14.0...v2.15.0) (2026-06-21)
2
+
3
+
4
+ ### Features
5
+
6
+ * **e18s02:** enforce-first --quick mode in build-epic step 6 ([abdea30](https://github.com/danielvm-git/bigpowers/commit/abdea303fa79d7babb89e979a4b7480b1b3a6946))
7
+
1
8
  # [2.14.0](https://github.com/danielvm-git/bigpowers/compare/v2.13.0...v2.14.0) (2026-06-21)
2
9
 
3
10
 
package/SKILL-INDEX.md CHANGED
@@ -3,7 +3,7 @@
3
3
  > **DO NOT EDIT** — This file is auto-generated by `scripts/generate-skill-index.sh`.
4
4
  > Edit `SKILL.md` source files or `skills-lock.json` instead. Run `bash scripts/sync-skills.sh` to regenerate.
5
5
 
6
- **Generated:** 2026-06-21T21:27:17Z
6
+ **Generated:** 2026-06-21T21:31:53Z
7
7
  **Skills:** 67
8
8
 
9
9
  ---
@@ -44,6 +44,7 @@ After step 5 (verify-work) completes successfully, step 6 runs `audit-code` auto
44
44
  2. **Pass (exit 0):** All checklist sections pass → advance to step 7 (commit-message). Record `epic_cycle.audit_result: pass` in `state.yaml`.
45
45
  3. **Fail (exit 1):** One or more checklist sections fail → **reset `epic_cycle.current_step` to `4`** (develop-tdd) and add the failing section IDs to `completed_steps` as `"1,2,3,4,5,6(fail: ...)"`. Record `epic_cycle.audit_result: fail` in `state.yaml`. Do NOT advance past step 6 until audit passes.
46
46
  4. **Audit artifact:** Full audit report saved to `specs/verifications/AUDIT-<epic>-<story>.md` regardless of pass/fail, for reviewer traceability.
47
+ 5. **Enforce F.I.R.S.T:** After audit-code passes, run `enforce-first --quick` on new/modified tests. Append F.I.R.S.T violations (if any) to the audit report. Failing F.I.R.S.T criteria trigger the same loop-back to step 4.
47
48
 
48
49
  ## Handoff
49
50
 
@@ -12,6 +12,11 @@ Apply the F.I.R.S.T rubric (Uncle Bob, Clean Code Chapter 9) to evaluate and imp
12
12
 
13
13
  This skill is typically invoked internally by `develop-tdd` during the test-writing phase. It can also be run standalone on an existing test suite.
14
14
 
15
+ ## Modes
16
+
17
+ - Default: full F.I.R.S.T audit (all 5 criteria)
18
+ - --quick: Check F (Fast), I (Independent), and S (Self-Validating) only. Used by build-epic step 6 as a mechanical gate after audit-code. Skips R (Repeatable) and T (Timely) which require contextual judgment.
19
+
15
20
  ## The F.I.R.S.T Rubric
16
21
 
17
22
  ### F — Fast
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bigpowers",
3
- "version": "2.14.0",
3
+ "version": "2.15.0",
4
4
  "description": "61 agent skills for spec-driven, test-first software development by solo developers",
5
5
  "main": "index.js",
6
6
  "scripts": {
package/skills-lock.json CHANGED
@@ -18,7 +18,7 @@
18
18
  },
19
19
  "build-epic": {
20
20
  "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.",
21
- "sha256": "ac7c8fc9740c4beb",
21
+ "sha256": "d33ba1c86463d91f",
22
22
  "path": "build-epic/SKILL.md"
23
23
  },
24
24
  "change-request": {
@@ -98,7 +98,7 @@
98
98
  },
99
99
  "enforce-first": {
100
100
  "description": "Apply the F.I.R.S.T test quality rubric (Fast, Independent, Repeatable, Self-Validating, Timely) to a test suite or individual tests. Use when develop-tdd is writing tests, when test quality needs to be checked, or when user mentions F.I.R.S.T or \"test quality\".",
101
- "sha256": "ca11eb77909d92b4",
101
+ "sha256": "cafd0bd664a74a2d",
102
102
  "path": "enforce-first/SKILL.md"
103
103
  },
104
104
  "evolve-skill": {