@heyai-rules/pilo-masterkit 2.1.0 → 3.1.0

package/.agent/skills/skill-comply/tests/test-parser.py

@@ -1,90 +1,90 @@
-"""Tests for parser module — JSONL trace and YAML spec parsing."""
-
-from pathlib import Path
-
-import pytest
-
-from scripts.parser import (
-    ComplianceSpec,
-    Detector,
-    ObservationEvent,
-    Step,
-    parse_spec,
-    parse_trace,
-)
-
-FIXTURES = Path(__file__).parent.parent / "fixtures"
-
-
-class TestParseTrace:
-    def test_parses_compliant_trace(self) -> None:
-        events = parse_trace(FIXTURES / "compliant_trace.jsonl")
-        assert len(events) == 5
-        assert all(isinstance(e, ObservationEvent) for e in events)
-
-    def test_events_sorted_by_timestamp(self) -> None:
-        events = parse_trace(FIXTURES / "compliant_trace.jsonl")
-        timestamps = [e.timestamp for e in events]
-        assert timestamps == sorted(timestamps)
-
-    def test_event_fields(self) -> None:
-        events = parse_trace(FIXTURES / "compliant_trace.jsonl")
-        first = events[0]
-        assert first.tool == "Write"
-        assert first.session == "sess-001"
-        assert "test_fib.py" in first.input
-        assert first.output == "File created"
-
-    def test_parses_noncompliant_trace(self) -> None:
-        events = parse_trace(FIXTURES / "noncompliant_trace.jsonl")
-        assert len(events) == 3
-        assert "src/fib.py" in events[0].input
-
-    def test_empty_file_returns_empty_list(self, tmp_path: Path) -> None:
-        empty = tmp_path / "empty.jsonl"
-        empty.write_text("")
-        events = parse_trace(empty)
-        assert events == []
-
-    def test_nonexistent_file_raises(self) -> None:
-        with pytest.raises(FileNotFoundError):
-            parse_trace(Path("/nonexistent/trace.jsonl"))
-
-
-class TestParseSpec:
-    def test_parses_tdd_spec(self) -> None:
-        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
-        assert isinstance(spec, ComplianceSpec)
-        assert spec.id == "tdd-workflow"
-        assert len(spec.steps) == 5
-
-    def test_step_fields(self) -> None:
-        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
-        first = spec.steps[0]
-        assert isinstance(first, Step)
-        assert first.id == "write_test"
-        assert first.required is True
-        assert isinstance(first.detector, Detector)
-        assert "test file" in first.detector.description
-        assert first.detector.before_step == "write_impl"
-
-    def test_optional_detector_fields(self) -> None:
-        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
-        write_test = spec.steps[0]
-        assert write_test.detector.after_step is None
-
-        run_test_red = spec.steps[1]
-        assert run_test_red.detector.after_step == "write_test"
-        assert run_test_red.detector.before_step == "write_impl"
-
-    def test_scoring_threshold(self) -> None:
-        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
-        assert spec.threshold_promote_to_hook == 0.6
-
-    def test_required_vs_optional_steps(self) -> None:
-        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
-        required = [s for s in spec.steps if s.required]
-        optional = [s for s in spec.steps if not s.required]
-        assert len(required) == 4
-        assert len(optional) == 1
-        assert optional[0].id == "refactor"
+"""Tests for parser module — JSONL trace and YAML spec parsing."""
+
+from pathlib import Path
+
+import pytest
+
+from scripts.parser import (
+    ComplianceSpec,
+    Detector,
+    ObservationEvent,
+    Step,
+    parse_spec,
+    parse_trace,
+)
+
+FIXTURES = Path(__file__).parent.parent / "fixtures"
+
+
+class TestParseTrace:
+    def test_parses_compliant_trace(self) -> None:
+        events = parse_trace(FIXTURES / "compliant_trace.jsonl")
+        assert len(events) == 5
+        assert all(isinstance(e, ObservationEvent) for e in events)
+
+    def test_events_sorted_by_timestamp(self) -> None:
+        events = parse_trace(FIXTURES / "compliant_trace.jsonl")
+        timestamps = [e.timestamp for e in events]
+        assert timestamps == sorted(timestamps)
+
+    def test_event_fields(self) -> None:
+        events = parse_trace(FIXTURES / "compliant_trace.jsonl")
+        first = events[0]
+        assert first.tool == "Write"
+        assert first.session == "sess-001"
+        assert "test_fib.py" in first.input
+        assert first.output == "File created"
+
+    def test_parses_noncompliant_trace(self) -> None:
+        events = parse_trace(FIXTURES / "noncompliant_trace.jsonl")
+        assert len(events) == 3
+        assert "src/fib.py" in events[0].input
+
+    def test_empty_file_returns_empty_list(self, tmp_path: Path) -> None:
+        empty = tmp_path / "empty.jsonl"
+        empty.write_text("")
+        events = parse_trace(empty)
+        assert events == []
+
+    def test_nonexistent_file_raises(self) -> None:
+        with pytest.raises(FileNotFoundError):
+            parse_trace(Path("/nonexistent/trace.jsonl"))
+
+
+class TestParseSpec:
+    def test_parses_tdd_spec(self) -> None:
+        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
+        assert isinstance(spec, ComplianceSpec)
+        assert spec.id == "tdd-workflow"
+        assert len(spec.steps) == 5
+
+    def test_step_fields(self) -> None:
+        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
+        first = spec.steps[0]
+        assert isinstance(first, Step)
+        assert first.id == "write_test"
+        assert first.required is True
+        assert isinstance(first.detector, Detector)
+        assert "test file" in first.detector.description
+        assert first.detector.before_step == "write_impl"
+
+    def test_optional_detector_fields(self) -> None:
+        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
+        write_test = spec.steps[0]
+        assert write_test.detector.after_step is None
+
+        run_test_red = spec.steps[1]
+        assert run_test_red.detector.after_step == "write_test"
+        assert run_test_red.detector.before_step == "write_impl"
+
+    def test_scoring_threshold(self) -> None:
+        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
+        assert spec.threshold_promote_to_hook == 0.6
+
+    def test_required_vs_optional_steps(self) -> None:
+        spec = parse_spec(FIXTURES / "tdd_spec.yaml")
+        required = [s for s in spec.steps if s.required]
+        optional = [s for s in spec.steps if not s.required]
+        assert len(required) == 4
+        assert len(optional) == 1
+        assert optional[0].id == "refactor"

package/.agent/skills/skill-stocktake/SKILL.md

@@ -1,193 +1,193 @@
----
-description: "Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation."
-origin: ECC
----
-
-# skill-stocktake
-
-Slash command (`/skill-stocktake`) that audits all Claude skills and commands using a quality checklist + AI holistic judgment. Supports two modes: Quick Scan for recently changed skills, and Full Stocktake for a complete review.
-
-## Scope
-
-The command targets the following paths **relative to the directory where it is invoked**:
-
-| Path | Description |
-|------|-------------|
-| `~/.claude/skills/` | Global skills (all projects) |
-| `{cwd}/.claude/skills/` | Project-level skills (if the directory exists) |
-
-**At the start of Phase 1, the command explicitly lists which paths were found and scanned.**
-
-### Targeting a specific project
-
-To include project-level skills, run from that project's root directory:
-
-```bash
-cd ~/path/to/my-project
-/skill-stocktake
-```
-
-If the project has no `.claude/skills/` directory, only global skills and commands are evaluated.
-
-## Modes
-
-| Mode | Trigger | Duration |
-|------|---------|---------|
-| Quick Scan | `results.json` exists (default) | 5–10 min |
-| Full Stocktake | `results.json` absent, or `/skill-stocktake full` | 20–30 min |
-
-**Results cache:** `~/.claude/skills/skill-stocktake/results.json`
-
-## Quick Scan Flow
-
-Re-evaluate only skills that have changed since the last run (5–10 min).
-
-1. Read `~/.claude/skills/skill-stocktake/results.json`
-2. Run: `bash ~/.claude/skills/skill-stocktake/scripts/quick-diff.sh \
-         ~/.claude/skills/skill-stocktake/results.json`
-   (Project dir is auto-detected from `$PWD/.claude/skills`; pass it explicitly only if needed)
-3. If output is `[]`: report "No changes since last run." and stop
-4. Re-evaluate only those changed files using the same Phase 2 criteria
-5. Carry forward unchanged skills from previous results
-6. Output only the diff
-7. Run: `bash ~/.claude/skills/skill-stocktake/scripts/save-results.sh \
-         ~/.claude/skills/skill-stocktake/results.json <<< "$EVAL_RESULTS"`
-
-## Full Stocktake Flow
-
-### Phase 1 — Inventory
-
-Run: `bash ~/.claude/skills/skill-stocktake/scripts/scan.sh`
-
-The script enumerates skill files, extracts frontmatter, and collects UTC mtimes.
-Project dir is auto-detected from `$PWD/.claude/skills`; pass it explicitly only if needed.
-Present the scan summary and inventory table from the script output:
-
-```
-Scanning:
-  ✓ ~/.claude/skills/         (17 files)
-  ✗ {cwd}/.claude/skills/    (not found — global skills only)
-```
-
-| Skill | 7d use | 30d use | Description |
-|-------|--------|---------|-------------|
-
-### Phase 2 — Quality Evaluation
-
-Launch an Agent tool subagent (**general-purpose agent**) with the full inventory and checklist:
-
-```text
-Agent(
-  subagent_type="general-purpose",
-  prompt="
-Evaluate the following skill inventory against the checklist.
-
-[INVENTORY]
-
-[CHECKLIST]
-
-Return JSON for each skill:
-{ \"verdict\": \"Keep\"|\"Improve\"|\"Update\"|\"Retire\"|\"Merge into [X]\", \"reason\": \"...\" }
-"
-)
-```
-
-The subagent reads each skill, applies the checklist, and returns per-skill JSON:
-
-`{ "verdict": "Keep"|"Improve"|"Update"|"Retire"|"Merge into [X]", "reason": "..." }`
-
-**Chunk guidance:** Process ~20 skills per subagent invocation to keep context manageable. Save intermediate results to `results.json` (`status: "in_progress"`) after each chunk.
-
-After all skills are evaluated: set `status: "completed"`, proceed to Phase 3.
-
-**Resume detection:** If `status: "in_progress"` is found on startup, resume from the first unevaluated skill.
-
-Each skill is evaluated against this checklist:
-
-```
-- [ ] Content overlap with other skills checked
-- [ ] Overlap with MEMORY.md / CLAUDE.md checked
-- [ ] Freshness of technical references verified (use WebSearch if tool names / CLI flags / APIs are present)
-- [ ] Usage frequency considered
-```
-
-Verdict criteria:
-
-| Verdict | Meaning |
-|---------|---------|
-| Keep | Useful and current |
-| Improve | Worth keeping, but specific improvements needed |
-| Update | Referenced technology is outdated (verify with WebSearch) |
-| Retire | Low quality, stale, or cost-asymmetric |
-| Merge into [X] | Substantial overlap with another skill; name the merge target |
-
-Evaluation is **holistic AI judgment** — not a numeric rubric. Guiding dimensions:
-- **Actionability**: code examples, commands, or steps that let you act immediately
-- **Scope fit**: name, trigger, and content are aligned; not too broad or narrow
-- **Uniqueness**: value not replaceable by MEMORY.md / CLAUDE.md / another skill
-- **Currency**: technical references work in the current environment
-
-**Reason quality requirements** — the `reason` field must be self-contained and decision-enabling:
-- Do NOT write "unchanged" alone — always restate the core evidence
-- For **Retire**: state (1) what specific defect was found, (2) what covers the same need instead
-  - Bad: `"Superseded"`
-  - Good: `"disable-model-invocation: true already set; superseded by continuous-learning-v2 which covers all the same patterns plus confidence scoring. No unique content remains."`
-- For **Merge**: name the target and describe what content to integrate
-  - Bad: `"Overlaps with X"`
-  - Good: `"42-line thin content; Step 4 of chatlog-to-article already covers the same workflow. Integrate the 'article angle' tip as a note in that skill."`
-- For **Improve**: describe the specific change needed (what section, what action, target size if relevant)
-  - Bad: `"Too long"`
-  - Good: `"276 lines; Section 'Framework Comparison' (L80–140) duplicates ai-era-architecture-principles; delete it to reach ~150 lines."`
-- For **Keep** (mtime-only change in Quick Scan): restate the original verdict rationale, do not write "unchanged"
-  - Bad: `"Unchanged"`
-  - Good: `"mtime updated but content unchanged. Unique Python reference explicitly imported by rules/python/; no overlap found."`
-
-### Phase 3 — Summary Table
-
-| Skill | 7d use | Verdict | Reason |
-|-------|--------|---------|--------|
-
-### Phase 4 — Consolidation
-
-1. **Retire / Merge**: present detailed justification per file before confirming with user:
-   - What specific problem was found (overlap, staleness, broken references, etc.)
-   - What alternative covers the same functionality (for Retire: which existing skill/rule; for Merge: the target file and what content to integrate)
-   - Impact of removal (any dependent skills, MEMORY.md references, or workflows affected)
-2. **Improve**: present specific improvement suggestions with rationale:
-   - What to change and why (e.g., "trim 430→200 lines because sections X/Y duplicate python-patterns")
-   - User decides whether to act
-3. **Update**: present updated content with sources checked
-4. Check MEMORY.md line count; propose compression if >100 lines
-
-## Results File Schema
-
-`~/.claude/skills/skill-stocktake/results.json`:
-
-**`evaluated_at`**: Must be set to the actual UTC time of evaluation completion.
-Obtain via Bash: `date -u +%Y-%m-%dT%H:%M:%SZ`. Never use a date-only approximation like `T00:00:00Z`.
-
-```json
-{
-  "evaluated_at": "2026-02-21T10:00:00Z",
-  "mode": "full",
-  "batch_progress": {
-    "total": 80,
-    "evaluated": 80,
-    "status": "completed"
-  },
-  "skills": {
-    "skill-name": {
-      "path": "~/.claude/skills/skill-name/SKILL.md",
-      "verdict": "Keep",
-      "reason": "Concrete, actionable, unique value for X workflow",
-      "mtime": "2026-01-15T08:30:00Z"
-    }
-  }
-}
-```
-
-## Notes
-
-- Evaluation is blind: the same checklist applies to all skills regardless of origin (ECC, self-authored, auto-extracted)
-- Archive / delete operations always require explicit user confirmation
-- No verdict branching by skill origin
+---
+description: "Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation."
+origin: ECC
+---
+
+# skill-stocktake
+
+Slash command (`/skill-stocktake`) that audits all Claude skills and commands using a quality checklist + AI holistic judgment. Supports two modes: Quick Scan for recently changed skills, and Full Stocktake for a complete review.
+
+## Scope
+
+The command targets the following paths **relative to the directory where it is invoked**:
+
+| Path | Description |
+|------|-------------|
+| `~/.claude/skills/` | Global skills (all projects) |
+| `{cwd}/.claude/skills/` | Project-level skills (if the directory exists) |
+
+**At the start of Phase 1, the command explicitly lists which paths were found and scanned.**
+
+### Targeting a specific project
+
+To include project-level skills, run from that project's root directory:
+
+```bash
+cd ~/path/to/my-project
+/skill-stocktake
+```
+
+If the project has no `.claude/skills/` directory, only global skills and commands are evaluated.
+
+## Modes
+
+| Mode | Trigger | Duration |
+|------|---------|---------|
+| Quick Scan | `results.json` exists (default) | 5–10 min |
+| Full Stocktake | `results.json` absent, or `/skill-stocktake full` | 20–30 min |
+
+**Results cache:** `~/.claude/skills/skill-stocktake/results.json`
+
+## Quick Scan Flow
+
+Re-evaluate only skills that have changed since the last run (5–10 min).
+
+1. Read `~/.claude/skills/skill-stocktake/results.json`
+2. Run: `bash ~/.claude/skills/skill-stocktake/scripts/quick-diff.sh \
+         ~/.claude/skills/skill-stocktake/results.json`
+   (Project dir is auto-detected from `$PWD/.claude/skills`; pass it explicitly only if needed)
+3. If output is `[]`: report "No changes since last run." and stop
+4. Re-evaluate only those changed files using the same Phase 2 criteria
+5. Carry forward unchanged skills from previous results
+6. Output only the diff
+7. Run: `bash ~/.claude/skills/skill-stocktake/scripts/save-results.sh \
+         ~/.claude/skills/skill-stocktake/results.json <<< "$EVAL_RESULTS"`
+
+## Full Stocktake Flow
+
+### Phase 1 — Inventory
+
+Run: `bash ~/.claude/skills/skill-stocktake/scripts/scan.sh`
+
+The script enumerates skill files, extracts frontmatter, and collects UTC mtimes.
+Project dir is auto-detected from `$PWD/.claude/skills`; pass it explicitly only if needed.
+Present the scan summary and inventory table from the script output:
+
+```
+Scanning:
+  ✓ ~/.claude/skills/         (17 files)
+  ✗ {cwd}/.claude/skills/    (not found — global skills only)
+```
+
+| Skill | 7d use | 30d use | Description |
+|-------|--------|---------|-------------|
+
+### Phase 2 — Quality Evaluation
+
+Launch an Agent tool subagent (**general-purpose agent**) with the full inventory and checklist:
+
+```text
+Agent(
+  subagent_type="general-purpose",
+  prompt="
+Evaluate the following skill inventory against the checklist.
+
+[INVENTORY]
+
+[CHECKLIST]
+
+Return JSON for each skill:
+{ \"verdict\": \"Keep\"|\"Improve\"|\"Update\"|\"Retire\"|\"Merge into [X]\", \"reason\": \"...\" }
+"
+)
+```
+
+The subagent reads each skill, applies the checklist, and returns per-skill JSON:
+
+`{ "verdict": "Keep"|"Improve"|"Update"|"Retire"|"Merge into [X]", "reason": "..." }`
+
+**Chunk guidance:** Process ~20 skills per subagent invocation to keep context manageable. Save intermediate results to `results.json` (`status: "in_progress"`) after each chunk.
+
+After all skills are evaluated: set `status: "completed"`, proceed to Phase 3.
+
+**Resume detection:** If `status: "in_progress"` is found on startup, resume from the first unevaluated skill.
+
+Each skill is evaluated against this checklist:
+
+```
+- [ ] Content overlap with other skills checked
+- [ ] Overlap with MEMORY.md / CLAUDE.md checked
+- [ ] Freshness of technical references verified (use WebSearch if tool names / CLI flags / APIs are present)
+- [ ] Usage frequency considered
+```
+
+Verdict criteria:
+
+| Verdict | Meaning |
+|---------|---------|
+| Keep | Useful and current |
+| Improve | Worth keeping, but specific improvements needed |
+| Update | Referenced technology is outdated (verify with WebSearch) |
+| Retire | Low quality, stale, or cost-asymmetric |
+| Merge into [X] | Substantial overlap with another skill; name the merge target |
+
+Evaluation is **holistic AI judgment** — not a numeric rubric. Guiding dimensions:
+- **Actionability**: code examples, commands, or steps that let you act immediately
+- **Scope fit**: name, trigger, and content are aligned; not too broad or narrow
+- **Uniqueness**: value not replaceable by MEMORY.md / CLAUDE.md / another skill
+- **Currency**: technical references work in the current environment
+
+**Reason quality requirements** — the `reason` field must be self-contained and decision-enabling:
+- Do NOT write "unchanged" alone — always restate the core evidence
+- For **Retire**: state (1) what specific defect was found, (2) what covers the same need instead
+  - Bad: `"Superseded"`
+  - Good: `"disable-model-invocation: true already set; superseded by continuous-learning-v2 which covers all the same patterns plus confidence scoring. No unique content remains."`
+- For **Merge**: name the target and describe what content to integrate
+  - Bad: `"Overlaps with X"`
+  - Good: `"42-line thin content; Step 4 of chatlog-to-article already covers the same workflow. Integrate the 'article angle' tip as a note in that skill."`
+- For **Improve**: describe the specific change needed (what section, what action, target size if relevant)
+  - Bad: `"Too long"`
+  - Good: `"276 lines; Section 'Framework Comparison' (L80–140) duplicates ai-era-architecture-principles; delete it to reach ~150 lines."`
+- For **Keep** (mtime-only change in Quick Scan): restate the original verdict rationale, do not write "unchanged"
+  - Bad: `"Unchanged"`
+  - Good: `"mtime updated but content unchanged. Unique Python reference explicitly imported by rules/python/; no overlap found."`
+
+### Phase 3 — Summary Table
+
+| Skill | 7d use | Verdict | Reason |
+|-------|--------|---------|--------|
+
+### Phase 4 — Consolidation
+
+1. **Retire / Merge**: present detailed justification per file before confirming with user:
+   - What specific problem was found (overlap, staleness, broken references, etc.)
+   - What alternative covers the same functionality (for Retire: which existing skill/rule; for Merge: the target file and what content to integrate)
+   - Impact of removal (any dependent skills, MEMORY.md references, or workflows affected)
+2. **Improve**: present specific improvement suggestions with rationale:
+   - What to change and why (e.g., "trim 430→200 lines because sections X/Y duplicate python-patterns")
+   - User decides whether to act
+3. **Update**: present updated content with sources checked
+4. Check MEMORY.md line count; propose compression if >100 lines
+
+## Results File Schema
+
+`~/.claude/skills/skill-stocktake/results.json`:
+
+**`evaluated_at`**: Must be set to the actual UTC time of evaluation completion.
+Obtain via Bash: `date -u +%Y-%m-%dT%H:%M:%SZ`. Never use a date-only approximation like `T00:00:00Z`.
+
+```json
+{
+  "evaluated_at": "2026-02-21T10:00:00Z",
+  "mode": "full",
+  "batch_progress": {
+    "total": 80,
+    "evaluated": 80,
+    "status": "completed"
+  },
+  "skills": {
+    "skill-name": {
+      "path": "~/.claude/skills/skill-name/SKILL.md",
+      "verdict": "Keep",
+      "reason": "Concrete, actionable, unique value for X workflow",
+      "mtime": "2026-01-15T08:30:00Z"
+    }
+  }
+}
+```
+
+## Notes
+
+- Evaluation is blind: the same checklist applies to all skills regardless of origin (ECC, self-authored, auto-extracted)
+- Archive / delete operations always require explicit user confirmation
+- No verdict branching by skill origin