@funnycode/myclaude 0.1.76 → 0.1.77

package/seed/marketplaces/ecc/skills/skill-comply/tests/test_runner.py

@@ -1,172 +1,172 @@
-"""Tests for runner module — scenario execution + subprocess error handling."""
-
-from __future__ import annotations
-
-import subprocess
-from dataclasses import dataclass
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from scripts.runner import _setup_sandbox, run_scenario
-
-
-@dataclass(frozen=True)
-class _FakeScenario:
-    """Minimal Scenario-like object for runner tests (avoids generator deps)."""
-
-    id: str
-    prompt: str = "do nothing"
-    setup_commands: tuple[str, ...] = ()
-
-
-class TestSetupSandboxSkipsShellBuiltins:
-    """Setup commands containing shell builtins (cd/pushd/popd) must be skipped.
-
-    Regression: subprocess.run(["cd", ...]) raises FileNotFoundError because
-    cd is a shell builtin, not an external binary. Real-world scenarios often
-    include "cd subdir" in setup_commands assuming shell semantics, so the
-    runner must tolerate this rather than crashing the whole scenario.
-    """
-
-    def test_skips_cd(self, tmp_path):
-        scenario = _FakeScenario(
-            id="t1",
-            setup_commands=("cd subdir",),
-        )
-        called_args: list[list[str]] = []
-
-        def fake_run(args, **kwargs):
-            called_args.append(args)
-            return subprocess.CompletedProcess(args=args, returncode=0)
-
-        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
-            _setup_sandbox(tmp_path, scenario)
-
-        # git init runs once; "cd subdir" must NOT be passed to subprocess
-        assert ["git", "init"] in called_args
-        assert ["cd", "subdir"] not in called_args
-
-    def test_skips_pushd_popd(self, tmp_path):
-        scenario = _FakeScenario(
-            id="t2",
-            setup_commands=("pushd dir", "popd"),
-        )
-        called_args: list[list[str]] = []
-
-        def fake_run(args, **kwargs):
-            called_args.append(args)
-            return subprocess.CompletedProcess(args=args, returncode=0)
-
-        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
-            _setup_sandbox(tmp_path, scenario)
-
-        assert ["pushd", "dir"] not in called_args
-        assert ["popd"] not in called_args
-
-    def test_tolerates_missing_executable(self, tmp_path):
-        """A scenario referencing an unavailable tool must not crash setup."""
-        scenario = _FakeScenario(
-            id="t3",
-            setup_commands=("nonexistent-tool-xyz arg",),
-        )
-
-        def fake_run(args, **kwargs):
-            if args[0] == "nonexistent-tool-xyz":
-                raise FileNotFoundError(2, "No such file or directory")
-            return subprocess.CompletedProcess(args=args, returncode=0)
-
-        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
-            # Must NOT raise — missing tools are skipped, not fatal
-            _setup_sandbox(tmp_path, scenario)
-
-    def test_real_commands_still_run(self, tmp_path):
-        """Skip logic must not break legitimate setup commands."""
-        scenario = _FakeScenario(
-            id="t4",
-            setup_commands=("touch file.txt", "cd ignored", "echo hi"),
-        )
-        called_args: list[list[str]] = []
-
-        def fake_run(args, **kwargs):
-            called_args.append(args)
-            return subprocess.CompletedProcess(args=args, returncode=0)
-
-        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
-            _setup_sandbox(tmp_path, scenario)
-
-        # Real commands present, cd absent
-        assert ["touch", "file.txt"] in called_args
-        assert ["echo", "hi"] in called_args
-        assert ["cd", "ignored"] not in called_args
-
-
-class TestRunScenarioMaxTurnsTermination:
-    """rc=1 with terminal_reason=max_turns is graceful termination, not failure.
-
-    claude -p returns rc=1 when --max-turns is reached, but the stream-json
-    output is still valid. Treating this as RuntimeError aborts scenarios
-    that would have produced useful observations. Detect the marker in stdout
-    and downgrade rc=1 + max_turns to non-fatal.
-    """
-
-    def test_rc1_with_max_turns_marker_returns_normally(self, tmp_path, monkeypatch):
-        scenario = _FakeScenario(id="mt1", prompt="long task", setup_commands=())
-
-        # Skip sandbox setup side effects
-        monkeypatch.setattr("scripts.runner._setup_sandbox", lambda *a, **kw: None)
-
-        max_turns_stdout = (
-            '{"type":"system","subtype":"init","session_id":"s1"}\n'
-            '{"type":"result","terminal_reason":"max_turns"}\n'
-        )
-
-        fake_result = subprocess.CompletedProcess(
-            args=["claude"], returncode=1, stdout=max_turns_stdout, stderr=""
-        )
-
-        with patch("scripts.runner.subprocess.run", return_value=fake_result):
-            # Must NOT raise — max_turns is graceful termination
-            run_scenario(scenario, model="haiku")
-
-    def test_rc1_without_max_turns_marker_still_raises(self, tmp_path, monkeypatch):
-        """Real failures (rc≠0 with no max_turns marker) must still raise."""
-        scenario = _FakeScenario(id="mt2", prompt="oops", setup_commands=())
-        monkeypatch.setattr("scripts.runner._setup_sandbox", lambda *a, **kw: None)
-
-        fake_result = subprocess.CompletedProcess(
-            args=["claude"], returncode=1, stdout="", stderr="auth error"
-        )
-
-        with patch("scripts.runner.subprocess.run", return_value=fake_result):
-            with pytest.raises(RuntimeError, match="claude -p failed"):
-                run_scenario(scenario, model="haiku")
-
-
-class TestRunScenarioErrorIncludesStdoutTail:
-    """Error messages must include stdout tail, not only stderr.
-
-    When claude -p fails inside an LLM call, useful diagnostic context often
-    appears in stdout (partial stream-json events, model error JSON), not
-    stderr. Including stdout tail in the RuntimeError message dramatically
-    improves debug-ability without adding any new dependency.
-    """
-
-    def test_error_message_contains_stdout_tail(self, tmp_path, monkeypatch):
-        scenario = _FakeScenario(id="e1", prompt="x", setup_commands=())
-        monkeypatch.setattr("scripts.runner._setup_sandbox", lambda *a, **kw: None)
-
-        diagnostic_marker = "DIAG_STDOUT_MARKER_xyz123"
-        fake_result = subprocess.CompletedProcess(
-            args=["claude"],
-            returncode=2,
-            stdout=f"some context {diagnostic_marker} more text",
-            stderr="generic error",
-        )
-
-        with patch("scripts.runner.subprocess.run", return_value=fake_result):
-            with pytest.raises(RuntimeError) as excinfo:
-                run_scenario(scenario, model="haiku")
-
-        # Stdout marker MUST appear in the error message
-        assert diagnostic_marker in str(excinfo.value)
+"""Tests for runner module — scenario execution + subprocess error handling."""
+
+from __future__ import annotations
+
+import subprocess
+from dataclasses import dataclass
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from scripts.runner import _setup_sandbox, run_scenario
+
+
+@dataclass(frozen=True)
+class _FakeScenario:
+    """Minimal Scenario-like object for runner tests (avoids generator deps)."""
+
+    id: str
+    prompt: str = "do nothing"
+    setup_commands: tuple[str, ...] = ()
+
+
+class TestSetupSandboxSkipsShellBuiltins:
+    """Setup commands containing shell builtins (cd/pushd/popd) must be skipped.
+
+    Regression: subprocess.run(["cd", ...]) raises FileNotFoundError because
+    cd is a shell builtin, not an external binary. Real-world scenarios often
+    include "cd subdir" in setup_commands assuming shell semantics, so the
+    runner must tolerate this rather than crashing the whole scenario.
+    """
+
+    def test_skips_cd(self, tmp_path):
+        scenario = _FakeScenario(
+            id="t1",
+            setup_commands=("cd subdir",),
+        )
+        called_args: list[list[str]] = []
+
+        def fake_run(args, **kwargs):
+            called_args.append(args)
+            return subprocess.CompletedProcess(args=args, returncode=0)
+
+        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
+            _setup_sandbox(tmp_path, scenario)
+
+        # git init runs once; "cd subdir" must NOT be passed to subprocess
+        assert ["git", "init"] in called_args
+        assert ["cd", "subdir"] not in called_args
+
+    def test_skips_pushd_popd(self, tmp_path):
+        scenario = _FakeScenario(
+            id="t2",
+            setup_commands=("pushd dir", "popd"),
+        )
+        called_args: list[list[str]] = []
+
+        def fake_run(args, **kwargs):
+            called_args.append(args)
+            return subprocess.CompletedProcess(args=args, returncode=0)
+
+        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
+            _setup_sandbox(tmp_path, scenario)
+
+        assert ["pushd", "dir"] not in called_args
+        assert ["popd"] not in called_args
+
+    def test_tolerates_missing_executable(self, tmp_path):
+        """A scenario referencing an unavailable tool must not crash setup."""
+        scenario = _FakeScenario(
+            id="t3",
+            setup_commands=("nonexistent-tool-xyz arg",),
+        )
+
+        def fake_run(args, **kwargs):
+            if args[0] == "nonexistent-tool-xyz":
+                raise FileNotFoundError(2, "No such file or directory")
+            return subprocess.CompletedProcess(args=args, returncode=0)
+
+        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
+            # Must NOT raise — missing tools are skipped, not fatal
+            _setup_sandbox(tmp_path, scenario)
+
+    def test_real_commands_still_run(self, tmp_path):
+        """Skip logic must not break legitimate setup commands."""
+        scenario = _FakeScenario(
+            id="t4",
+            setup_commands=("touch file.txt", "cd ignored", "echo hi"),
+        )
+        called_args: list[list[str]] = []
+
+        def fake_run(args, **kwargs):
+            called_args.append(args)
+            return subprocess.CompletedProcess(args=args, returncode=0)
+
+        with patch("scripts.runner.subprocess.run", side_effect=fake_run):
+            _setup_sandbox(tmp_path, scenario)
+
+        # Real commands present, cd absent
+        assert ["touch", "file.txt"] in called_args
+        assert ["echo", "hi"] in called_args
+        assert ["cd", "ignored"] not in called_args
+
+
+class TestRunScenarioMaxTurnsTermination:
+    """rc=1 with terminal_reason=max_turns is graceful termination, not failure.
+
+    claude -p returns rc=1 when --max-turns is reached, but the stream-json
+    output is still valid. Treating this as RuntimeError aborts scenarios
+    that would have produced useful observations. Detect the marker in stdout
+    and downgrade rc=1 + max_turns to non-fatal.
+    """
+
+    def test_rc1_with_max_turns_marker_returns_normally(self, tmp_path, monkeypatch):
+        scenario = _FakeScenario(id="mt1", prompt="long task", setup_commands=())
+
+        # Skip sandbox setup side effects
+        monkeypatch.setattr("scripts.runner._setup_sandbox", lambda *a, **kw: None)
+
+        max_turns_stdout = (
+            '{"type":"system","subtype":"init","session_id":"s1"}\n'
+            '{"type":"result","terminal_reason":"max_turns"}\n'
+        )
+
+        fake_result = subprocess.CompletedProcess(
+            args=["claude"], returncode=1, stdout=max_turns_stdout, stderr=""
+        )
+
+        with patch("scripts.runner.subprocess.run", return_value=fake_result):
+            # Must NOT raise — max_turns is graceful termination
+            run_scenario(scenario, model="haiku")
+
+    def test_rc1_without_max_turns_marker_still_raises(self, tmp_path, monkeypatch):
+        """Real failures (rc≠0 with no max_turns marker) must still raise."""
+        scenario = _FakeScenario(id="mt2", prompt="oops", setup_commands=())
+        monkeypatch.setattr("scripts.runner._setup_sandbox", lambda *a, **kw: None)
+
+        fake_result = subprocess.CompletedProcess(
+            args=["claude"], returncode=1, stdout="", stderr="auth error"
+        )
+
+        with patch("scripts.runner.subprocess.run", return_value=fake_result):
+            with pytest.raises(RuntimeError, match="claude -p failed"):
+                run_scenario(scenario, model="haiku")
+
+
+class TestRunScenarioErrorIncludesStdoutTail:
+    """Error messages must include stdout tail, not only stderr.
+
+    When claude -p fails inside an LLM call, useful diagnostic context often
+    appears in stdout (partial stream-json events, model error JSON), not
+    stderr. Including stdout tail in the RuntimeError message dramatically
+    improves debug-ability without adding any new dependency.
+    """
+
+    def test_error_message_contains_stdout_tail(self, tmp_path, monkeypatch):
+        scenario = _FakeScenario(id="e1", prompt="x", setup_commands=())
+        monkeypatch.setattr("scripts.runner._setup_sandbox", lambda *a, **kw: None)
+
+        diagnostic_marker = "DIAG_STDOUT_MARKER_xyz123"
+        fake_result = subprocess.CompletedProcess(
+            args=["claude"],
+            returncode=2,
+            stdout=f"some context {diagnostic_marker} more text",
+            stderr="generic error",
+        )
+
+        with patch("scripts.runner.subprocess.run", return_value=fake_result):
+            with pytest.raises(RuntimeError) as excinfo:
+                run_scenario(scenario, model="haiku")
+
+        # Stdout marker MUST appear in the error message
+        assert diagnostic_marker in str(excinfo.value)

package/seed/marketplaces/ecc/skills/skill-scout/SKILL.md

@@ -1,140 +1,140 @@
----
-name: skill-scout
-description: Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
-origin: community
----
-
-# Skill Scout
-
-Use this skill before creating a new skill. The goal is to avoid duplicating
-existing community or marketplace work, while still vetting anything external
-before adoption.
-
-Source: salvaged from stale community PR #1232 by `redminwang`.
-
-## When to Use
-
-- The user says "create a skill", "build a skill", "make a skill", or "new
-  skill".
-- The user asks "is there a skill for X?" or "does a skill exist that does Y?"
-- The user describes a workflow and you are about to suggest creating a new
-  skill.
-- The user wants to fork or extend an existing skill.
-
-If the user explicitly says to skip search or create from scratch, acknowledge
-that and proceed with the requested creation workflow.
-
-## How It Works
-
-### Step 1 - Capture Intent
-
-Extract:
-
-- The task the skill should perform.
-- The trigger conditions for using it.
-- The domain, tools, frameworks, or data sources involved.
-- Three to five search keywords plus useful synonyms.
-
-### Step 2 - Search Local Sources
-
-Search installed and marketplace skill names first. Local sources are preferred
-because they are already part of the user's environment.
-
-```bash
-find ~/.claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | grep -iE "keyword|synonym"
-find ~/.claude/plugins/marketplaces -path '*/skills/*/SKILL.md' 2>/dev/null | grep -iE "keyword|synonym"
-```
-
-Then search frontmatter descriptions:
-
-```bash
-grep -RilE "keyword|synonym" ~/.claude/skills ~/.claude/plugins/marketplaces 2>/dev/null
-```
-
-### Step 3 - Search Remote Sources
-
-Use available GitHub and web search tools. Prefer concise queries:
-
-```bash
-gh search repos "claude code skill keyword" --limit 10 --sort stars
-gh search code "name: keyword" --filename SKILL.md --limit 10
-```
-
-For web search, use at most three targeted queries such as:
-
-```text
-"claude code skill" keyword
-"SKILL.md" keyword
-"everything-claude-code" keyword
-```
-
-### Step 4 - Vet External Matches
-
-Before recommending any external skill for adoption or forking:
-
-- Read the `SKILL.md` frontmatter and instructions.
-- Look for unexpected shell commands, file writes, network calls, credential
-  handling, or package installs.
-- Check whether the repository appears maintained.
-- Prefer copying into a fresh local branch and reviewing the diff over editing
-  marketplace originals.
-
-### Step 5 - Rank Results
-
-Rank candidates by:
-
-1. Exact keyword match in the skill name.
-2. Keyword or synonym match in description.
-3. Local installed or marketplace source.
-4. Maintained GitHub source with recent activity.
-5. Web-only mention.
-
-Cap the final list at 10 results.
-
-### Step 6 - Present Decision Options
-
-Give the user a short table:
-
-| Option | Meaning |
-| --- | --- |
-| Use existing | Invoke or install a matching skill as-is. |
-| Fork or extend | Copy the closest skill and modify it. |
-| Create fresh | Build a new skill after confirming no close match exists. |
-
-Only create a new skill after the user chooses that path or after the search
-finds no close match.
-
-## Examples
-
-### Result Table
-
-```markdown
-| # | Skill | Source | Why it matches | Gap |
-| --- | --- | --- | --- | --- |
-| 1 | article-writing | Local ECC | Drafts articles and guides | Not focused on release notes |
-| 2 | content-engine | Local ECC | Multi-format content workflow | Heavier than needed |
-| 3 | blog-writer | GitHub | Blog writing skill with recent commits | Needs security review |
-```
-
-### User-Facing Summary
-
-```markdown
-I found two close local matches and one external candidate. The closest fit is
-`article-writing`; it covers drafting and revision, but it does not include the
-release-note checklist you asked for. I can either use it as-is, fork it into a
-release-note variant, or create a fresh skill.
-```
-
-## Anti-Patterns
-
-- Do not jump directly to new skill creation when a search is reasonable.
-- Do not install external skills without reading them first.
-- Do not present a long unranked list of weak matches.
-- Do not treat web-only mentions as trusted sources.
-- Do not edit installed marketplace originals in place.
-
-## Related
-
-- `search-first` - General search-before-building workflow.
-- `skill-stocktake` - Audit installed skills for health, duplicates, and gaps.
-- `agent-sort` - Categorize and organize existing agents and skills.
+---
+name: skill-scout
+description: Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
+origin: community
+---
+
+# Skill Scout
+
+Use this skill before creating a new skill. The goal is to avoid duplicating
+existing community or marketplace work, while still vetting anything external
+before adoption.
+
+Source: salvaged from stale community PR #1232 by `redminwang`.
+
+## When to Use
+
+- The user says "create a skill", "build a skill", "make a skill", or "new
+  skill".
+- The user asks "is there a skill for X?" or "does a skill exist that does Y?"
+- The user describes a workflow and you are about to suggest creating a new
+  skill.
+- The user wants to fork or extend an existing skill.
+
+If the user explicitly says to skip search or create from scratch, acknowledge
+that and proceed with the requested creation workflow.
+
+## How It Works
+
+### Step 1 - Capture Intent
+
+Extract:
+
+- The task the skill should perform.
+- The trigger conditions for using it.
+- The domain, tools, frameworks, or data sources involved.
+- Three to five search keywords plus useful synonyms.
+
+### Step 2 - Search Local Sources
+
+Search installed and marketplace skill names first. Local sources are preferred
+because they are already part of the user's environment.
+
+```bash
+find ~/.claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | grep -iE "keyword|synonym"
+find ~/.claude/plugins/marketplaces -path '*/skills/*/SKILL.md' 2>/dev/null | grep -iE "keyword|synonym"
+```
+
+Then search frontmatter descriptions:
+
+```bash
+grep -RilE "keyword|synonym" ~/.claude/skills ~/.claude/plugins/marketplaces 2>/dev/null
+```
+
+### Step 3 - Search Remote Sources
+
+Use available GitHub and web search tools. Prefer concise queries:
+
+```bash
+gh search repos "claude code skill keyword" --limit 10 --sort stars
+gh search code "name: keyword" --filename SKILL.md --limit 10
+```
+
+For web search, use at most three targeted queries such as:
+
+```text
+"claude code skill" keyword
+"SKILL.md" keyword
+"everything-claude-code" keyword
+```
+
+### Step 4 - Vet External Matches
+
+Before recommending any external skill for adoption or forking:
+
+- Read the `SKILL.md` frontmatter and instructions.
+- Look for unexpected shell commands, file writes, network calls, credential
+  handling, or package installs.
+- Check whether the repository appears maintained.
+- Prefer copying into a fresh local branch and reviewing the diff over editing
+  marketplace originals.
+
+### Step 5 - Rank Results
+
+Rank candidates by:
+
+1. Exact keyword match in the skill name.
+2. Keyword or synonym match in description.
+3. Local installed or marketplace source.
+4. Maintained GitHub source with recent activity.
+5. Web-only mention.
+
+Cap the final list at 10 results.
+
+### Step 6 - Present Decision Options
+
+Give the user a short table:
+
+| Option | Meaning |
+| --- | --- |
+| Use existing | Invoke or install a matching skill as-is. |
+| Fork or extend | Copy the closest skill and modify it. |
+| Create fresh | Build a new skill after confirming no close match exists. |
+
+Only create a new skill after the user chooses that path or after the search
+finds no close match.
+
+## Examples
+
+### Result Table
+
+```markdown
+| # | Skill | Source | Why it matches | Gap |
+| --- | --- | --- | --- | --- |
+| 1 | article-writing | Local ECC | Drafts articles and guides | Not focused on release notes |
+| 2 | content-engine | Local ECC | Multi-format content workflow | Heavier than needed |
+| 3 | blog-writer | GitHub | Blog writing skill with recent commits | Needs security review |
+```
+
+### User-Facing Summary
+
+```markdown
+I found two close local matches and one external candidate. The closest fit is
+`article-writing`; it covers drafting and revision, but it does not include the
+release-note checklist you asked for. I can either use it as-is, fork it into a
+release-note variant, or create a fresh skill.
+```
+
+## Anti-Patterns
+
+- Do not jump directly to new skill creation when a search is reasonable.
+- Do not install external skills without reading them first.
+- Do not present a long unranked list of weak matches.
+- Do not treat web-only mentions as trusted sources.
+- Do not edit installed marketplace originals in place.
+
+## Related
+
+- `search-first` - General search-before-building workflow.
+- `skill-stocktake` - Audit installed skills for health, duplicates, and gaps.
+- `agent-sort` - Categorize and organize existing agents and skills.