@phuc1403/musketeer 0.7.0 → 0.9.0

package/template/.claude/skills/skill-creator/references/eval-schemas.md

@@ -1,121 +1,121 @@
-# Eval JSON Schemas
-
-All JSON schemas used by the eval infrastructure.
-
-## evals.json — Test Cases
-
-```json
-{
-  "skill_name": "example-skill",
-  "evals": [
-    {
-      "id": 0,
-      "prompt": "User task prompt",
-      "expected_output": "Description of correct output",
-      "files": [],
-      "assertions": [
-        {"id": "assertion-1", "text": "Output contains valid JSON"},
-        {"id": "assertion-2", "text": "All rows processed correctly"}
-      ]
-    }
-  ]
-}
-```
-
-## eval_metadata.json — Per-Test Metadata
-
-```json
-{
-  "eval_id": 0,
-  "eval_name": "descriptive-name",
-  "prompt": "Task prompt",
-  "assertions": [
-    {"id": "assertion-1", "text": "Output contains valid JSON"}
-  ]
-}
-```
-
-## grading.json — Grader Output
-
-```json
-{
-  "expectations": [
-    {"text": "Output contains valid JSON", "passed": true, "evidence": "File output.json parsed successfully"}
-  ],
-  "pass_rate": 0.75,
-  "metrics": {
-    "execution_time_ms": 12500,
-    "tokens_used": 8400,
-    "tool_calls": 5
-  },
-  "claims": ["Additional observations beyond assertions"],
-  "critique": "Evaluation feedback on criteria quality"
-}
-```
-
-**Field names are exact** — viewer depends on: `text` (not name), `passed` (not met), `evidence` (not details).
-
-## benchmark.json — Aggregated Stats
-
-```json
-{
-  "metadata": {"skill_name": "example", "timestamp": "..."},
-  "runs": [{"eval_id": 0, "config": "with_skill", "pass_rate": 0.85}],
-  "summaries": {
-    "with_skill": {"mean_pass_rate": 0.85, "stddev": 0.05},
-    "without_skill": {"mean_pass_rate": 0.45, "stddev": 0.10}
-  },
-  "deltas": {"pass_rate_delta": 0.40, "tokens_delta": -2000}
-}
-```
-
-## timing.json — Duration & Tokens
-
-```json
-{
-  "total_tokens": 84852,
-  "duration_ms": 23332,
-  "total_duration_seconds": 23.3
-}
-```
-
-Must capture immediately from subagent notifications — data not persisted elsewhere.
-
-## feedback.json — Human Reviews
-
-```json
-{
-  "reviews": [
-    {"run_id": "eval-0-with_skill", "feedback": "User comment", "timestamp": "..."}
-  ],
-  "status": "complete"
-}
-```
-
-## comparison.json — Blind A/B Results
-
-```json
-{
-  "winner": "output_a",
-  "reasoning": "Detailed explanation with citations",
-  "scores": {"output_a": 8, "output_b": 6},
-  "content_score": {"correctness": 4, "completeness": 5},
-  "structure_score": {"organization": 4, "formatting": 3}
-}
-```
-
-## history.json — Optimization Iterations
-
-```json
-{
-  "versions": [
-    {
-      "description": "Current description text",
-      "pass_rate": 0.85,
-      "precision": 0.90,
-      "recall": 0.80,
-      "iteration": 1
-    }
-  ]
-}
-```
+# Eval JSON Schemas
+
+All JSON schemas used by the eval infrastructure.
+
+## evals.json — Test Cases
+
+```json
+{
+  "skill_name": "example-skill",
+  "evals": [
+    {
+      "id": 0,
+      "prompt": "User task prompt",
+      "expected_output": "Description of correct output",
+      "files": [],
+      "assertions": [
+        {"id": "assertion-1", "text": "Output contains valid JSON"},
+        {"id": "assertion-2", "text": "All rows processed correctly"}
+      ]
+    }
+  ]
+}
+```
+
+## eval_metadata.json — Per-Test Metadata
+
+```json
+{
+  "eval_id": 0,
+  "eval_name": "descriptive-name",
+  "prompt": "Task prompt",
+  "assertions": [
+    {"id": "assertion-1", "text": "Output contains valid JSON"}
+  ]
+}
+```
+
+## grading.json — Grader Output
+
+```json
+{
+  "expectations": [
+    {"text": "Output contains valid JSON", "passed": true, "evidence": "File output.json parsed successfully"}
+  ],
+  "pass_rate": 0.75,
+  "metrics": {
+    "execution_time_ms": 12500,
+    "tokens_used": 8400,
+    "tool_calls": 5
+  },
+  "claims": ["Additional observations beyond assertions"],
+  "critique": "Evaluation feedback on criteria quality"
+}
+```
+
+**Field names are exact** — viewer depends on: `text` (not name), `passed` (not met), `evidence` (not details).
+
+## benchmark.json — Aggregated Stats
+
+```json
+{
+  "metadata": {"skill_name": "example", "timestamp": "..."},
+  "runs": [{"eval_id": 0, "config": "with_skill", "pass_rate": 0.85}],
+  "summaries": {
+    "with_skill": {"mean_pass_rate": 0.85, "stddev": 0.05},
+    "without_skill": {"mean_pass_rate": 0.45, "stddev": 0.10}
+  },
+  "deltas": {"pass_rate_delta": 0.40, "tokens_delta": -2000}
+}
+```
+
+## timing.json — Duration & Tokens
+
+```json
+{
+  "total_tokens": 84852,
+  "duration_ms": 23332,
+  "total_duration_seconds": 23.3
+}
+```
+
+Must capture immediately from subagent notifications — data not persisted elsewhere.
+
+## feedback.json — Human Reviews
+
+```json
+{
+  "reviews": [
+    {"run_id": "eval-0-with_skill", "feedback": "User comment", "timestamp": "..."}
+  ],
+  "status": "complete"
+}
+```
+
+## comparison.json — Blind A/B Results
+
+```json
+{
+  "winner": "output_a",
+  "reasoning": "Detailed explanation with citations",
+  "scores": {"output_a": 8, "output_b": 6},
+  "content_score": {"correctness": 4, "completeness": 5},
+  "structure_score": {"organization": 4, "formatting": 3}
+}
+```
+
+## history.json — Optimization Iterations
+
+```json
+{
+  "versions": [
+    {
+      "description": "Current description text",
+      "pass_rate": 0.85,
+      "precision": 0.90,
+      "recall": 0.80,
+      "iteration": 1
+    }
+  ]
+}
+```

package/template/.claude/skills/skill-creator/references/mcp-skills-integration.md

@@ -1,71 +1,71 @@
-# MCP + Skills Integration
-
-## The Kitchen Analogy
-
-- **MCP** provides the professional kitchen: access to tools, ingredients, equipment
-- **Skills** provide the recipes: step-by-step instructions to create something valuable
-
-Together, they enable users to accomplish complex tasks without figuring out every step.
-
-## How They Work Together
-
-| MCP (Connectivity) | Skills (Knowledge) |
-|---|---|
-| Connects Claude to services (Notion, Asana, Linear) | Teaches Claude how to use services effectively |
-| Provides real-time data access and tool invocation | Captures workflows and best practices |
-| What Claude *can* do | How Claude *should* do it |
-
-## Without Skills (MCP only)
-
-- Users connect MCP but don't know what to do next
-- Support tickets: "how do I do X with your integration?"
-- Each conversation starts from scratch
-- Inconsistent results (users prompt differently)
-- Users blame connector when issue is workflow guidance
-
-## With Skills (MCP + Skills)
-
-- Pre-built workflows activate automatically
-- Consistent, reliable tool usage
-- Best practices embedded in every interaction
-- Lower learning curve for integration
-
-## Building MCP-Enhanced Skills
-
-### Key Techniques
-
-1. **Reference correct MCP tool names** — tool names are case-sensitive
-2. **Include error handling** for common MCP issues (connection refused, auth expired)
-3. **Embed domain expertise** users would otherwise need to specify each time
-4. **Coordinate multiple MCP calls** in sequence with data passing between steps
-5. **Add fallback instructions** when MCP is unavailable
-
-### Example: MCP Enhancement Skill Structure
-
-```markdown
-## Prerequisites
-- [Service] MCP server must be connected (Settings > Extensions)
-- Valid API key with [specific scopes]
-
-## Workflow: [Task Name]
-### Step 1: Fetch Context
-Call `mcp_tool_name` with parameters from user input
-### Step 2: Process
-Apply domain rules to MCP response
-### Step 3: Execute
-Call `mcp_action_tool` with processed data
-### Step 4: Verify
-Confirm action completed, report results
-
-## Troubleshooting
-If "Connection refused": verify MCP server running
-If auth error: check API key in Settings > Extensions
-```
-
-## Positioning MCP + Skills
-
-**Focus on outcomes:**
-> "The ProjectHub skill enables teams to set up complete project workspaces in seconds — instead of 30 minutes on manual setup."
-
-**Not features:**
-> ~~"The ProjectHub skill is a folder containing YAML frontmatter that calls our MCP server tools."~~
+# MCP + Skills Integration
+
+## The Kitchen Analogy
+
+- **MCP** provides the professional kitchen: access to tools, ingredients, equipment
+- **Skills** provide the recipes: step-by-step instructions to create something valuable
+
+Together, they enable users to accomplish complex tasks without figuring out every step.
+
+## How They Work Together
+
+| MCP (Connectivity) | Skills (Knowledge) |
+|---|---|
+| Connects Claude to services (Notion, Asana, Linear) | Teaches Claude how to use services effectively |
+| Provides real-time data access and tool invocation | Captures workflows and best practices |
+| What Claude *can* do | How Claude *should* do it |
+
+## Without Skills (MCP only)
+
+- Users connect MCP but don't know what to do next
+- Support tickets: "how do I do X with your integration?"
+- Each conversation starts from scratch
+- Inconsistent results (users prompt differently)
+- Users blame connector when issue is workflow guidance
+
+## With Skills (MCP + Skills)
+
+- Pre-built workflows activate automatically
+- Consistent, reliable tool usage
+- Best practices embedded in every interaction
+- Lower learning curve for integration
+
+## Building MCP-Enhanced Skills
+
+### Key Techniques
+
+1. **Reference correct MCP tool names** — tool names are case-sensitive
+2. **Include error handling** for common MCP issues (connection refused, auth expired)
+3. **Embed domain expertise** users would otherwise need to specify each time
+4. **Coordinate multiple MCP calls** in sequence with data passing between steps
+5. **Add fallback instructions** when MCP is unavailable
+
+### Example: MCP Enhancement Skill Structure
+
+```markdown
+## Prerequisites
+- [Service] MCP server must be connected (Settings > Extensions)
+- Valid API key with [specific scopes]
+
+## Workflow: [Task Name]
+### Step 1: Fetch Context
+Call `mcp_tool_name` with parameters from user input
+### Step 2: Process
+Apply domain rules to MCP response
+### Step 3: Execute
+Call `mcp_action_tool` with processed data
+### Step 4: Verify
+Confirm action completed, report results
+
+## Troubleshooting
+If "Connection refused": verify MCP server running
+If auth error: check API key in Settings > Extensions
+```
+
+## Positioning MCP + Skills
+
+**Focus on outcomes:**
+> "The ProjectHub skill enables teams to set up complete project workspaces in seconds — instead of 30 minutes on manual setup."
+
+**Not features:**
+> ~~"The ProjectHub skill is a folder containing YAML frontmatter that calls our MCP server tools."~~

package/template/.claude/skills/skill-creator/references/metadata-quality-criteria.md

@@ -1,94 +1,94 @@
-# Metadata Quality Criteria
-
-Metadata determines when Claude activates the skill. Poor metadata = wrong activation or missed activation.
-
-## Name Field
-
-**Format:** use either `skill-name` or `namespace:skill-name` (for example `ck:plan`), all lowercase
-
-**Good Examples:**
-- `pdf-editor` - clear domain
-- `ck:bigquery-analyst` - namespaced variant
-- `frontend-webapp-builder` - specific function
-
-**Bad Examples:**
-- `helper` - too generic
-- `mySkill` - wrong case
-- `pdf` - too short, unclear purpose
-
-## Description Field
-
-**Constraint:** ≤1024 characters (official max). Shorter is better for token efficiency, but longer descriptions trigger more reliably.
-
-**Purpose:** Trigger automatic activation during implementation. Be "pushy" — include specific trigger contexts.
-
-### Good Descriptions
-
-Specific, action-oriented, includes use cases:
-
-```yaml
-description: Build React/TypeScript frontends with modern patterns. Use for components, Suspense, lazy loading, performance optimization.
-```
-
-```yaml
-description: Process PDFs with rotation, splitting, merging. Use for document manipulation, page extraction, PDF conversion.
-```
-
-### Bad Descriptions
-
-Too generic or educational:
-
-```yaml
-description: A skill for working with databases.  # Too vague
-```
-
-```yaml
-description: This skill helps you understand how React works.  # Educational, not actionable
-```
-
-## Trigger Precision
-
-Description should answer: "What phrases would a user say that should trigger this skill?"
-
-**Example for `image-editor` skill:**
-- "Remove red-eye from this image"
-- "Rotate this photo 90 degrees"
-- "Crop the background out"
-
-Include these trigger phrases/actions in description.
-
-## Third-Person Style
-
-**Correct:** "This skill should be used when..."
-**Wrong:** "Use this skill when..." or "You should use this..."
-
-## Validation
-
-Check with packaging script:
-
-```bash
-scripts/package_skill.py <skill-path>
-```
-
-Fails if:
-- Missing name or description
-- Description exceeds 1024 characters
-- Name exceeds 64 characters
-- Invalid YAML syntax
-
-## Pushy Descriptions (Anti-Undertriggering)
-
-**Problem:** Generic descriptions cause skills to activate too rarely.
-
-```yaml
-# BAD — undertriggers
-description: Data processing skill
-
-# GOOD — triggers reliably
-description: Process CSV files and tabular data. Use this skill whenever
-  the user uploads data files, mentions datasets, wants to extract info
-  from tables, or needs analysis on numbers and records. Make sure to
-  use this skill whenever data transformation is needed.
-```
-
-Include "Use this skill whenever..." and list specific trigger contexts.
+# Metadata Quality Criteria
+
+Metadata determines when Claude activates the skill. Poor metadata = wrong activation or missed activation.
+
+## Name Field
+
+**Format:** use either `skill-name` or `namespace:skill-name` (for example `ck:plan`), all lowercase
+
+**Good Examples:**
+- `pdf-editor` - clear domain
+- `ck:bigquery-analyst` - namespaced variant
+- `frontend-webapp-builder` - specific function
+
+**Bad Examples:**
+- `helper` - too generic
+- `mySkill` - wrong case
+- `pdf` - too short, unclear purpose
+
+## Description Field
+
+**Constraint:** ≤1024 characters (official max). Shorter is better for token efficiency, but longer descriptions trigger more reliably.
+
+**Purpose:** Trigger automatic activation during implementation. Be "pushy" — include specific trigger contexts.
+
+### Good Descriptions
+
+Specific, action-oriented, includes use cases:
+
+```yaml
+description: Build React/TypeScript frontends with modern patterns. Use for components, Suspense, lazy loading, performance optimization.
+```
+
+```yaml
+description: Process PDFs with rotation, splitting, merging. Use for document manipulation, page extraction, PDF conversion.
+```
+
+### Bad Descriptions
+
+Too generic or educational:
+
+```yaml
+description: A skill for working with databases.  # Too vague
+```
+
+```yaml
+description: This skill helps you understand how React works.  # Educational, not actionable
+```
+
+## Trigger Precision
+
+Description should answer: "What phrases would a user say that should trigger this skill?"
+
+**Example for `image-editor` skill:**
+- "Remove red-eye from this image"
+- "Rotate this photo 90 degrees"
+- "Crop the background out"
+
+Include these trigger phrases/actions in description.
+
+## Third-Person Style
+
+**Correct:** "This skill should be used when..."
+**Wrong:** "Use this skill when..." or "You should use this..."
+
+## Validation
+
+Check with packaging script:
+
+```bash
+scripts/package_skill.py <skill-path>
+```
+
+Fails if:
+- Missing name or description
+- Description exceeds 1024 characters
+- Name exceeds 64 characters
+- Invalid YAML syntax
+
+## Pushy Descriptions (Anti-Undertriggering)
+
+**Problem:** Generic descriptions cause skills to activate too rarely.
+
+```yaml
+# BAD — undertriggers
+description: Data processing skill
+
+# GOOD — triggers reliably
+description: Process CSV files and tabular data. Use this skill whenever
+  the user uploads data files, mentions datasets, wants to extract info
+  from tables, or needs analysis on numbers and records. Make sure to
+  use this skill whenever data transformation is needed.
+```
+
+Include "Use this skill whenever..." and list specific trigger contexts.