superkit-mcp-server 1.2.1 → 1.2.3

package/skills/tech/alpha-vantage/references/time-series.md

@@ -1,157 +1,157 @@
-# Time Series Stock Data APIs
-
-Base URL: `https://www.alphavantage.co/query`
-
-## GLOBAL_QUOTE — Latest Price
-
-Returns the latest price and volume for a ticker.
-
-**Required:** `symbol`
-
-```python
-data = av_get("GLOBAL_QUOTE", symbol="IBM")
-q = data["Global Quote"]
-# q keys: "01. symbol", "02. open", "03. high", "04. low", "05. price",
-#          "06. volume", "07. latest trading day", "08. previous close",
-#          "09. change", "10. change percent"
-print(q["05. price"])  # "217.51"
-```
-
-## TIME_SERIES_INTRADAY — Intraday OHLCV (Premium)
-
-Returns intraday candles with 20+ years of history.
-
-**Required:** `symbol`, `interval` (`1min`, `5min`, `15min`, `30min`, `60min`)
-
-**Optional:**
-- `adjusted` — default `true` (split/dividend adjusted)
-- `extended_hours` — default `true` (pre/post market included)
-- `month` — format `YYYY-MM` (query specific historical month)
-- `outputsize` — `compact` (100 points) or `full` (30 days / full month)
-- `entitlement` — `realtime` or `delayed` (15-min delayed)
-- `datatype` — `json` or `csv`
-
-```python
-data = av_get("TIME_SERIES_INTRADAY", symbol="IBM", interval="5min", outputsize="compact")
-ts = data["Time Series (5min)"]
-# Key: "2024-01-15 16:00:00" → {"1. open": "...", "2. high": ..., "3. low": ..., "4. close": ..., "5. volume": ...}
-
-# Get specific historical month
-data = av_get("TIME_SERIES_INTRADAY", symbol="IBM", interval="5min", month="2023-06", outputsize="full")
-```
-
-## TIME_SERIES_DAILY — Daily OHLCV
-
-**Required:** `symbol`
-
-**Optional:** `outputsize` (`compact`=100 points, `full`=20+ years), `datatype`
-
-```python
-data = av_get("TIME_SERIES_DAILY", symbol="IBM", outputsize="full")
-ts = data["Time Series (Daily)"]
-# Key: "2024-01-15" → {"1. open", "2. high", "3. low", "4. close", "5. volume"}
-```
-
-## TIME_SERIES_DAILY_ADJUSTED — Daily OHLCV with Adjustments (Premium)
-
-Includes split coefficient and dividend amount.
-
-**Required:** `symbol`
-
-**Optional:** `outputsize`, `datatype`
-
-```python
-data = av_get("TIME_SERIES_DAILY_ADJUSTED", symbol="IBM")
-ts = data["Time Series (Daily)"]
-# Extra keys: "6. adjusted close", "7. dividend amount", "8. split coefficient"
-```
-
-## TIME_SERIES_WEEKLY — Weekly OHLCV
-
-**Required:** `symbol`
-
-**Optional:** `datatype`
-
-```python
-data = av_get("TIME_SERIES_WEEKLY", symbol="IBM")
-ts = data["Weekly Time Series"]
-```
-
-## TIME_SERIES_WEEKLY_ADJUSTED — Weekly OHLCV with Adjustments
-
-```python
-data = av_get("TIME_SERIES_WEEKLY_ADJUSTED", symbol="IBM")
-ts = data["Weekly Adjusted Time Series"]
-```
-
-## TIME_SERIES_MONTHLY — Monthly OHLCV
-
-```python
-data = av_get("TIME_SERIES_MONTHLY", symbol="IBM")
-ts = data["Monthly Time Series"]
-```
-
-## TIME_SERIES_MONTHLY_ADJUSTED — Monthly with Adjustments
-
-```python
-data = av_get("TIME_SERIES_MONTHLY_ADJUSTED", symbol="IBM")
-ts = data["Monthly Adjusted Time Series"]
-```
-
-## REALTIME_BULK_QUOTES — Multiple Tickers (Premium)
-
-Get quotes for up to 100 symbols in one request.
-
-**Required:** `symbol` — comma-separated list (e.g., `IBM,AAPL,MSFT`)
-
-```python
-data = av_get("REALTIME_BULK_QUOTES", symbol="IBM,AAPL,MSFT,GOOGL")
-quotes = data["data"]  # list of quote objects
-for q in quotes:
-    print(q["symbol"], q["price"])
-```
-
-## SYMBOL_SEARCH — Ticker Search
-
-Search for ticker symbols by keyword.
-
-**Required:** `keywords`
-
-**Optional:** `datatype`
-
-```python
-data = av_get("SYMBOL_SEARCH", keywords="Microsoft")
-matches = data["bestMatches"]
-for m in matches:
-    print(m["1. symbol"], m["2. name"], m["4. region"])
-# Fields: "1. symbol", "2. name", "3. type", "4. region",
-#         "5. marketOpen", "6. marketClose", "7. timezone",
-#         "8. currency", "9. matchScore"
-```
-
-## MARKET_STATUS — Global Market Hours
-
-Returns open/closed status for major global exchanges.
-
-```python
-data = av_get("MARKET_STATUS")
-markets = data["markets"]
-for m in markets:
-    print(m["market_type"], m["region"], m["current_status"])
-# Fields: "market_type", "region", "primary_exchanges",
-#         "local_open", "local_close", "current_status", "notes"
-```
-
-## Convert to DataFrame
-
-```python
-import pandas as pd
-
-data = av_get("TIME_SERIES_DAILY", symbol="AAPL", outputsize="full")
-ts = data["Time Series (Daily)"]
-df = pd.DataFrame.from_dict(ts, orient="index")
-df.columns = ["open", "high", "low", "close", "volume"]
-df.index = pd.to_datetime(df.index)
-df = df.astype(float).sort_index()
-print(df.tail())
-```
+# Time Series Stock Data APIs
+
+Base URL: `https://www.alphavantage.co/query`
+
+## GLOBAL_QUOTE — Latest Price
+
+Returns the latest price and volume for a ticker.
+
+**Required:** `symbol`
+
+```python
+data = av_get("GLOBAL_QUOTE", symbol="IBM")
+q = data["Global Quote"]
+# q keys: "01. symbol", "02. open", "03. high", "04. low", "05. price",
+#          "06. volume", "07. latest trading day", "08. previous close",
+#          "09. change", "10. change percent"
+print(q["05. price"])  # "217.51"
+```
+
+## TIME_SERIES_INTRADAY — Intraday OHLCV (Premium)
+
+Returns intraday candles with 20+ years of history.
+
+**Required:** `symbol`, `interval` (`1min`, `5min`, `15min`, `30min`, `60min`)
+
+**Optional:**
+- `adjusted` — default `true` (split/dividend adjusted)
+- `extended_hours` — default `true` (pre/post market included)
+- `month` — format `YYYY-MM` (query specific historical month)
+- `outputsize` — `compact` (100 points) or `full` (30 days / full month)
+- `entitlement` — `realtime` or `delayed` (15-min delayed)
+- `datatype` — `json` or `csv`
+
+```python
+data = av_get("TIME_SERIES_INTRADAY", symbol="IBM", interval="5min", outputsize="compact")
+ts = data["Time Series (5min)"]
+# Key: "2024-01-15 16:00:00" → {"1. open": "...", "2. high": ..., "3. low": ..., "4. close": ..., "5. volume": ...}
+
+# Get specific historical month
+data = av_get("TIME_SERIES_INTRADAY", symbol="IBM", interval="5min", month="2023-06", outputsize="full")
+```
+
+## TIME_SERIES_DAILY — Daily OHLCV
+
+**Required:** `symbol`
+
+**Optional:** `outputsize` (`compact`=100 points, `full`=20+ years), `datatype`
+
+```python
+data = av_get("TIME_SERIES_DAILY", symbol="IBM", outputsize="full")
+ts = data["Time Series (Daily)"]
+# Key: "2024-01-15" → {"1. open", "2. high", "3. low", "4. close", "5. volume"}
+```
+
+## TIME_SERIES_DAILY_ADJUSTED — Daily OHLCV with Adjustments (Premium)
+
+Includes split coefficient and dividend amount.
+
+**Required:** `symbol`
+
+**Optional:** `outputsize`, `datatype`
+
+```python
+data = av_get("TIME_SERIES_DAILY_ADJUSTED", symbol="IBM")
+ts = data["Time Series (Daily)"]
+# Extra keys: "6. adjusted close", "7. dividend amount", "8. split coefficient"
+```
+
+## TIME_SERIES_WEEKLY — Weekly OHLCV
+
+**Required:** `symbol`
+
+**Optional:** `datatype`
+
+```python
+data = av_get("TIME_SERIES_WEEKLY", symbol="IBM")
+ts = data["Weekly Time Series"]
+```
+
+## TIME_SERIES_WEEKLY_ADJUSTED — Weekly OHLCV with Adjustments
+
+```python
+data = av_get("TIME_SERIES_WEEKLY_ADJUSTED", symbol="IBM")
+ts = data["Weekly Adjusted Time Series"]
+```
+
+## TIME_SERIES_MONTHLY — Monthly OHLCV
+
+```python
+data = av_get("TIME_SERIES_MONTHLY", symbol="IBM")
+ts = data["Monthly Time Series"]
+```
+
+## TIME_SERIES_MONTHLY_ADJUSTED — Monthly with Adjustments
+
+```python
+data = av_get("TIME_SERIES_MONTHLY_ADJUSTED", symbol="IBM")
+ts = data["Monthly Adjusted Time Series"]
+```
+
+## REALTIME_BULK_QUOTES — Multiple Tickers (Premium)
+
+Get quotes for up to 100 symbols in one request.
+
+**Required:** `symbol` — comma-separated list (e.g., `IBM,AAPL,MSFT`)
+
+```python
+data = av_get("REALTIME_BULK_QUOTES", symbol="IBM,AAPL,MSFT,GOOGL")
+quotes = data["data"]  # list of quote objects
+for q in quotes:
+    print(q["symbol"], q["price"])
+```
+
+## SYMBOL_SEARCH — Ticker Search
+
+Search for ticker symbols by keyword.
+
+**Required:** `keywords`
+
+**Optional:** `datatype`
+
+```python
+data = av_get("SYMBOL_SEARCH", keywords="Microsoft")
+matches = data["bestMatches"]
+for m in matches:
+    print(m["1. symbol"], m["2. name"], m["4. region"])
+# Fields: "1. symbol", "2. name", "3. type", "4. region",
+#         "5. marketOpen", "6. marketClose", "7. timezone",
+#         "8. currency", "9. matchScore"
+```
+
+## MARKET_STATUS — Global Market Hours
+
+Returns open/closed status for major global exchanges.
+
+```python
+data = av_get("MARKET_STATUS")
+markets = data["markets"]
+for m in markets:
+    print(m["market_type"], m["region"], m["current_status"])
+# Fields: "market_type", "region", "primary_exchanges",
+#         "local_open", "local_close", "current_status", "notes"
+```
+
+## Convert to DataFrame
+
+```python
+import pandas as pd
+
+data = av_get("TIME_SERIES_DAILY", symbol="AAPL", outputsize="full")
+ts = data["Time Series (Daily)"]
+df = pd.DataFrame.from_dict(ts, orient="index")
+df.columns = ["open", "high", "low", "close", "volume"]
+df.index = pd.to_datetime(df.index)
+df = df.astype(float).sort_index()
+print(df.tail())
+```

package/skills/tech/doc.md

@@ -18,14 +18,14 @@ Skills are folder-based packages. You can define these scopes based on your need
 
 | Scope         | Path                              | Description                          |
 | ------------- | --------------------------------- | ------------------------------------ |
-| **Workspace** | `<workspace-root>/.agent/skills/` | Available only in a specific project |
+| **Workspace** | `<workspace-root>/skills/` | Available only in a specific project |
 
 ### Skill Directory Structure
 
 ```
 my-skill/
 ├── SKILL.md      # (Required) Metadata & instructions
-├── scripts/      # (Optional) Python or Bash scripts
+├── scripts/      # (Optional) Automation scripts
 ├── references/   # (Optional) Text, documentation, templates
 └── assets/       # (Optional) Images or logos
 ```
@@ -39,7 +39,7 @@ This is an instruction-only skill; you only need to create the `SKILL.md` file.
 ### Step 1: Create the directory
 
 ```bash
-mkdir -p .agent/skills/code-review
+mkdir -p skills/code-review
 ```
 
 ### Step 2: Create SKILL.md
@@ -119,12 +119,12 @@ This skill uses a reference file in the `resources/` (or `references/`) director
 ### Step 1: Create the directory
 
 ```bash
-mkdir -p .agent/skills/license-header-adder/resources
+mkdir -p skills/license-header-adder/resources
 ```
 
 ### Step 2: Create the template file
 
-**`.agent/skills/license-header-adder/resources/HEADER.txt`**:
+**`skills/license-header-adder/resources/HEADER.txt`**:
 
 ```
 /*
@@ -136,7 +136,7 @@ mkdir -p .agent/skills/license-header-adder/resources
 
 ### Step 3: Create SKILL.md
 
-**`.agent/skills/license-header-adder/SKILL.md`**:
+**`skills/license-header-adder/SKILL.md`**:
 
 ```markdown
 ---

package/skills/tech/financial-modeling/SKILL.md

@@ -1,18 +1,18 @@
----
-name: financial-modeling
-description: Consolidated financial modeling skill aggregating Discounted Cash Flow (DCF), Leveraged Buyout (LBO), Merger Modeling, and 3-Statement financial projections.
----
-
-# Financial Modeling Knowledge Base
-
-This parent skill aggregates rigorous qualitative and quantitative modeling instructions for the `quant-developer` agent. By integrating the sub-skills below, the agent can structure complex, multi-statement forecasts and perform advanced valuation tasks.
-
-## Available Sub-Skills
-
-- **[DCF Model](skills/dcf-model/SKILL.md):** Instruction sets and templates for building intrinsic valuations using Discounted Cash Flows.
-- **[LBO Model](skills/lbo-model/SKILL.md):** Private equity leveraged buyout modeling covering debt schedules, IRR, and MoM return analysis.
-- **[Merger Model](skills/merger-model/SKILL.md):** M&A accretion/dilution analysis, purchase price allocation, and pro-forma balance sheets.
-- **[3-Statements](skills/3-statements/SKILL.md):** Standard income statement, balance sheet, and cash flow historical extraction and projection protocols.
-
-## Integration Notice
-These sub-skills were ported from the specialized `financial-services-plugins` repository to fortify the baseline reasoning capabilities of the `quant-developer` agent. Ensure that assumptions (e.g., WACC, tax rates) are properly isolated when running backtests or algorithmic models based on these fundamental outputs.
+---
+name: financial-modeling
+description: Consolidated financial modeling skill aggregating Discounted Cash Flow (DCF), Leveraged Buyout (LBO), Merger Modeling, and 3-Statement financial projections.
+---
+
+# Financial Modeling Knowledge Base
+
+This parent skill aggregates rigorous qualitative and quantitative modeling instructions for the `quant-developer` agent. By integrating the sub-skills below, the agent can structure complex, multi-statement forecasts and perform advanced valuation tasks.
+
+## Available Sub-Skills
+
+- **[DCF Model](skills/dcf-model/SKILL.md):** Instruction sets and templates for building intrinsic valuations using Discounted Cash Flows.
+- **[LBO Model](skills/lbo-model/SKILL.md):** Private equity leveraged buyout modeling covering debt schedules, IRR, and MoM return analysis.
+- **[Merger Model](skills/merger-model/SKILL.md):** M&A accretion/dilution analysis, purchase price allocation, and pro-forma balance sheets.
+- **[3-Statements](skills/3-statements/SKILL.md):** Standard income statement, balance sheet, and cash flow historical extraction and projection protocols.
+
+## Integration Notice
+These sub-skills were ported from the specialized `financial-services-plugins` repository to fortify the baseline reasoning capabilities of the `quant-developer` agent. Ensure that assumptions (e.g., WACC, tax rates) are properly isolated when running backtests or algorithmic models based on these fundamental outputs.