docs: Update CLI help text (#132)

* update docs link

* Clean up flag descriptions

* Remove single file example scan

docs/_data/curio.yaml

@@ -7,7 +7,7 @@ options:
       usage: help for this command
 see_also:
     - ' config - Scan config files for misconfigurations'
-    - ' init - writes default config to curio.yml'
-    - ' scan - Scan git repository'
+    - ' init - Generates a default config to `curio.yml`'
+    - ' scan - Scan a directory or file'
     - ' version - Print the version'
 aliases: 

docs/_data/curio_config.yaml

@@ -2,26 +2,29 @@ name: ' config'
 synopsis: Scan config files for misconfigurations
 usage: ' config [flags] DIR'
 options:
+    - name: context
+      usage: |
+        Expand context of schema classification e.g., --context=health, to include data types particular to health
     - name: disable-domain-resolution
       default_value: "false"
       usage: |
-        do not attempt to resolve detected domains during classification (default false), eg. --disable-domain-resolution=true
+        Do not attempt to resolve detected domains during classification (default false), e.g. --disable-domain-resolution=true
     - name: domain-resolution-timeout
       default_value: 3s
       usage: |
-        set timeout when attempting to resolve detected domains during classification (default 3 seconds), eg. --domain-resolution-timeout=TODO
+        Set timeout when attempting to resolve detected domains during classification (default 3 seconds), e.g. --domain-resolution-timeout=3s
     - name: help
       shorthand: h
       default_value: "false"
       usage: help for config
     - name: internal-domains
       default_value: '[]'
       usage: |
-        define regular expressions for better classification of private or unreachable domains eg. --internal-domains="*.my-company.com,private.sh"
+        Define regular expressions for better classification of private or unreachable domains e.g. --internal-domains="*.my-company.com,private.sh"
     - name: skip-path
       default_value: '[]'
       usage: |
-        specify the comma separated files and directories to skip (supports * syntax), eg. --skip-path users/*.go,users/admin.sql
+        Specify the comma separated files and directories to skip. Supports * syntax, e.g. --skip-path users/*.go,users/admin.sql
 see_also:
     - ' - '
 aliases: conf

docs/_data/curio_init.yaml

@@ -1,20 +1,25 @@
 name: ' init'
-synopsis: writes default config to curio.yml
+synopsis: Generates a default config to `curio.yml`
 usage: ' init [flags]'
 options:
     - name: config-file
-      usage: file from which to load configurations
+      usage: Load configuration from the defined path
+    - name: context
+      usage: |
+        Expand context of schema classification e.g., --context=health, to include data types particular to health
     - name: debug
       default_value: "false"
-      usage: enable debug logs
+      usage: Enable debug logs
     - name: disable-domain-resolution
       default_value: "false"
       usage: |
-        do not attempt to resolve detected domains during classification (default false), eg. --disable-domain-resolution=true
+        Do not attempt to resolve detected domains during classification (default false), e.g. --disable-domain-resolution=true
     - name: domain-resolution-timeout
       default_value: 3s
       usage: |
-        set timeout when attempting to resolve detected domains during classification (default 3 seconds), eg. --domain-resolution-timeout=TODO
+        Set timeout when attempting to resolve detected domains during classification (default 3 seconds), e.g. --domain-resolution-timeout=3s
+    - name: existing-worker
+      usage: URL of an existing worker
     - name: file-size-max
       default_value: "25000000"
       usage: ignore files with file size larger than this config
@@ -24,36 +29,40 @@ options:
     - name: format
       shorthand: f
       default_value: json
-      usage: format (json)
+      usage: Specify report format (json, yaml)
     - name: help
       shorthand: h
       default_value: "false"
       usage: help for init
     - name: internal-domains
       default_value: '[]'
       usage: |
-        define regular expressions for better classification of private or unreachable domains eg. --internal-domains="*.my-company.com,private.sh"
+        Define regular expressions for better classification of private or unreachable domains e.g. --internal-domains="*.my-company.com,private.sh"
     - name: memory-max
       default_value: "800000000"
       usage: |
         if memory needed to scan a file surpasses this limit, skip the file
+    - name: only-policy
+      default_value: '[]'
+      usage: |
+        specify the comma separated ids of the policies you would like to run. Skips all other policies.
     - name: output
-      usage: path where to save report
+      usage: Specify output path for report
+    - name: quiet
+      default_value: "false"
+      usage: Suppress non-essential messages
     - name: report
       default_value: detectors
-      usage: specify the kind of report (detectors)
+      usage: |
+        Specify the kind of report (detectors, dataflow, policies, stats)
     - name: skip-path
       default_value: '[]'
       usage: |
-        specify the comma separated files and directories to skip (supports * syntax), eg. --skip-path users/*.go,users/admin.sql
+        Specify the comma separated files and directories to skip. Supports * syntax, e.g. --skip-path users/*.go,users/admin.sql
     - name: skip-policy
       default_value: '[]'
       usage: |
         specify the comma separated ids of the policies you would like to skip. Runs all other policies.
-    - name: only-policy
-      default_value: '[]'
-      usage: |
-        specify the comma separated ids of the policies you would like to run. Skips all other policies.
     - name: timeout
       default_value: 10m0s
       usage: time allowed to complete scan
@@ -77,4 +86,4 @@ options:
       usage: number of processing workers to spawn
 see_also:
     - ' - '
-aliases:
+aliases: 

docs/_data/curio_scan.yaml

@@ -1,20 +1,25 @@
 name: ' scan'
-synopsis: Scan git repository
-usage: ' scan [flags] PATH'
+synopsis: Scan a directory or file
+usage: ' scan [flags] <path>'
 options:
     - name: config-file
-      usage: file from which to load configurations
+      usage: Load configuration from the defined path
+    - name: context
+      usage: |
+        Expand context of schema classification e.g., --context=health, to include data types particular to health
     - name: debug
       default_value: "false"
-      usage: enable debug logs
+      usage: Enable debug logs
     - name: disable-domain-resolution
       default_value: "false"
       usage: |
-        do not attempt to resolve detected domains during classification (default false), eg. --disable-domain-resolution=true
+        Do not attempt to resolve detected domains during classification (default false), e.g. --disable-domain-resolution=true
     - name: domain-resolution-timeout
       default_value: 3s
       usage: |
-        set timeout when attempting to resolve detected domains during classification (default 3 seconds), eg. --domain-resolution-timeout=TODO
+        Set timeout when attempting to resolve detected domains during classification (default 3 seconds), e.g. --domain-resolution-timeout=3s
+    - name: existing-worker
+      usage: URL of an existing worker
     - name: file-size-max
       default_value: "25000000"
       usage: ignore files with file size larger than this config
@@ -24,36 +29,40 @@ options:
     - name: format
       shorthand: f
       default_value: json
-      usage: format (json)
+      usage: Specify report format (json, yaml)
     - name: help
       shorthand: h
       default_value: "false"
       usage: help for scan
     - name: internal-domains
       default_value: '[]'
       usage: |
-        define regular expressions for better classification of private or unreachable domains eg. --internal-domains="*.my-company.com,private.sh"
+        Define regular expressions for better classification of private or unreachable domains e.g. --internal-domains="*.my-company.com,private.sh"
     - name: memory-max
       default_value: "800000000"
       usage: |
         if memory needed to scan a file surpasses this limit, skip the file
+    - name: only-policy
+      default_value: '[]'
+      usage: |
+        specify the comma separated ids of the policies you would like to run. Skips all other policies.
     - name: output
-      usage: path where to save report
+      usage: Specify output path for report
+    - name: quiet
+      default_value: "false"
+      usage: Suppress non-essential messages
     - name: report
       default_value: detectors
-      usage: specify the kind of report (detectors)
+      usage: |
+        Specify the kind of report (detectors, dataflow, policies, stats)
     - name: skip-path
       default_value: '[]'
       usage: |
-        specify the comma separated files and directories to skip (supports * syntax), eg. --skip-path users/*.go,users/admin.sql
+        Specify the comma separated files and directories to skip. Supports * syntax, e.g. --skip-path users/*.go,users/admin.sql
     - name: skip-policy
       default_value: '[]'
       usage: |
         specify the comma separated ids of the policies you would like to skip. Runs all other policies.
-    - name: only-policy
-      default_value: '[]'
-      usage: |
-        specify the comma separated ids of the policies you would like to run. Skips all other policies.
     - name: timeout
       default_value: 10m0s
       usage: time allowed to complete scan
@@ -76,10 +85,8 @@ options:
       default_value: "1"
       usage: number of processing workers to spawn
 example: |4-
-      # Scan a local project including language-specific files
-      $ curio s /path/to/your_project
-      # Scan a single file
-      $ curio s ./curio-ci-test/Pipfile.lock
+      # Scan a local project, including language-specific files
+      $ curio scan /path/to/your_project
 see_also:
     - ' - '
 aliases: s

integration/flags/.snapshots/TestMetadataFlags-help

@@ -1,13 +1,27 @@
-Curio is a tool for scanning policy breaches
+Curio - discover sensitive data flows and security risks.
 
-Scan Example:
-	# Scan local repository
-	$ curio scan <repository>
+Usage: curio <command> [flags]
 
 Available Commands:
-	scan              Scan git repository
-	init              Writes default config to curio.yml
+	scan              Scan a directory or file
+	init              Write the default config to curio.yml
 	version           Print the version
 
+Examples:
+	# Scan local directory or file
+	$ curio scan <path>
+
+	# Scan current directory and output the data flow to a file
+	$ curio scan --report dataflow --output <output-path> .
+
+Learn More:
+	Curio scans your source code to discover sensitive data flows 
+	and data security risks in your codebase. This includes detecting
+	PHI, PII, and PD usage in data stores, internal APIs, and external
+	APIs. You can run Curio locally or as part of your CI/CD pipeline.
+
+	For more examples, tutorials, and to learn more about the project 
+	visit https://curio.sh
+
 --
 

integration/flags/.snapshots/TestMetadataFlags-help-scan

@@ -1,24 +1,22 @@
-Scan git repository
+Scan a directory or file
 
 Usage:
-   scan [flags] PATH
+   scan [flags] <path>
 Aliases:
   scan, s
 Examples:
-  # Scan a local project including language-specific files
-  $ curio s /path/to/your_project
-  # Scan a single file
-  $ curio s ./curio-ci-test/Pipfile.lock
+  # Scan a local project, including language-specific files
+  $ curio scan /path/to/your_project
 
 
 Scan Flags
-      --context string                       expand context of schema classification e.g. --context=health to include data types particular to health
-      --debug                                enable debug logs
-      --disable-domain-resolution            do not attempt to resolve detected domains during classification (default false), eg. --disable-domain-resolution=true
-      --domain-resolution-timeout duration   set timeout when attempting to resolve detected domains during classification (default 3 seconds), eg. --domain-resolution-timeout=TODO (default 3s)
-      --internal-domains strings             define regular expressions for better classification of private or unreachable domains eg. --internal-domains="*.my-company.com,private.sh"
-      --quiet                                suppress non-essential messages
-      --skip-path strings                    specify the comma separated files and directories to skip (supports * syntax), eg. --skip-path users/*.go,users/admin.sql
+      --context string                       Expand context of schema classification e.g., --context=health, to include data types particular to health
+      --debug                                Enable debug logs
+      --disable-domain-resolution            Do not attempt to resolve detected domains during classification (default false), e.g. --disable-domain-resolution=true
+      --domain-resolution-timeout duration   Set timeout when attempting to resolve detected domains during classification (default 3 seconds), e.g. --domain-resolution-timeout=3s (default 3s)
+      --internal-domains strings             Define regular expressions for better classification of private or unreachable domains e.g. --internal-domains="*.my-company.com,private.sh"
+      --quiet                                Suppress non-essential messages
+      --skip-path strings                    Specify the comma separated files and directories to skip. Supports * syntax, e.g. --skip-path users/*.go,users/admin.sql
 
 Policy Flags
       --only-policy strings   specify the comma separated ids of the policies you would like to run. Skips all other policies.
@@ -37,12 +35,12 @@ Worker Flags
       --workers int                         number of processing workers to spawn (default 1)
 
 Report Flags
-  -f, --format string   format (json, yaml) (default "json")
-      --output string   path where to save report
-      --report string   specify the kind of report (detectors, dataflow, policies, stats) (default "detectors")
+  -f, --format string   Specify report format (json, yaml) (default "json")
+      --output string   Specify output path for report
+      --report string   Specify the kind of report (detectors, dataflow, policies, stats) (default "detectors")
 
 General Flags
-      --config-file string   file from which to load configurations
+      --config-file string   Load configuration from the defined path
 
 
 --

integration/flags/.snapshots/TestMetadataFlags-scan-help

@@ -1,24 +1,22 @@
-Scan git repository
+Scan a directory or file
 
 Usage:
-   scan [flags] PATH
+   scan [flags] <path>
 Aliases:
   scan, s
 Examples:
-  # Scan a local project including language-specific files
-  $ curio s /path/to/your_project
-  # Scan a single file
-  $ curio s ./curio-ci-test/Pipfile.lock
+  # Scan a local project, including language-specific files
+  $ curio scan /path/to/your_project
 
 
 Scan Flags
-      --context string                       expand context of schema classification e.g. --context=health to include data types particular to health
-      --debug                                enable debug logs
-      --disable-domain-resolution            do not attempt to resolve detected domains during classification (default false), eg. --disable-domain-resolution=true
-      --domain-resolution-timeout duration   set timeout when attempting to resolve detected domains during classification (default 3 seconds), eg. --domain-resolution-timeout=TODO (default 3s)
-      --internal-domains strings             define regular expressions for better classification of private or unreachable domains eg. --internal-domains="*.my-company.com,private.sh"
-      --quiet                                suppress non-essential messages
-      --skip-path strings                    specify the comma separated files and directories to skip (supports * syntax), eg. --skip-path users/*.go,users/admin.sql
+      --context string                       Expand context of schema classification e.g., --context=health, to include data types particular to health
+      --debug                                Enable debug logs
+      --disable-domain-resolution            Do not attempt to resolve detected domains during classification (default false), e.g. --disable-domain-resolution=true
+      --domain-resolution-timeout duration   Set timeout when attempting to resolve detected domains during classification (default 3 seconds), e.g. --domain-resolution-timeout=3s (default 3s)
+      --internal-domains strings             Define regular expressions for better classification of private or unreachable domains e.g. --internal-domains="*.my-company.com,private.sh"
+      --quiet                                Suppress non-essential messages
+      --skip-path strings                    Specify the comma separated files and directories to skip. Supports * syntax, e.g. --skip-path users/*.go,users/admin.sql
 
 Policy Flags
       --only-policy strings   specify the comma separated ids of the policies you would like to run. Skips all other policies.
@@ -37,12 +35,12 @@ Worker Flags
       --workers int                         number of processing workers to spawn (default 1)
 
 Report Flags
-  -f, --format string   format (json, yaml) (default "json")
-      --output string   path where to save report
-      --report string   specify the kind of report (detectors, dataflow, policies, stats) (default "detectors")
+  -f, --format string   Specify report format (json, yaml) (default "json")
+      --output string   Specify output path for report
+      --report string   Specify the kind of report (detectors, dataflow, policies, stats) (default "detectors")
 
 General Flags
-      --config-file string   file from which to load configurations
+      --config-file string   Load configuration from the defined path
 
 
 --