@cleocode/cleo 2026.3.4 → 2026.3.6

package/packages/ct-skills/skills/ct-library-implementer-bash/SKILL.md

@@ -1,316 +0,0 @@
----
-name: ct-library-implementer-bash
-description: Bash library development with focus on creating well-structured lib/*.sh files following shell best practices. Implements reusable functions, utility modules, and shared helpers with proper documentation, error handling, and dependency management. Use when creating new lib/ modules, implementing shared functions, or adding utility libraries. Triggers on library implementation tasks, bash module creation, or utility function needs.
-version: 2.0.0
-tier: 2
-core: false
-category: specialist
-protocol: implementation
-dependencies: []
-sharedResources:
-  - subagent-protocol-base
-  - task-system-integration
-compatibility:
-  - claude-code
-  - cursor
-  - windsurf
-  - gemini-cli
-license: MIT
----
-
-# Library Implementer (Bash) Context Injection
-
-**Protocol**: @protocols/implementation.md
-**Type**: Context Injection (cleo-subagent)
-**Version**: 2.0.0
-
----
-
-## Purpose
-
-Context injection for Bash library implementation tasks spawned via cleo-subagent. Provides domain expertise for creating well-structured bash library files with reusable functions following shell best practices.
-
----
-
-## Capabilities
-
-1. **Function Libraries** - Create lib/*.sh files with related functions
-2. **Utility Functions** - Implement shared helper functions
-3. **Module Design** - Organize functions into cohesive modules
-4. **Documentation** - Document function signatures and usage
-
----
-
-## Bash Library Architecture
-
-### Directory Structure
-
-```
-lib/
-├── exit-codes.sh       # Exit code constants
-├── output-format.sh    # JSON/human output formatting
-├── validation.sh       # Input validation functions
-├── file-ops.sh         # Atomic file operations
-├── logging.sh          # Audit trail logging
-├── config.sh           # Configuration management
-└── {new-module}.sh     # Your new library
-```
-
-### Library Template
-
-```bash
-#!/usr/bin/env bash
-# lib/{module-name}.sh - Brief description of module purpose
-#
-# Functions:
-#   function_name()     - Brief description
-#   another_function()  - Brief description
-
-# Guard against multiple sourcing
-[[ -n "${_MODULE_NAME_LOADED:-}" ]] && return 0
-readonly _MODULE_NAME_LOADED=1
-
-# Dependencies (source other libs if needed)
-# source "${LIB_DIR:-./lib}/dependency.sh"
-
-# ==============================================================================
-# CONSTANTS
-# ==============================================================================
-
-readonly MODULE_CONSTANT="value"
-
-# ==============================================================================
-# FUNCTIONS
-# ==============================================================================
-
-# Brief description of what this function does
-#
-# Arguments:
-#   $1 - arg_name: Description
-#   $2 - arg_name: Description (optional, default: value)
-#
-# Returns:
-#   0 on success, non-zero on failure
-#
-# Output:
-#   Writes result to stdout (JSON or text)
-#
-# Example:
-#   result=$(function_name "arg1" "arg2")
-#
-function_name() {
-  local arg1="$1"
-  local arg2="${2:-default}"
-
-  # Implementation
-}
-
-# Another function with similar documentation
-another_function() {
-  local input="$1"
-
-  # Implementation
-}
-```
-
----
-
-## Function Design Guidelines
-
-### Naming Conventions
-
-```bash
-# Public functions: lowercase_with_underscores
-get_task_by_id()
-validate_json_schema()
-
-# Private/internal functions: prefix with underscore
-_internal_helper()
-_parse_config()
-
-# Module-specific prefix for clarity
-rm_get_entry()        # research-manifest module
-orc_build_prompt()    # orchestrator module
-```
-
-### Input Validation
-
-```bash
-function_name() {
-  local required_arg="$1"
-  local optional_arg="${2:-default}"
-
-  # Validate required arguments
-  if [[ -z "$required_arg" ]]; then
-    echo "ERROR: required_arg is required" >&2
-    return 1
-  fi
-
-  # Implementation
-}
-```
-
-### Error Handling
-
-```bash
-function_name() {
-  local file="$1"
-
-  # Check preconditions
-  if [[ ! -f "$file" ]]; then
-    echo "ERROR: File not found: $file" >&2
-    return "${EXIT_FILE_ERROR:-4}"
-  fi
-
-  # Use set -e locally if needed
-  local result
-  if ! result=$(risky_operation 2>&1); then
-    echo "ERROR: Operation failed: $result" >&2
-    return 1
-  fi
-
-  echo "$result"
-}
-```
-
-### JSON Output
-
-```bash
-# Functions that produce output should support JSON
-get_data() {
-  local id="$1"
-  local format="${2:-json}"
-
-  local data
-  data=$(fetch_data "$id")
-
-  if [[ "$format" == "json" ]]; then
-    jq -nc --arg id "$id" --arg data "$data" \
-      '{"id": $id, "data": $data}'
-  else
-    echo "ID: $id"
-    echo "Data: $data"
-  fi
-}
-```
-
----
-
-## Module Organization
-
-### Single Responsibility
-
-Each library should have ONE clear purpose:
-
-```bash
-# GOOD: lib/research-manifest.sh
-# - All functions related to research manifest operations
-
-# BAD: lib/utils.sh
-# - Grab bag of unrelated functions
-```
-
-### Dependency Management
-
-```bash
-# At top of file, source dependencies
-source "${LIB_DIR:-./lib}/exit-codes.sh"
-source "${LIB_DIR:-./lib}/output-format.sh"
-
-# Or check for required functions
-if ! declare -f required_function &>/dev/null; then
-  echo "ERROR: required_function not available" >&2
-  return 1
-fi
-```
-
-### Avoid Circular Dependencies
-
-```
-Layer 0: exit-codes.sh (no deps)
-Layer 1: output-format.sh (deps: exit-codes)
-Layer 2: validation.sh (deps: exit-codes, output-format)
-Layer 3: Your module (deps: layers 0-2)
-```
-
----
-
-## Testing Library Functions
-
-```bash
-# In tests/unit/{module}.bats
-
-@test "function_name returns expected result" {
-  source lib/{module}.sh
-
-  result=$(function_name "input")
-
-  assert_equal "$result" "expected"
-}
-
-@test "function_name handles missing input" {
-  source lib/{module}.sh
-
-  run function_name ""
-
-  assert_failure
-  assert_output --partial "required"
-}
-```
-
----
-
-## Output Location
-
-Libraries go in: `lib/{{MODULE_NAME}}.sh`
-
----
-
-## Task System Integration
-
-@skills/_shared/task-system-integration.md
-
-### Execution Sequence
-
-1. Read task: `{{TASK_SHOW_CMD}} {{TASK_ID}}`
-2. Start task: `{{TASK_START_CMD}} {{TASK_ID}}` (if not already started by orchestrator)
-3. Create library file in lib/
-4. Verify syntax: `bash -n lib/{module}.sh`
-5. Append manifest entry to `{{MANIFEST_PATH}}`
-6. Complete task: `{{TASK_COMPLETE_CMD}} {{TASK_ID}}`
-7. Return summary message
-
----
-
-## Subagent Protocol
-
-@skills/_shared/subagent-protocol-base.md
-
-### Output Requirements
-
-1. MUST create library file in lib/
-2. MUST verify syntax: `bash -n lib/{module}.sh`
-3. MUST append ONE line to: `{{MANIFEST_PATH}}`
-4. MUST return ONLY: "Implementation complete. See MANIFEST.jsonl for summary."
-5. MUST NOT return full library content in response
-
-### Manifest Entry Format
-
-```json
-{"id":"lib-{{MODULE}}-{{DATE}}","file":"{{DATE}}_lib-{{MODULE}}.md","title":"Library: {{MODULE}}","date":"{{DATE}}","status":"complete","agent_type":"implementation","topics":["library","bash","{{DOMAIN}}"],"key_findings":["Created lib/{{MODULE}}.sh with N functions","Functions: function1, function2, function3","Dependencies: list or 'none'","Syntax check passed"],"actionable":false,"needs_followup":["{{TEST_TASK_IDS}}"],"linked_tasks":["{{TASK_ID}}"]}
-```
-
----
-
-## Completion Checklist
-
-- [ ] Task started via `{{TASK_START_CMD}}` (if not already started)
-- [ ] Library file created in lib/
-- [ ] Guard against multiple sourcing included
-- [ ] Functions documented with signatures
-- [ ] Input validation implemented
-- [ ] Error handling with proper exit codes
-- [ ] Syntax check passed (`bash -n`)
-- [ ] Manifest entry appended
-- [ ] Task completed via `{{TASK_COMPLETE_CMD}}`
-- [ ] Return summary message only

package/packages/ct-skills/skills/ct-skill-lookup/SKILL.md

@@ -1,179 +0,0 @@
----
-name: ct-skill-lookup
-description: This skill should be used when the user asks to "find me a skill", "search for skills", "what skills are available", "get skill XYZ", "install a skill", "extend Claude's capabilities with skills", or mentions Agent Skills, prompts.chat, SkillsMP, marketplace, external skills, or reusable AI agent components.
-version: 1.1.0
-tier: 3
-core: false
-category: meta
-protocol: null
-dependencies: []
-sharedResources: []
-compatibility:
-  - claude-code
-  - cursor
-  - windsurf
-  - gemini-cli
-license: MIT
----
-
-When the user needs Agent Skills, wants to extend Claude's capabilities, or is looking for reusable AI agent components, you have two sources available:
-
-1. **prompts.chat MCP server** - Agent Skills marketplace (when available)
-2. **SkillsMP** - CLEO's built-in skill marketplace integration
-
-## When to Use This Skill
-
-Activate this skill when the user:
-
-- Asks for Agent Skills ("Find me a code review skill")
-- Wants to search for skills ("What skills are available for testing?")
-- Needs to retrieve a specific skill ("Get skill XYZ")
-- Wants to install a skill ("Install the documentation skill")
-- Mentions extending Claude's capabilities with skills
-- Mentions marketplace, SkillsMP, or external skills
-
-## Available Tools
-
-### prompts.chat MCP Tools (when available)
-
-- `search_skills` - Search for skills by keyword
-- `get_skill` - Get a specific skill by ID with all its files
-
-### CLEO SkillsMP (built-in)
-
-Use `cleo skills` commands to search and retrieve skills:
-
-```bash
-cleo skills search <query> [--source skillsmp]  # Search SkillsMP marketplace
-cleo skills get <id> --source skillsmp          # Get skill from marketplace
-cleo skills install <id> --source skillsmp      # Install from marketplace
-```
-
-## How to Search for Skills
-
-### Using prompts.chat MCP
-
-Call `search_skills` with:
-
-- `query`: The search keywords from the user's request
-- `limit`: Number of results (default 10, max 50)
-- `category`: Filter by category slug (e.g., "coding", "automation")
-- `tag`: Filter by tag slug
-
-Present results showing:
-- Title and description
-- Author name
-- File list (SKILL.md, reference docs, scripts)
-- Category and tags
-- Link to the skill
-
-### Using SkillsMP
-
-Execute `cleo skills search` with:
-
-```bash
-cleo skills search "code review" --source skillsmp
-cleo skills search "testing" --source skillsmp --limit 20
-```
-
-Results include:
-- Skill ID, name, and description
-- Version and compatibility
-- Author and license
-- Installation status (local/marketplace)
-
-## How to Get a Skill
-
-### Using prompts.chat MCP
-
-Call `get_skill` with:
-
-- `id`: The skill ID
-
-Returns the skill metadata and all file contents:
-- SKILL.md (main instructions)
-- Reference documentation
-- Helper scripts
-- Configuration files
-
-### Using SkillsMP
-
-Execute `cleo skills get`:
-
-```bash
-cleo skills get ct-code-reviewer --source skillsmp
-```
-
-Returns full skill content including metadata and files.
-
-## How to Install a Skill
-
-### Using prompts.chat MCP
-
-When the user asks to install a skill:
-
-1. Call `get_skill` to retrieve all files
-2. Create the directory `.claude/skills/{slug}/`
-3. Save each file to the appropriate location:
-   - `SKILL.md` → `.claude/skills/{slug}/SKILL.md`
-   - Other files → `.claude/skills/{slug}/{filename}`
-
-### Using SkillsMP
-
-Execute `cleo skills install`:
-
-```bash
-cleo skills install ct-code-reviewer --source skillsmp
-cleo skills install ct-testing-assistant --source skillsmp --force
-```
-
-The command automatically:
-- Downloads skill files from marketplace
-- Validates skill structure
-- Installs to `skills/{slug}/`
-- Updates skill registry
-
-## Skill Structure
-
-Skills contain:
-- **SKILL.md** (required) - Main instructions with frontmatter
-- **Reference docs** - Additional documentation files
-- **Scripts** - Helper scripts (Python, shell, etc.)
-- **Config files** - JSON, YAML configurations
-
-## Guidelines
-
-- Always search before suggesting the user create their own skill
-- Try SkillsMP first (`cleo skills search`), then prompts.chat MCP if available
-- Present search results in a readable format with file counts
-- When installing, confirm the skill was saved successfully
-- Explain what the skill does and when it activates
-
-## Examples
-
-### Searching SkillsMP
-
-```bash
-# Find code review skills
-cleo skills search "code review" --source skillsmp
-
-# Find testing-related skills
-cleo skills search "test" --source skillsmp --limit 10
-```
-
-### Getting Skill Details
-
-```bash
-# Get full skill information
-cleo skills get ct-code-reviewer --source skillsmp
-```
-
-### Installing from Marketplace
-
-```bash
-# Install a skill from SkillsMP
-cleo skills install ct-code-reviewer --source skillsmp
-
-# Force reinstall (overwrite existing)
-cleo skills install ct-code-reviewer --source skillsmp --force
-```