Initialize a project for cogitation workflows. Sets up EC project context, scaffolds directories, and configures project-specific commands.
Initializes cogitation workflows by scaffolding directories, detecting project stacks, and configuring commands for memory-enhanced development.
npx claudepluginhub merewhiplash/engram-cogitatorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
First-time setup for a project. Creates the foundation for memory-enhanced workflows.
Announce: "I'm using the init skill to set up cogitation for this project."
Verify EC → Check Existing → Scaffold → Configure → Store
Test that Engram Cogitator is running:
ec_search: test connection
If EC unavailable: Stop. Cogitation requires EC.
"EC connection failed. Please ensure engram-cogitator is running. See: https://github.com/MereWhiplash/engram-cogitator"
Search for prior initialization:
ec_search: project config
ec_search: cogitation initialized
If found: Ask before reinitializing.
{
"questions": [{
"question": "This project already has cogitation context. What would you like to do?",
"header": "Existing",
"options": [
{ "label": "Keep existing", "description": "Exit without changes" },
{ "label": "Reconfigure", "description": "Update settings, keep memories" },
{ "label": "Fresh start", "description": "Clear all and reinitialize" }
],
"multiSelect": false
}]
}
Create standard directories if they don't exist:
mkdir -p docs/designs docs/plans
Analyze the project to suggest defaults:
ls -la
Look for:
package.json → Node/npm/pnpm/bungo.mod → GoCargo.toml → Rustpyproject.toml / requirements.txt → PythonMakefile → Make-basedUse AskUserQuestion to confirm/customize commands:
{
"questions": [
{
"question": "What command runs your tests?",
"header": "Test",
"options": [
{ "label": "[detected]", "description": "Based on project files" },
{ "label": "pnpm test", "description": "pnpm package manager" },
{ "label": "npm test", "description": "npm package manager" },
{ "label": "go test ./...", "description": "Go testing" }
],
"multiSelect": false
},
{
"question": "What command checks types/lints?",
"header": "Lint",
"options": [
{ "label": "[detected]", "description": "Based on project files" },
{ "label": "pnpm lint", "description": "ESLint via pnpm" },
{ "label": "go vet ./...", "description": "Go vet" },
{ "label": "None", "description": "Skip linting" }
],
"multiSelect": false
},
{
"question": "What command builds the project?",
"header": "Build",
"options": [
{ "label": "[detected]", "description": "Based on project files" },
{ "label": "pnpm build", "description": "Build via pnpm" },
{ "label": "go build ./...", "description": "Go build" },
{ "label": "None", "description": "No build step" }
],
"multiSelect": false
}
]
}
{
"questions": [{
"question": "What branching convention do you use?",
"header": "Branches",
"options": [
{ "label": "feat/fix/chore", "description": "feat/<name>, fix/<name>, chore/<name>" },
{ "label": "feature/bugfix", "description": "feature/<name>, bugfix/<name>" },
{ "label": "Flat", "description": "Just descriptive names" }
],
"multiSelect": false
}]
}
Store the project configuration in EC:
ec_add:
type: config
area: project
content: |
test_command: <user choice>
lint_command: <user choice>
build_command: <user choice>
branch_convention: <user choice>
rationale: Project configuration for cogitation workflows
Mark initialization complete:
ec_add:
type: pattern
area: project
content: Cogitation initialized for this project
rationale: Marker for init detection
Present what was set up:
Cogitation initialized
- Test:
<command>- Lint:
<command>- Build:
<command>- Branches:
<convention>Directories created:
docs/designs/,docs/plans/Ready to use cogitation skills. Try
@brainstormingto start a feature.
Suggest next steps based on context:
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.