Menu
Analyze a project repository and add it to the Arkadian documentation registry with standardized structure. Use when: user provides a path to a new project to onboard.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | add-project |
| description | Analyze a project repository and add it to the Arkadian documentation registry with standardized structure. Use when: user provides a path to a new project to onboard. |
| allowed-tools | ["Read","Write","Edit","Bash","Glob","Grep"] |
When to use:
User input: An absolute path to a project repository (e.g., /Users/name/code/my-project).
This skill automates the process of analyzing a project and adding comprehensive documentation to the Arkadian registry, following the same pattern used for existing projects like boltz-backend, fulmine, and arkd.
Given a project path, do this:
Check that the provided path:
/ or ~).git directory (is a git repository)If validation fails, ask the user to provide a valid project path.
Perform comprehensive project analysis by reading key files:
Step 2.1: Read Basic Project Information
README.md or README - Project description and features.git/config - Git repository information (if available)Step 2.2: Identify Technology Stack
Read configuration files to determine languages and frameworks:
package.json - Node.js/TypeScript projectsCargo.toml - Rust projectsgo.mod - Go projectsrequirements.txt or pyproject.toml - Python projectspom.xml or build.gradle - Java projectsGemfile - Ruby projectsStep 2.3: Explore Project Structure
Step 2.4: Extract Project Metadata
From the analysis, determine:
ask_question: Conceptual keywordsdevelop: Development task keywordstest_or_run: Testing/execution keywordsdebug: Error/troubleshooting keywordsStep 2.5: Get Current Commit for Sync Tracking
cd <project-path>
INITIAL_COMMIT=$(git rev-parse HEAD)
INITIAL_DATE=$(date '+%Y-%m-%d %H:%M:%S')
Create a concise project ID (2-4 words, hyphenated):
Step 4.1: Create Branch
git checkout -b feat/docs-add-<project-id>
Step 4.2: Create Directory Structure
mkdir -p docs/projects/<project-id>/{system,testing,sop,tasks,change-log,pr-report}
Step 4.3: Create Project INDEX.md
Write docs/projects/<project-id>/INDEX.md with YAML frontmatter including:
project_iddefault_sections_by_intent (qna, qa, dev, debug, monitoring)aliasesscripts (derived from package.json, Makefile, etc.)Step 4.4: Create Core Documentation Files
Create these files with content derived from project analysis:
| File | Size Limit | Content |
|---|---|---|
system/project_overview.md | 150 lines | What, features, tech stack, use cases |
system/architecture.md | 700 words | Architecture diagram, components, data flow |
system/integration-with-arkd.md | (if Ark-related) | Integration patterns |
testing/usage.md | 120 lines | Quick start, config, Docker |
testing/how_to_run.md | - | Prerequisites, deployment, env vars |
testing/how_to_test.md | - | Unit/integration tests, coverage |
testing/troubleshooting.md | - | Common issues, debugging |
testing/api-reference.md | 200 lines/group | (if project has API) |
sop/development-workflow.md | - | Build, test, PR workflow |
Step 4.5: Create Sync Tracking Files
change-log/last-sync.txt — Initial commit hashchange-log/SYNC_HISTORY.md — Initial sync entryInsert new project entry in docs/INDEX.md in alphabetical order with complete metadata (description, capabilities, tags, synonyms, triggers, dependencies).
Also update:
Verify:
Create conventional commit: docs(<project-id>): add project to documentation registry
Provide summary with files created, INDEX.md updates, sync tracking status, and next steps.
| Type | Indicators | Key Commands |
|---|---|---|
| Go Backend | go.mod, Makefile | make build, make test |
| TypeScript Frontend | package.json + React/Vite | pnpm install, pnpm run dev |
| TypeScript Backend | package.json + Node.js | pnpm install, pnpm run start:dev |
| Infrastructure | *.tf files | tofu init, tofu plan |
| External Service | API-focused | Document integration |
| Library/SDK | API docs | Code samples |
Analyse an Arkadian orchestrator session - read transcripts, logs, and artifacts to understand what happened and suggest improvements. Use when: user wants to debug or review a past session.
Generate validated operational SOPs for Ark ecosystem projects by testing commands before documenting them. Use when: user wants to create or audit SOPs for a project.
Remove a project from the Arkadian documentation registry and delete all associated documentation files. Use when: user wants to deregister a project.
Update project documentation based on new commits and changes in the repository. Use when: user wants to sync docs after project changes.
Self-improvement loop for arkadian. Launches arkadian -d with a GitHub issue, polls until done, evaluates per-agent criteria, reads transcripts on failure, improves prompts, deletes worktree, and relaunches. Loops until passing or max iterations.
Debug and investigate fulmine production issues. Downloads logs and SQLite datadir from remote Docker containers, and queries the Boltz PostgreSQL database remotely. Analyzes errors and queries databases for root cause analysis. Use when: (1) investigating fulmine production errors or failures, (2) checking swap/vHTLC/delegate task status in prod, (3) analyzing fulmine logs for recent issues, (4) debugging VTXO or transaction problems on mainnet, (5) inspecting Boltz swap state in PostgreSQL. Triggers on: "fulmine prod", "production logs", "prod errors", "check prod fulmine", "debug fulmine", "fulmine mainnet issue", "boltz db", "boltz prod".