skills-catalog/ln-112-project-core-creator/SKILL.md
Creates core project docs (requirements, architecture, tech stack, patterns catalog). Use for any project regardless of type.
npx skillsauth add levnikolaevich/claude-code-skills ln-112-project-core-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Paths: File paths (
shared/,references/,../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Ifshared/is missing, fetch files via WebFetch fromhttps://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.
Type: L3 Worker
L3 Worker that creates 4 core project documentation files. These are ALWAYS created regardless of project type.
From coordinator:
contextStore: Full Context Store with all discovered data
targetDir: Project root directoryMANDATORY READ: Load shared/references/docs_quality_contract.md, shared/references/docs_quality_rules.json, and shared/references/markdown_read_protocol.md.
| File | Target Sections | Questions | Auto-Discovery | |------|-----------------|-----------|----------------| | docs/project/requirements.md | Functional Requirements (FR-XXX-NNN format) | Q23 | Low | | docs/project/architecture.md | 11 arc42 sections with C4 diagrams | Q24-Q34 | High | | docs/project/tech_stack.md | Frontend, Backend, Database, Additional | Q35-Q38 | High | | docs/architecture/patterns_catalog.md | Pattern summary, 4-score model, trend tracking | — | High |
For each document (docs/project/requirements.md, docs/project/architecture.md, docs/project/tech_stack.md, docs/architecture/patterns_catalog.md):
references/templates/docs/project/requirements.md: derive requirements from current product/project sources and normalize to FR-XXX structuredocs/project/architecture.md: derive structure from current source tree, ADRs, and runtime boundaries; generate diagrams from live code factsdocs/project/tech_stack.md: derive versions and rationale from current dependencies and config filesdocs/architecture/patterns_catalog.md:
shared/templates/patterns_template.md<!-- Auto-detected by ln-112, audit with ln-640 -->{{PLACEHOLDER}} with Context Store valuesSCOPE, DOC_KIND, DOC_ROLE, READ_WHEN, SKIP_WHEN, PRIMARY_SOURCESQuick Navigation, Agent Entry, Maintenance[TBD: ...]For each created document:
Quick Navigation, Agent Entry, Maintenance)Return to coordinator:
{
"created_files": ["docs/project/requirements.md", "docs/project/architecture.md", "docs/project/tech_stack.md", "docs/architecture/patterns_catalog.md"],
"skipped_files": [],
"quality_inputs": {
"doc_paths": ["docs/project/requirements.md", "docs/project/architecture.md", "docs/project/tech_stack.md", "docs/architecture/patterns_catalog.md"],
"owners": {
"docs/project/requirements.md": "ln-112-project-core-creator",
"docs/project/architecture.md": "ln-112-project-core-creator",
"docs/project/tech_stack.md": "ln-112-project-core-creator",
"docs/architecture/patterns_catalog.md": "ln-112-project-core-creator"
}
},
"validation_status": "passed",
"diagrams_generated": 3
}
[TBD: ...], TODO, or leaked template metadataDocuments describe contracts and decisions, NOT implementations:
<!-- NO_CODE_EXAMPLES: ... --> tag - FOLLOW ITTables > Mermaid/ASCII diagrams > Lists > Text
MANDATORY READ: Load shared/references/docs_generation_summary_contract.md
Accept optional summaryArtifactPath.
Summary kind:
docs-generationRequired payload semantics:
worker = "ln-112"statuscreated_filesskipped_filesquality_inputsvalidation_statuswarningsWrite the summary to the provided artifact path or return the same envelope in structured output.
references/templates/requirements_template.md, references/templates/architecture_template.md, references/templates/tech_stack_template.mdshared/templates/patterns_template.mdreferences/questions_core.md (Q23-Q38)Version: 2.2.0 Last Updated: 2025-01-12
testing
Checks runtime lifecycle and config validation: bootstrap, shutdown, probes, cleanup, env sync, and fail-fast startup. Use for runtime readiness.
testing
Checks races, deadlocks, async hazards, TOCTOU, blocking I/O, and shared resource contention. Use when auditing concurrency correctness.
testing
Checks diagnosability through structured logs, metrics, traces, correlation IDs, and useful log levels. Use when auditing incident visibility.
development
Finds code that can be safely deleted: unreachable, unused, obsolete compatibility, and commented-out code. Use when pruning dead code.