Generate missing verification tool configs (linter, test runner, CI pipeline, coverage) to bring a project up to autonomy level L2. Use when the user says 'scaffold quality tools', 'add linting', 'set up CI', 'improve test infrastructure', or after /autonomy-assess shows the project is below L2. Shows a dry-run plan before applying.
From famdecknpx claudepluginhub ivintik/private-claude-marketplace --plugin famdeckThis skill uses the workspace's default tool permissions.
evals/evals.jsonSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
This skill generates the configs a project needs to reach L2 autonomy — the level where an agent can work independently with quality gates catching mistakes. It detects the project's language (Python, TypeScript, Go, Rust) and generates idiomatic configs for that ecosystem.
Never generate configs without showing the user what will be created. The dry-run runs an assessment, identifies gaps, and shows exactly which files will be created or modified:
python -c "
from famdeck.autonomy.scaffold import scaffold_and_reassess
plan, report = scaffold_and_reassess('$PWD', dry_run=True)
if plan.is_empty:
print('No scaffolding needed -- project is fully configured.')
else:
print('Scaffolding plan:')
for f in plan.files:
print(f' CREATE {f.path} -- {f.description}')
for s in plan.pyproject_sections:
header = s.split(chr(10))[0]
print(f' APPEND to pyproject.toml: {header}')
if plan.package_json_updates:
print(f' UPDATE package.json: {list(plan.package_json_updates.keys())}')
print()
print(report.summary())
"
Present the plan and explain each item — what it does and why it's needed. Wait for the user to confirm before applying.
python -c "
from famdeck.autonomy.scaffold import scaffold_and_reassess
plan, report = scaffold_and_reassess('$PWD')
print('Scaffolding applied.')
print()
print(report.summary())
"
After applying, the reassessment shows the new autonomy level. If the project reached L2, say so. If gaps remain (e.g., the scaffolder doesn't cover every tool), explain what's still needed and suggest manual next steps.
If famdeck is not importable, scaffold manually based on what /autonomy-assess found missing. Use standard configs for the detected language — e.g., ruff.toml for Python linting, .github/workflows/ci.yml for CI, vitest.config.ts for TypeScript testing. The goal is the same: get the project to a state where tests, linting, and CI are all in place.