manastalukdar
UserProfessional development studio for Claude Code CLI
Categories
Indexed Skills (56)
config-cleanup
Garbage-collect a bloated Claude Code configuration (~/.claude and project .claude) — finds stale/duplicate skills, orphaned hooks, redundant permissions, dead MCP servers, and old caches/sessions, then confirms each deletion one at a time. Use when the user says "clean up my config", "my .claude is bloated", "too many skills", "audit my Claude setup", or after installing a large skill pack.
skill-validator
Internal skill that validates a new or modified AI DevStudio skill against project standards. Checks YAML frontmatter, token optimization section, line limit, and naming conventions. Used by the code-reviewer agent during PR review.
accessibility
Accessibility (a11y) compliance checking with WCAG 2.1 validation
agent-evaluate
Define behavioral contracts, run adversarial tests, and detect regressions for AI agents — invariants, edge cases, statistical analysis, and benchmark-production gap detection
ai-governance
Audit an AI/ML system for governance controls — bias risk, explainability, model risk management, data lineage, fairness metrics, and regulatory alignment (EU AI Act, NIST AI RMF)
ai-system-review
Review LLM application code for context assembly quality, retrieval integration, prompt construction, output validation, cost controls, and failure handling
api-test-generate
Auto-generate comprehensive API tests for REST and GraphQL endpoints with request/response validation
architecture-diagram
Generate architecture diagrams in Mermaid, PlantUML, or diagrams.net formats
assumption-map
Map and prioritize the riskiest assumptions behind a feature, product decision, or technical design — surface what would kill it if wrong, then propose the cheapest test for each
briefing
Generate a daily development briefing — recent git activity, open TODOs, pending PRs, failing tests, and session context — so you can start work immediately without manually checking multiple sources.
browser-testing-with-devtools
Use Chrome DevTools MCP for live DOM inspection, console error capture, network request analysis, and paint profiling — runtime verification beyond what Playwright scripting covers.
cache-strategy
Implement caching strategies for HTTP, service workers, and memoization
canary
Monitor a deployment for errors and regressions after shipping — polls logs, error rates, and key endpoints in a configurable loop until the deployment is confirmed healthy or a problem is detected.
careful
Intercept destructive commands before execution — rm -rf, DROP TABLE, force-push, git reset --hard, and similar irreversible operations. Prompts for confirmation and suggests safer alternatives. Inspired by gstack's careful skill.
chaos-test
Analyze codebase for resilience gaps — missing retry logic, absent timeouts, circuit-breaker opportunities, single points of failure, and degradation-mode blind spots
ci-sweep
React to CI failures on main or active branches — diagnose the failure type, propose a minimal fix for regressions, re-run flakes, and escalate infrastructure failures. Designed to run with /loop 15m.
cleanproject
Remove debug artifacts and temporary files safely with git checkpoint protection
code-review-checklist
Generate context-aware code review checklists for changes
commit
Analyze changes and create meaningful conventional commits with pre-commit quality checks
component-library
Scaffold component library structure with Storybook and documentation
conflict-resolve
Guided conflict resolution with semantic analysis and validation
context-budget
Report estimated context window utilization and flag when approaching the compaction threshold
context-engineering
Audit and curate the 5-layer agent context hierarchy to prevent quality degradation mid-session — rules files, specs, source files, error output, and conversation history.
context-restore
Restore work-in-progress context saved by /context-save — finds the most recent WIP commit on the current branch and unpacks it back to the working tree so you can resume exactly where you left off. Inspired by gstack's context-restore skill.
context-save
Save current work-in-progress context as a git WIP commit — captures all staged and unstaged changes with a timestamped stash message so you can switch contexts safely and restore later. Inspired by gstack's context-save skill.
continuous-learning
Extract repeated patterns from archived sessions and offer to convert them into reusable skills
cost-track
Report token spend per session and cumulative totals from session logs
cross-modal-review
Run a second-model quality gate on staged changes, a skill draft, or any generated output. A cheaper, independent model reviews the primary output for correctness, safety, and completeness before the user sees the final result.
db-diagram
Generate database ER diagrams from schema for documentation
ddd-model
Apply Domain-Driven Design — identify bounded contexts, model aggregates and value objects, map context relationships, and generate implementation scaffolding
debug-root-cause
Root cause analysis with dependency tracing and call stack analysis
agent-debug
Structured self-debugging for AI agent run failures — loop limits, repeated retries with no progress, context drift, or tool failures. Use when an agent session is stuck or degrading and needs a reproducible diagnosis instead of a blind retry.
click-path-audit
Trace every user-facing touchpoint (button, toggle, form submit) through its full state-change sequence to find interaction bugs where handlers individually work but conflict when combined — silent resets, async races, stale closures. Use when a button "does nothing" despite no crash or type error, after modifying a shared state store, or after a refactor touching shared state, and static debugging already came up empty.
code-tour
Generate VS Code CodeTour .tour JSON files with persona-targeted, step-by-step walkthroughs anchored to real file:line locations. Use when the user asks for a code tour, onboarding walkthrough, PR tour, architecture walkthrough, RCA tour, or a reusable guided explanation of how a subsystem works.
completion-verify
Verify a session's own work (build, types, lint, tests, diff scope, quick security check) before claiming a task is done. Use when about to say "done", before opening a PR, or after a feature/refactor is finished.
council
Convene four voices (Architect, Skeptic, Pragmatist, Critic) to surface structured disagreement on an ambiguous decision or go/no-go call. Use when multiple credible paths exist and no single review agent should have the final word.
changelog-auto
Auto-generate changelogs from commit history
project-health
Internal health check skill for AI DevStudio project. Checks skill count consistency across docs, detects stale sessions, and identifies cache files to clean. Not user-facing.
api-docs-generate
Generate OpenAPI/Swagger documentation from code analysis
api-examples
Generate API usage examples and tutorials from code analysis
api-mock
Generate API mocks and stub servers from OpenAPI specs or code analysis
api-validate
API contract validation and breaking change detection
brainstorm
Interactive design refinement with structured exploration
branch-finish
Complete branch workflow with squash, rebase, and cleanup
bundle-analyze
Bundle size analysis and optimization for Webpack, Vite, and esbuild
caveman
Activate ultra-compressed communication mode that drops ~75% token usage by eliminating articles, filler, pleasantries, and hedging while preserving technical accuracy. Use when user says "caveman mode", "be brief", "less tokens", or invokes /caveman.
ci-setup
Configure CI/CD pipelines for GitHub Actions, GitLab CI, CircleCI with best practices
complexity-reduce
Reduce cyclomatic complexity with targeted refactoring strategies
container-optimize
Docker/container optimization for size, layers, caching, and security
contributing
Contribution readiness assessment analyzing project guidelines and requirements
database-connect
Database MCP server integration for PostgreSQL, MySQL, MongoDB
debug-session
Document debugging sessions with hypothesis tracking and knowledge base
debug-systematic
Systematic debugging workflow with hypothesis testing
boilerplate
Generate framework-specific boilerplate code
config-generate
Generate configuration files for development tools
create-todos
Add contextual TODO comments for future development work
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.