Loading...
Loading...
Found 1,407 Skills
Deterministic 4-phase documentation drift detector: Scan, Cross-Reference, Detect, Report. Use when skills/agents/commands are added, removed, or renamed, when README files seem outdated, or before committing documentation changes. Use for "check docs", "sync README", "documentation audit", or "stale entries". Do NOT use for writing documentation content, improving descriptions, or generating new README files.
Hugo site link health analysis: scan markdown, build internal link graph, validate paths, and report issues. Use when auditing site link structure, finding orphan pages, checking for broken internal/external links, or validating image paths. Use for "link audit", "orphan pages", "broken links", "link health", or "site link structure". Do NOT use for single-post pre-publish checks or content editing.
Audit and maintain blog taxonomy (categories/tags) for consistency, SEO, and navigation: scan content, detect orphans and duplicates, merge and rename terms, verify builds. Use when user asks to "audit tags", "fix taxonomy", "consolidate categories", "merge tags", or "clean up taxonomy". Do NOT use for writing new content, individual post SEO optimization, or major content restructuring.
Gold-standard code review for SAP CC Go repositories against the project's lead review standards. Dispatches 10 domain-specialist agents in parallel — each loads domain-specific references and scans ALL packages for violations in their assigned domain. Produces a prioritized report with REJECTED/CORRECT code examples. Optional --fix mode applies corrections on a worktree branch. This is the definitive "would this code pass lead review?" assessment.
Systematic detection and prioritization of neglected code quality issues: stale TODOs, unused imports, deprecated functions, high complexity, dead code. Use when user requests "code cleanup", "find TODOs", "technical debt scan", or "quality of life fixes". Do NOT use for bug fixing (use systematic-debugging), feature work (use test-driven-development), or formatting-only (use code-linting).
Perses plugin scaffolding and creation: select plugin type (Panel, Datasource, Query, Variable, Explore), generate with percli plugin generate, implement CUE schema and React component, test with percli plugin start, build archive with percli plugin build. Use for "create perses plugin", "new panel plugin", "new datasource plugin", "perses plugin scaffold". Do NOT use for dashboard creation (use perses-dashboard-create).
Generate a project-specific CLAUDE.md by analyzing the current repository's code, build system, and architecture. 4-phase pipeline: SCAN, DETECT, GENERATE, VALIDATE. Auto-detects language/framework and enriches output with domain-specific conventions (e.g., go-sapcc-conventions for sapcc Go repos). Use for "generate claude.md", "create claude.md", "init claude.md", "bootstrap claude.md", "make claude.md". Do NOT use for improving an existing CLAUDE.md (use claude-md-improver instead).
General Technical Design Document Summarization Skill: Scan documents and diagrams in the current execution directory (Markdown, PlantUML/Mermaid, drawio, images, etc.), extract system objectives, module boundaries, core processes, sequences and states, and output structured technical design documents. Use this skill when users mention "technical design documents", "solution sorting", "summarize design based on existing documents", "summarize documents and diagrams in the directory", or "complete sequence diagrams/state diagrams".
ML supply chain security scanner. Scans model files, scores risk (0-100), maps to 5 global compliance frameworks (ISM-2072, EU AI Act, OWASP LLM, MITRE ATLAS, NIST AI RMF), and provides remediation steps. Zero-config, auto-installs scanners. Use when the user asks to scan a model, check if a model is safe, audit ML security posture, check compliance, inspect pickle/safetensors/pytorch files, or mentions model supply chain security. Also trigger on ISM-2072, EU AI Act, OWASP LLM06, model risk score, "is this model safe", "scan my models", "check compliance".
Propose a new spec-driven change. Scaffolds proposal.md, design.md, tasks.md, and questions.md for a named change, populated with project context.
Initialize a .spec-driven/ directory in a project. Creates config.yaml and specs/ scaffold, then guides the user to fill in project context.
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.