Claude Skills by denniscalazans

Use when the user wants to inspect a web page, check UI state, verify element presence, explore an app interactively, create a replayable Playwright flow, or record a Retina-quality video of a browser interaction. Uses agent-browser for lightweight exploration (93% less context than Playwright MCP) and Playwright connectOverCDP for flows and recording — both on the same shared Chrome session. Framework-agnostic — works with any web application on any URL (localhost or remote). Triggers: "expl...

Use when the user needs to authenticate into a web app using agent-browser and 1Password, open a persistent browser session, log in as a specific role, switch between users, or manage named agent-browser sessions. Handles automated login via snapshot+refs discovery, session reuse, parallel multi-role login, and already-authenticated detection. Handles form-based login including Auth0 and Angular Material via agent-browser's fill command. Triggers: "login", "browser session", "authenticate", "...

Use when the user wants to run multiple Playwright flow files in parallel, batch-execute test suites across subagents, or collect results from many flows into a summary report. Also use when cross-batch learning is needed to avoid agents rediscovering the same failures independently. Triggers: "run flows", "parallel flows", "cross-batch", "run the flows", "execute all flows", "flow results".

Use when inspecting the local SonarQube infrastructure: which IDE embedded servers are running, which ports they own, and which MCP Docker containers are active. Also use when the user asks "what's listening on the sonar ports?", "which IDE is my MCP connected to?", or wants to check for port mismatches or orphaned containers. Triggers: "sonar environment", "sonar ports", "sonar-env", "sonar containers", "mcp containers", "port mismatch", "what's running", "check sonar infra", "sonar docker".

Use when the user wants to fix a SonarQube issue, resolve a code smell, or address a flagged violation. Also use when the user says "fix this issue", "resolve the ternary", or "clean up sonar findings". Triggers: "fix sonar", "fix issue", "resolve code smell", "fix violation", "sonar fix", "clean up issue", "address finding". Not for: triaging false positives (use sonar-triage), browsing issues without fixing (use sonar-issues).

Use when browsing, searching, or listing SonarQube issues for a project or PR. Also use when the user asks "what issues are there?", "show me the code smells", or wants to see issues by severity. Triggers: "sonar issues", "code smells", "show issues", "list issues", "what issues", "browse issues", "sonar findings".

Use when the user asks about a SonarQube rule, wants to understand why code was flagged, or needs compliant/noncompliant examples. Also use when seeing rule IDs like "S3358" or "typescript:S1135". Triggers: "explain rule", "what is S3358", "sonar rule", "why was this flagged", "show rule", "rule details", "noncompliant example".

Use when setting up SonarQube MCP integration, diagnosing connectivity issues, or checking which code-quality skills are functional. Also use when the user asks "is SonarQube working?", "set up sonar", or wants to enable IDE-connected mode. Triggers: "sonar setup", "configure sonarqube", "sonar not working", "mcp connection", "ide mode", "analyze_file_list", "sonar connectivity".

Use when checking code quality health, quality gate status, or dashboard metrics for a project or PR. Also use when the user asks "did my PR pass?", "how's code quality?", or wants a quick health check. Triggers: "quality gate", "sonar status", "code quality", "dashboard metrics", "did my PR pass", "quality check", "sonar health".

Use when the user wants to mark a SonarQube issue as false positive, accept it, or reopen a previously triaged issue. Also use when the user says "this is a false positive", "accept this issue", or "triage sonar findings". Triggers: "false positive", "triage", "accept issue", "sonar triage", "mark as false positive", "reopen issue", "not a real issue". Not for: fixing issues (use sonar-fix), browsing issues (use sonar-issues).

Use when the user wants to verify which SonarQube issues are fixed locally before pushing. Also use when cross-referencing server issues with local analysis results (RED/GREEN validation). Triggers: "verify fixes", "red green", "which issues did I fix", "sonar verify", "check local fixes", "pre-push check", "validate fixes".

Use when the user's input is messy, unstructured, or appears to come from voice transcription or fast typing. Also use when the input contains mixed languages, broken sentences, typos, false starts, contradictions, or multiple interleaved topics. Handles any task type — code, planning, decisions, writing, research. If the input looks chaotic and you're unsure what the user wants, use this skill before doing anything else. Triggers: "brain dump", "messy thoughts", "structure this", "braindump"...

Use when the user asks to distill, extract key insights, or restructure content for clarity. Also use when the user shares a brainstorm, thought dump, meeting notes, or long-form content and wants it transformed into a reader-friendly format. Triggers: "distill this", "extract insights", "make this clearer", "restructure for readability", "summarize this", "TL;DR", "key takeaways", "simplify this text", "clean this up", "organize my notes", "break this down".

Use when the user wants a plan, design, or architecture stress-tested through relentless questioning until reaching shared understanding — even if they don't say "grill" explicitly. Any request to challenge, probe, or poke holes in a plan qualifies. Does homework first — explores the codebase, researches trade-offs, ranks options with pros/cons — then asks surgical questions about what's genuinely ambiguous. Resolves each branch of the decision tree one-by-one, surfacing contradictions, hidde...

Applies strict plain-language writing rules to any content. Use this skill whenever the user asks to write, edit, review, clean, or improve any text — emails, reports, presentations, announcements, web copy, documentation, READMEs, or any written content. Also triggers on: "clean this text", "make this clearer", "rewrite this", "simplify", "plain language", "too wordy", "shorten this", or when the user pastes text and asks for improvements.

Use when writing or editing markdown files, PR descriptions, code comments, or documentation. Also use when producing commit bodies, README updates, or deciding whether content should be a table, list, or paragraph. Triggers: "format this", "write a PR description", "one sentence per line", "markdown convention", "writing style", "fix formatting", "paragraph spacing", "trailing spaces", "table or list".

Use when finishing a task and cleaning up local branches whose content is already in the default branch. Also use when the user wants to clean up after merging PRs or remove branches that were squash-merged or rebased. Triggers: "finish task", "forge finish", "clean up branches", "prune branches", "clean branches", "delete integrated branches", "remove merged branches", "done with task".

Use when implementing features, fixes, or infrastructure changes that modify code. Use when the user wants adversarial quality checking before committing. Do not use for trivial single-file changes like typos or comment edits. Triggers: "implement", "forge implement", "implement this ticket", "build this feature", "start implementing", "implement feature", "adversarial pipeline", "build with forge".

Use when the user has a clear goal but implementation hasn't started yet. Also use when Claude needs to understand existing codebase patterns, conventions, and constraints before proposing changes. Produces a "TODAY IS / EXPECTED IS" investigation report, then stops. Does NOT write code or propose implementations. Triggers: "investigate first", "explore the codebase", "what exists", "map the patterns", "today is expected is", "before we implement", "what are the conventions", "understand befo...

Use when starting a new task and wanting a clean working directory on the default branch. Also use when finishing a task, switching context, or returning to main after a PR. Triggers: "start task", "forge start", "reset", "switch to main", "start fresh", "back to main", "done with this task", "clean up workspace", "done with branch".

Use when interacting with the Figma REST API to read design files, extract components, export images, list projects, read variables, manage comments, or query any Figma design data programmatically. Also use when the user provides a Figma URL and wants to inspect its structure, extract design tokens, or export assets from it. Use this skill instead of the Figma MCP server when you need raw API access, batch operations, or endpoints the MCP doesn''t cover (comments, versions, projects, team co...

Use when working with 1Password CLI - injecting secrets into apps, managing vault items, or setting up shell plugins for biometric auth. Triggers: "1password", "op run", "op://", "secrets", "vault", "biometric auth", "inject secrets", "environment variables", "secure credentials", ".env setup", "MCP server secrets".

Use when the user wants to turn a researched CLI tool into a reusable, production-quality Claude skill for operating that one tool safely. Consumes a research bundle produced by learn-a-cli and generates a per-tool skill folder (SKILL.md plus references/, recipes/, and a version-drift preflight). Defaults to one skill per tool, refreshed in place. Triggers: "package this CLI as a skill", "make a skill for gh/kubectl/aws", "turn the research bundle into a skill", "generate a CLI skill", "cli a...

Use when the user wants to deeply research and understand a CLI tool before using it, or to produce a reusable research bundle about a command-line tool. Inspects local --help and man pages first, then official docs and the source repo, and captures the command surface, flags, structured-output modes, config, exit codes, safety profile, and examples into a structured bundle on disk. Triggers: "learn the X CLI", "research this command-line tool", "understand gh/kubectl/aws", "how does this CLI...

Write explanations, answers, and documents that a busy, tired, non-native-English reader can understand completely on the first read, with no rereading, no backtracking, and no follow-up questions. Applies a fixed method: verify the facts first, then produce a structured, jargon-free, step-by-step write-up with message-style headings, short connected sentences, problem/counter-pattern pairs, and small diagrams. Works in two modes: explaining a topic from scratch, or rewriting content the user...

Use when working with 1Password CLI - injecting secrets into apps, managing vault items, or setting up shell plugins for biometric auth. Triggers: "1password", "op run", "op://", "secrets", "vault", "biometric auth", "inject secrets", "environment variables", "secure credentials", ".env setup", "MCP server secrets".