skills

Detect code-improvement catalog violations in recent PR files and guide small stacked commits/branches.

Mentor for Exercism exercises: hints while solving, code review and improvement suggestions when asked. Use when solving Exercism challenges, mentions exercism-mode or exercism-mentor, or asks for help on https://exercism.org/tracks/typescript or any Exercism track.

Review pull requests using the tools available in the current environment. Works with GitHub or Bitbucket, MCP tools or CLI tools, and local git diffs. Produces actionable review findings, optional human-inspection callouts, and optional PR comments including both an overall review comment and inline file/line comments when posting is requested.

Create a concise, visual technical HTML walkthrough for a pull request by combining PR code changes with Specs/OpenSpec/design artifacts. Use when the user asks to explain what changed in a PR, generate a PR walkthrough, produce architecture/design documentation for a PR, summarize a spec-backed implementation, or create visual delta docs with Mermaid diagrams. Prefer this skill over a normal PR review when the user wants understanding, onboarding, or design explanation rather than defect findings.

Launch parallel agent sessions in the current cmux workspace from a list of input items. Use when the user wants to script cmux, keep the current pane on the left, create a right-side vertical stack with one pane per item, run Codex, Claude Code, Cursor Agent, or Rovo Dev over a list, trigger a custom skill or prompt for each item, or monitor parallel agent runs in cmux. If the user has not clearly specified an agent, ask which agent to use before spawning panes.

Break a feature definition markdown file into independently-grabbable OpenSpec changes organized by feature capability, then scaffold each one via OpenSpec Propose. Use when the user wants to convert a feature file into OpenSpec changes, create spec-driven change proposals from a feature definition, or split a medium/small feature into sequenced OpenSpec work items. Assume the feature file is passed as input; if it is not provided, ask the user for the feature file before proceeding.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Summarize project status across plans, features, issues, tasks, and OpenSpec changes as a color-coded scrum report. Use when the user asks for a scrum update, standup summary, project status, progress report, or where the project stands.

Brainstorm and define a medium or small software feature before implementation. Use when the user wants to explore an idea, design a feature, clarify requirements, turn a vague feature request into a concrete markdown feature definition, or start the medium/small feature workflow before RFCs, issues, tasks, or code.

Break a feature definition markdown file into independently-grabbable implementation issues organized by feature capability. Use when the user wants to convert a feature file into issues, create implementation tickets from a feature definition, or split a medium/small feature into work items. Assume the feature file is passed as input; if it is not provided, ask the user for the feature file before proceeding.

Break an issue file into concrete, ordered, AI-executable tasks. Use when the user wants to implement an issue, start work on a ticket, or break down an issue into smaller steps.

Finish completed work on the current git branch by confirming source and target branches, marking current issue/task/feature index markdown as done when present, diffing against the target branch, generating a PR summary, and either creating a GitHub or Bitbucket pull request or merging locally. Use when implementation is complete and the user wants to finish work, create a PR, open a pull request, merge locally, or prepare branch changes for review.

Use when implementing any feature or bugfix, before writing implementation code

List and inspect open GitHub and Bitbucket pull requests across configured repositories. Use this skill when the user asks for a PR dashboard, open PR summary, recent pull requests by repo, reviewer/status overview, or asks to drill into additional pages of PRs for a configured GitHub or Bitbucket project.

Manage Raindrop.io bookmarks, collections, tags, highlights, imports, exports, and bookmark cleanup via the Raindrop REST API. Use when the user mentions Raindrop, raindrop.io, bookmarks, saved links, collections, tags, web highlights, reading lists, URL organization, or asks to search, save, update, move, bulk edit, import, export, or audit bookmarks.

Summarize links, articles, blogs, bookmarks, and reading material into Sathish's Smartnotes Obsidian vault. Use when the user asks to save, summarize, file, index, convert, combine, or organize bookmarked web content as fleeting notes, permanent notes, literature notes, or H3-indexed Smartnotes entries in the mysmartnotes vault.

Use this skill when the user wants to annotate, review, or provide feedback on a generated HTML spec, diagram, prototype, or executive artifact. It adds a lightweight browser annotation plugin to the HTML, guides the reviewer to export feedback JSON, and applies unresolved feedback back to the source without rereading the entire HTML page.

Read Markco markdown comments from feature and issue planning files, confirm the exact file scope with the user, incorporate unresolved feedback into the markdown, and mark addressed Markco comments as resolved. Use when the user asks to handle Markco comments, annotated feedback, markdown feedback, or reviewer comments on feature/issue specs.

Build or serve a local HTML viewer for markdown documentation in a repository's `codewiki/` folder. Use when the user asks to launch, open, view, serve, render, or generate an HTML site for CodeWiki docs. If `codewiki/` markdown files are missing, ask the user whether they want to generate the wiki first before attempting to start the viewer.

AI-powered codebase documentation generator inspired by Deepwiki. Analyzes any code repository using a four-stage pipeline (Preprocessing → Research → Documentation → Verification) and generates comprehensive markdown documentation in a `codewiki/` folder. Produces C4-model architecture diagrams, workflow documentation, deep-dive module analyses, boundary interfaces, and database overviews using Mermaid. Works with all programming languages. Use when the user wants to generate documentation, create a wiki, understand a codebase, or analyze architecture for any repository.

Generates comprehensive 4+1 Architecture Blueprint documentation for any codebase. Analyzes project structure, identifies architectural elements, and creates markdown wiki documents organized by Logical View, Process View, Development View, Physical View, and Scenarios (use cases). Produces Mermaid diagrams for each view. Use when the user wants to create architecture documentation, generate a deepwiki, analyze system architecture, or document a codebase using the 4+1 architectural views model.

AI-powered C4 model documentation generator for any codebase. Analyzes project structure, identifies architecture patterns, creates C4 context/container/component diagrams, and generates comprehensive markdown documentation in c4wiki/ folder. Works with all programming languages.

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Systematically debug issues using graph-powered code navigation

Debug and explain production incidents by combining prometheus-metrics-analyzer and loki-logs-analyzer workflows, correlating Prometheus metrics with Loki logs over the incident window.

Analyze logs to investigate errors and exceptions

Analyze metrics to debug alerts or incidents

Create a PRD through user interview, codebase exploration, and module design, then save it as a file. Use when the user wants to write a PRD, create a product requirements document, or plan a new feature.

Implement one issue or task file on a normal git feature branch. Use when the user asks to implement an issue or task without a worktree, wants git-flow style branch handling, or wants branch parent selection based on issue/task relationships. If the input issue or task file is missing, ask for it before proceeding.

Implement one issue or task file in an isolated git worktree. Use when the user asks to implement an issue or task with worktree isolation, when the current workspace is dirty, or when parallel implementation may be useful. If the input issue or task file is missing, ask for it before proceeding.

Implement a feature directory, list of issue files, or list of task files by scheduling independent work across subagents. Use when the user wants parallel implementation, wants multiple issues or tasks executed, or asks to use subagents to implement a feature. Determine dependency order, ask the user for branch or worktree strategy, run unblocked work in parallel, and wait for completion or user confirmation before dependent work.

Log user prompt requests from the current coding session into one append-only session markdown file. Use when the user asks to log, capture, record, journal, audit, or save their prompts, instructions, requests, or coding-session inputs. Use this skill whenever prompt_requests or prompt logging are mentioned.

Perform a language-agnostic first-pass code review covering logic errors, bad practices, operation ordering, magic strings, pattern improvements, strict type checking, and SQL injection. Use when asked to review code, audit a file, or check a diff. Accepts a single file, a diff with multiple hunks, or can explore the repo when needed to resolve external references. If no input is provided, ask the user to share a file or diff before proceeding.

Run a cross-cutting audit across all code produced for a feature. Use when a feature is complete, all PRs are merged, and the user wants a final review for security issues, logic errors, consistency, and best practices.

Break a PRD into independently-grabbable issues using tracer-bullet vertical slices. Use when the user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.