easier-life-skills

Process the top Todo card on a GitHub Project (v2) board end-to-end: pull the board into a task-agent `tasks.yml`, run `task-agent` to open a PR for the top pending task, sync the PR back to the card, then wait for Copilot to review the PR and apply fixes for actionable comments. Use when the user says "work on the next task", "do the next board task", "pick up the next GitHub project item", "process the next card", "work on the next item in github project", "run the next board task", "drain the top todo", "process the top board todo", "auto-process the next card", or any phrasing that means "take the next pending item from a GitHub Project board and implement it". Composes `gh-project-sync` → `task-agent` → `gh-project-sync` → `copilot-review-fixer` (skill wrapper shipped by `task-agent`) via the `workflow` skill against the fixed YAML at `${CLAUDE_PLUGIN_ROOT}/workflows/auto-board-task.yaml`. All arguments are forwarded verbatim to the workflow runner; validation happens there and inside the composed sub-sk

Reads unresolved Copilot review comments on a pull request and applies code fixes for actionable ones. Thin skill wrapper around the `copilot-review-fixer` sub-agent — callable as a workflow step.

Reads a list of tasks in a yaml to be done in certain github repos. Agents clone the repo, do the task, commit the changes and create a PR. Not to be called automatically by Claude by any means.

Reconciler between a GitHub Project (v2) board and a task-agent unified `tasks.yml`. Use when the user asks to "sync the project board with tasks.yml", "reconcile the GitHub project", "pull Todo cards into the task queue", "push completed tasks back to the board", or supplies both a project URL/number and a tasks file. Arguments use `key=value` grammar: `tasks=<path>` (required), one of `project_url=<url>` OR `project_owner=<owner> project_number=<n>` (required), optional `default_repo=<owner/repo>` (for draft cards without a linked issue), and optional column name overrides `todo_column=…`, `in_review_column=…`, `done_column=…`, `wont_do_column=…` (default: `Todo` / `In Review` (falling back to `In Progress` if the board has no `In Review` column) / `Done` / `Won't Do`). Idempotent — running it any number of times converges to the same state.

Scan all dependencies for outdated versions and known security vulnerabilities. Uses npm audit / pip-audit / cargo audit / bundler-audit with grep-based fallbacks when dedicated tools are unavailable. Produces a prioritised, read-only report. Use when the user asks to "audit dependencies", "check for vulnerabilities", "find outdated packages", "run a dependency audit", "check npm audit", "scan for CVEs in dependencies", or anything about dependency security or freshness.

Run a multi-step skill workflow declared in a workflow YAML file. Use when the user asks to "run the workflow at <path>", "execute workflow <name>", "run the <name> workflow", "chain these skills", "compose <skill-a> and <skill-b>", or supplies a path to a `.yaml` workflow definition. Arguments follow a `key=value` grammar: the first positional value is the workflow file path, remaining `key=value` pairs are workflow inputs. The runner executes steps strictly in order, halts on the first non-zero exit, and writes a summary JSON to the workflow directory.

Scan a codebase for OWASP Top-10 vulnerabilities, hardcoded secrets, insecure dependencies, and unsafe code patterns. Produces a read-only markdown report ranked by severity (Critical / High / Medium / Low). Use when the user says "security review", "scan for vulnerabilities", "check for secrets", "audit my code for security issues", "find OWASP issues", "check for hardcoded passwords", "security audit", or "find insecure patterns".

Read the project and suggest the 5 most valuable features or improvements the developer could build next. Use when the user asks "what should I build next?", "brainstorm ideas for this project", "what features are missing?", "how can I improve this?", "what's worth adding?", "give me ideas", or anything about deciding what to work on next. Also use when the user seems stuck or is asking for direction on their project. TRIGGER this skill whenever the user asks for ideas, suggestions, or "what next" guidance about their own codebase — even if they don't say "brainstorm" explicitly.

Analyze git history and report breaking changes in REST APIs. Use when the user asks to "find breaking API changes", "check for breaking REST changes", "what endpoints did I break", "is this a breaking change", "compare API versions", "what changed in the API", or anything about REST endpoint compatibility. Works for Flask, FastAPI, Express, Spring Boot, and OpenAPI/Swagger specs. Handles multi-file routers, shared request/response schemas, auth changes, and path prefix changes. Reads git history — no external tools required. TRIGGER this skill whenever the user mentions REST APIs, endpoints, routes, or API versioning alongside words like "breaking", "changed", "removed", "compatible", or "diff".

Find unused code — functions, classes, variables, imports, constants, types, and more. Use when the user asks to "find dead code", "find unused code", "clean up unused imports", "find unreachable code", or "find what can be deleted". Accounts for dependency injection frameworks (Spring, CDI, NestJS, Angular, etc.) to avoid false positives.

Audit and improve logging quality across a codebase. Use when the user asks to "improve logging", "fix log levels", "add logging", "review our logs", "make logging consistent", "we have bad logging", or anything about log messages being unclear, missing, or at the wrong severity. Produces a prioritized list of recommendations — does not edit files directly.

Generate or update CHANGELOG.md files by reading git history. Use this skill whenever the user wants to document what changed in their project — whether they say "create a changelog", "update the changelog", "write release notes", "what's new since v1.2", "document changes for this release", "prep the changelog before we ship", or anything else about recording or summarizing code changes for a version or release. Also use it when the user asks to reformat an existing CHANGELOG to Keep a Changelog format. Works for single repos and monorepos. Always prefer this skill over improvising — it handles deduplication, categorization, and format detection correctly.

Create or improve project documentation. Use when the user asks to "document the project", "create docs", "improve documentation", "write a README", "add a getting started guide", or mentions that documentation is missing or outdated. Produces a minimal root README.md and a /docs directory with linked pages. All diagrams use ASCII or Mermaid.

Analyze the active repository and find Claude Code skills from known marketplaces that would be useful for this project. Use when the user asks "what skills are useful for this project?", "find skills for my repo", "what plugins should I install?", "are there any skills for this?", or "recommend skills". Optionally searches online if the user explicitly includes "online" or "search the web" in their request.

Generate a complete plugin skeleton (directory tree, plugin.json, phase-structured SKILL.md, evals.json with 3 placeholder cases, and optional agents/references) from a single prompt. Use when the user asks to "scaffold a plugin", "create a new skill", "generate a plugin skeleton", "bootstrap a skill", "start a new plugin", or anything about creating a fresh plugin in this marketplace. Arguments follow a key=value grammar — see the Investigation phase for the full syntax. The generator is idempotent: it refuses to overwrite an existing plugin directory unless the `force` flag is passed.

Audit a website for UX issues, bugs, accessibility problems, performance issues, and behavior that would surprise users. Use when the user says "audit this site", "check this URL", "review this website", "find issues on", "test this page", "what's wrong with", or anything about evaluating a live website for quality. Writes a site-audit-report.md with findings grouped by severity.

Audit database indexes TODO: expand this paragraph with the user phrases that should trigger the skill (e.g. "find unused code", "audit my logs"). The description is the primary matching signal Claude uses, so make it specific.

Analyze and improve a CV and LinkedIn profile for software industry roles. Use when the user asks to "improve my CV", "review my resume", "optimize my LinkedIn profile", "help with my LinkedIn", "make my resume better", "create a CV", "prepare my resume for job applications", "update my LinkedIn", or anything about career documents for software engineers, developers, product managers, product owners, engineering managers, tech leads, SREs, DevOps engineers, data engineers, ML engineers, or other software-industry roles. The user must provide a CV file path and a path to an unzipped LinkedIn data export directory (obtained via LinkedIn's "Get a copy of your data" feature). If either is missing, ask for both before proceeding and — if the export is missing — walk the user through requesting it.