skills/suggesting-next-steps/SKILL.md
Use this skill to suggest prioritised next steps for a project. Triggers when the user asks what to work on next, wants to resume after a break, or needs help prioritising a backlog.
npx skillsauth add mattobee/skills suggesting-next-stepsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Analyse a project's current state and suggest prioritised next steps. This is a read-only skill — gather and organise information, do not make changes.
Collect whatever signals are available. Not every project has all of these — adapt to what exists. Do not block on missing sources.
git status — uncommitted changes, staged filesgit branch — local branches, especially any that look like work-in-progressgit log --oneline -20 — recent commit history to understand what was worked on lastgit stash list — stashed changes that may have been forgottengh pr list --state open — open pull requests (these are active work)gh issue list --state open --limit 30 — open issuesgh issue list --label bug --state open — bugs specifically (these take priority)If gh is not authenticated or the repo has no remote, skip GitHub queries and note it.
Look for any of these in the repo root or docs/:
STATUS.md — implementation status tracking (e.g., sections for "Implemented", "Partially Implemented", "Not Started")ROADMAP.md, TODO.md, CHANGELOG.md — other common tracking filesWhen a tracking file exists, it is the primary source for what is done and what remains. Parse its structure and extract incomplete items with as much specificity as available (sub-features, specific user stories, named gaps).
AGENTS.md — project description, goals, architecture. Use for context about what the project is and what matters, not as a source of tasks.README.md — project overviewdocs/ — long-term goals and scopepackage.json (or equivalent) — scripts that exist, test setup, dependenciespackage.json and whether test files exist in the repogh run list --limit 5Group what was found into five categories, presented in this order:
Unfinished work from previous sessions. This is the highest-priority category because it represents interrupted momentum.
Things that are broken or degraded. These should be addressed before new work.
Partially implemented features with specific incomplete sub-tasks identified. This comes from tracking files (STATUS.md), GitHub issues with checklists, or PRD sections that map to existing but incomplete code.
List the specific incomplete sub-tasks, not just the feature name. "Conformance tracking: evaluation status, pass/fail/NA per criterion, summary view" is useful. "Finish story 08" is not.
Highest-impact work that hasn't been started yet. Draw from:
Do not list everything. Pick the 3–5 items that appear most impactful based on project context. If a PRD or roadmap suggests phasing, respect it — do not suggest Phase 3 work when Phase 1 is incomplete.
Maintenance and quality improvements. Lower urgency but worth noting.
For each item, provide:
Keep it concise. The goal is orientation, not a project plan. If a category has no items, omit it entirely.
If there is genuinely nothing to suggest — the project is clean, tests pass, no open issues, tracking is up to date — say so.
gh fails, rely on local signals (git history, tracking files, project docs). Note the limitation but don't treat it as a blocker.data-ai
Use this skill to create Obsidian event notes for the day's calendar meetings, each pre-populated with grounded talking points. Triggers when the user asks to prepare for their meetings, create notes for today's calendar events, set up meeting notes, or get ready for the day. Pulls the events they have accepted, creates one note per meeting following the vault's event conventions, and fills a prep section with talking points grounded in prior meeting notes, related project notes, recent GitHub activity, and Slack threads. Use it for daily meeting prep even when the user doesn't mention Obsidian or notes by name.
tools
Use this skill to work through review feedback on a pull request — read the inline review comments, assess each one's validity, make the code changes that are warranted, and reply to every thread with a one-line explanation of what was done (or why it was declined). Triggers when the user asks to address PR feedback, respond to reviewers, work through review comments, handle a code review, action the comments on a PR, or asks "what do the reviewers want changed?" Also triggers when resuming work on a PR that has open review threads.
testing
Use this skill to write Playwright accessibility tests using the two-layer strategy (axe-core scans + targeted assertions). Triggers when adding accessibility test coverage, reviewing test gaps, writing axe scans, or creating Playwright assertions for accessible names, landmarks, ARIA states, focus management, or contrast.
development
Use this skill to review implemented UI code for WCAG accessibility compliance. Triggers when reviewing components, pages, or templates for accessibility, auditing a feature after implementation, or answering questions about accessible patterns, ARIA, keyboard navigation, or screen reader support.