Scan the org's communication surfaces (chat like Slack or Teams, open PRs, RFC docs and design docs, ticket threads, whichever MCPs are connected) for high-leverage discussions the user should weigh in on, decisions still being formed, people stuck or circling, questions squarely inside the user's domains, cross-team…
Goal-driven smoke test for the feature just implemented. Drives a browser (UI) or hits the running service (backend), both, when full-stack. Tests every behaviour acceptance criteria define plus exploratory edges, catches console errors / network failures / a11y issues / contract violations / auth leaks / missing…
Pre-commit audit. Invoke before every git commit. Diffs the staged change against the repo's "canaries" (README, decision log, roadmap, public API, doc comments, release notes, test discipline) and surfaces anything that's drifted out of sync. Updates the obvious drifts in place; flags judgement calls for the operator.
Generate a two-part standup report: Yesterday (everything code-related you shipped, reviewed, or addressed since your last working day, PRs merged, reviews left and answered, comments addressed, deploys that fired, tickets closed) and Today (carry-over threads plus priority-ordered queue items, framed as "likely…
Draft comprehensive Technical Design Documents. Analyzes codebase, fetches ticket/design/doc context via MCP. Every technical claim is verified against actual code. Unverified information is explicitly marked. Use when the user wants to write a TDD, create a technical design document, plan a large engineering project…
Use when proposing, writing, or reviewing automated tests, defines what a good test is: behavior over implementation details, and the Testing Trophy with a hard floor on end-to-end coverage for user-facing features. Generalized to any language and any layer (frontend, backend, CLI, library), not just JS/React.…
Create well-structured tickets as reviewable markdown files, then push to any tracker (Jira, Linear, Trello, Asana, Shortcut) via MCP or CLI after user review. Grounds each ticket in actual code by calling /flagrare:codebase-explore before drafting, and polishes the Context section via /flagrare:write-docs. Use when…
Socratic tutor mode. Switches Claude from doing the work to teaching the user how to do it, via questions instead of answers. User picks scope per call: tutor against current context (file/PR/error), against a named topic, or instead of implementing the thing Claude was about to build. Refuses to give the answer…
Uninstall the flagrare plugin and remove the marketplace. Use when the user says 'uninstall flagrare', 'remove flagrare', 'disable flagrare skills', or 'remove flagrare-skills'.
Pull the latest flagrare skills from GitHub. Use when the user says 'update skills', 'refresh skills', 'pull latest skills', 'update flagrare', or 'sync skills'.
Goal-locked UX audit. Drives a real browser through every reachable route (or a user-specified scope) and every visible affordance, screenshots each state, and ships a severity-ranked findings table (High/Medium/Low) with location, why-it's-painful, and recommended fix. Installs Chrome DevTools MCP automatically if…
Orchestrates the full preparation workflow for a ticket. Calls /flagrare:intake (which gathers context from Jira/Notion/Figma, grounds the brief in the codebase via /flagrare:codebase-explore, then asks codebase-informed clarifying questions), then hands the codebase-grounded brief to /flagrare:atdd-plan for a…
Post-implementation quality gate. Runs automated checks (tests, lint, types), invokes /flagrare:implementation-review for the seven-check parallel review, then performs additional SOLID and Clean Code review on any findings not covered. Use when the user says 'wrap up', 'review changes', 'check my work', 'am I done'…
Write documentation that reads like a person wrote it for another person. The skill teaches the craft layer first, how to set context, how to calibrate tone, how to escape the curse of knowledge, when prose beats a bullet list, and only then the structural conventions (Diátaxis modes, README landing-page arc). Use…
Socratic-method tutor for Claude Code with anti-dependency design. Teach yourself any subject, codebase, or concept through dialogue with Echo, Cipher, or Vex.
Socratic-method tutor for Claude Code. Asks questions, reveals hints in layers, refuses to give you the answer until you've made the discovery yourself.
Start a Socratic tutoring journey grounded in an actual codebase. Reads files via Read/Grep/Glob to build the learning path; concepts carry file:symbol anchors so the tutor can reference real code. Invoke with a path: /tutor-codebase ./my-repo (defaults to 'overview' aspect) or /tutor-codebase ./my-repo 'auth flow'…
Close an active tutoring topic. Calculates XP earned from per-concept first-attempt quality, marks the topic complete in state, runs the hybrid feedback flow (thumbs + targeted rotating question with cycles rewards), and logs feedback for later analysis. Invoke when you're done with a topic. Use with no arg to close…
Show the learning path for an active or completed tutoring topic — the ordered list of prerequisite concepts with progress markers and dependency annotations. Internal-by-default; the path is generated by /tutor-start but kept hidden unless the user explicitly asks to see it. Invoke with no arg to show the current…
Start a tutoring session on the current working directory — convenience wrapper for /tutor-codebase against $PWD. Accepts an optional aspect: /tutor-project (defaults to overview) or /tutor-project 'how requests flow'. Triggers: '/tutor-project', 'tutor me on this project', 'tutor me on what I'm working on', 'teach me…
Pick up a paused tutoring session. Finds the user's active in-progress topic, briefly reorients them (where they are, what's acquired, what's coming), and hands the dialogue back to the active persona. If multiple topics are in progress, asks which one. Invoke when you're returning after a break. Triggers…
Start a Socratic tutoring journey on any user-supplied topic. Generates a learning path of 5-8 prerequisite concepts, calibrates the user's knowledge via 3 graduated prompts, charges 1 cycle, and hands off to the active Echo/Cipher/Vex persona for the dialogue. Invoke with the subject as an argument (e.g. /tutor-start…
Show the llm-tutor dashboard — XP total, cycles balance with time-until-next-refill, active topics with progress, completed topics with XP earned, and lifetime stats. Invoke with no arguments. Triggers: '/tutor-status', 'show me my tutor status', 'how am I doing', 'check my XP', 'where am I at with the tutor'.