hoangsa

This skill should be used when the user is building, changing, or trying to verify a frontend feature on web (React/Vite) or React Native/Expo, and is unsure how to prove it actually works. Triggers on phrases like 'how do I test this component/screen', 'verify this feature', 'make sure this works on web/mobile', 'is this covered by tests', 'my tests pass but the feature is broken', 'no tests yet', or before shipping any FE change. Guides the full loop: define verifiable success criteria before coding, write tests at the correct layer (logic/component/E2E/visual), and confirm behavior by running the real app.

This skill should be used when the user wants to start a new task, switch between tasks, park or resume work, finish a task (push + PR), clean up merged branches, or sync with upstream. Triggers on phrases like 'start task', 'new task', 'work on', 'switch to', 'park this', 'resume', 'continue where I left off', 'done with this', 'finish task', 'create PR', 'clean branches', 'delete merged', 'rebase', 'pull latest', or 'sync with main'.

Use when the user needs to run hoangsa-memory CLI commands — init / index / query / watch / memory / archive / impact / context / changes / graph / projects. Examples: "index this repo", "show memory", "trace the graph", "find taint paths", "consolidate memory".

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "why is X failing?", "where does this error come from?", "trace this bug", "who calls this method?", "this endpoint returns 500".

This skill should be used before any non-trivial coding action — editing code, writing new files, running migrations, deploying, or answering a question that involves factual claims about this codebase. It forces the agent to consult hoangsa-memory's persistent memory (USER.md, MEMORY.md, LESSONS.md, the indexed code graph) and acknowledge relevant lessons before acting. Trigger phrases: "edit", "refactor", "implement", "fix the bug in", "add a feature", "deploy", "why does this do", "how does X work".

Use when the user asks about hoangsa-memory itself — available MCP tools, CLI commands, resources, prompts, skill catalog, or how to drive the memory/graph workflow. Examples: "what hoangsa-memory tools are available?", "how do I use hoangsa-memory?", "what skills do I have?".

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "is it safe to change X?", "what depends on this?", "what will break?", "show me the blast radius". Also compose with PR review — run this per touched symbol after `gh pr diff`.

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "rename this function", "extract this into a module", "split this class", "move this to a separate file", "refactor this service".

This skill should be used at the end of a coding session, after a bug fix, a finished feature, a deployment, or whenever the user says "we're done", "wrap up", "summarize the session", "what did we learn", or "save what you learned". It drives a structured self-reflection pass that decides whether to persist new preferences, facts, lessons, or skills to hoangsa-memory's long-term memory. Also triggers on phrases like "reflect", "postmortem", or "retrospective" applied to the current session.

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "how does X work?", "what calls this function?", "show me the auth flow", "where is the DB logic?".

This skill should be used when the user provides screenshots, videos, screen recordings, or mentions visual bugs, UI glitches, layout shifts, animation issues, or visual regressions. Analyzes media files to create annotated montage grids with diff overlays for visual debugging.