dinhanhthi
UserLean toolkit for disciplined engineering workflows with AI Agents (Claude Code, Codex, Oh-my-pi, Cursor, Grok CLI, Antigravity, ZCode).
Categories
Indexed Skills (27)
cf-design
UI design workflow — scan existing UI patterns, design new UI from a description, or modify existing UI while keeping it visually consistent with the rest of the project. Use when the user wants to: design or redesign a component, page, or section; change colors, typography, spacing, or visual style; understand the project's current design system; add new UI that should match existing patterns; or ensure a UI change doesn't look out of place. Use when the user says things like "make it look like", "update the styling", "redesign this", "match the existing style", "what design patterns does this project use", "extract the design system", "add a dark mode", "make it more minimal/bold/clean", or describes a desired visual outcome. Invoke via /cf-design — helps Claude produce intentional, consistent UI.
cf-warm
Catch up after absence — summarize git history for a specific user. Use when a user returns after time away from a project and needs to understand what happened — e.g. "warm up", "catch me up", "what happened while I was away", "what did I work on", "summarize recent changes", "what changed since I left", "warm up the project".
cf-sys-debug
Systematic 4-phase debugging — root cause investigation, hypothesis testing, regression-guarded fix, mandatory bug doc. Auto-invoke when a bug is non-trivial or a previous fix didn't stick — signals: bug recurs ("still broken", "same error again", "came back"), flaky / intermittent / race / timing, "used to work, now broken", regression after update or dependency bump, hard-to-reproduce, works locally but fails in CI (or vice versa), multi-stage pipeline failure, stack trace into a library, user already tried fixes that didn't help, or user asks to "find the root cause", "investigate", "diagnose", "why is this happening", "trace this", "bisect", "deep dive". Also load BEFORE touching code whenever the cause is unclear and a hypothesis must be stated first. Prefer over cf-fix for hard, recurring, or investigation-heavy bugs (cf-fix may delegate here). Do NOT auto-invoke for trivial typos, one-line fixes, or config errors with an obvious cause.
cf-tdd
Use when writing new production code, adding features, implementing changes, or refactoring existing code — e.g. "implement this", "build this feature", "create a function", "add a new endpoint", "write the implementation", "refactor this", "clean up this code", "extract into a module", "simplify this function", "scaffold", "write a test", "add tests", "create a component", "implement the API", "add a route", "write a service", "create the handler". Also auto-invoke when the conversation transitions from planning/discussion to actual code writing — any time production code is about to be written, this skill MUST be loaded first. By default uses direct implementation (no new tests written). TDD is enabled when `--add-tests` is present or config `tdd: true`. This is the gate for all code writing in the project. Do NOT auto-invoke for documentation-only changes, config edits, non-code file updates, or when the user is only asking questions about code without requesting changes.
cf-advise
Decision advisory via structured interview — never writes code or plans. Use when the user wants help DECIDING — e.g. "should I", "is X worth it", "which approach", "help me decide between A and B", "am I overthinking this", "what would you recommend", "pros and cons of". Unlike $cf-plan (builds) or $cf-ask (looks up code), this only advises.
cf-ask
Quick Q&A about the codebase → docs/memory. Use for focused project questions — e.g. "how does X work?", "where is Y defined?", "what's the flow for Z?", "explain this module", "why is this done this way?". Unlike $cf-research, one answer.
cf-checkpoint-from
Load a saved checkpoint as working context, then do the next ask. Triggers: "resume from checkpoint", "load checkpoint", "continue from checkpoint", "cf-checkpoint-from", "restore conversation context". First word is the slug; `--recap` prints a summary. Does NOT create checkpoints (use $cf-checkpoint).
cf-checkpoint
Save a conversation checkpoint (goal, decisions, breaking changes, next steps) for a DIFFERENT conversation. Triggers: "save a checkpoint", "checkpoint this conversation", "capture context", "snapshot the conversation", "cf-checkpoint". Unlike /compact (same chat) or $cf-remember (project facts). Slash-only — does NOT auto-invoke.
cf-commit
Smart conventional commit with diff analysis. Triggers: "commit this", "commit my changes", "save my work", "create a commit", "git commit", "stage and commit".
cf-help
Answer questions about Coding Friend itself — skills, agents, hooks, CLI, config, memory, hosts, parameters. TRIGGER — "what skills are available?", "how does coding friend work?", "list all skills", "how do I use cf-plan?", "what is cf-tdd?", "is the CLI required?", or any question about a cf-* name, flag, hook, or config key. SKIP — general coding questions unrelated to Coding Friend, and requests to run a skill (invoke that skill instead).
cf-learn
Extract educational notes for the human from the conversation (unlike $cf-remember, which stores project memory for AI recall). TRIGGER — substantial new technical knowledge, a debugging breakthrough, an architecture decision explained, or a complex explanation worth keeping; the user says "explain what we learned", "make notes on this", "cf-learn". SKIP — trivial edits, typo fixes, routine operations, or knowledge that belongs in project memory rather than learning notes (use $cf-remember).
cf-optimize
Structured performance work — baseline, analyze, optimize, measure, compare. TRIGGER — "this is slow", "make it faster", "optimize", "performance", "bottleneck", "too many queries", "high latency", "memory leak", "speed up", "timeout", "N+1", or any request to reduce time, memory, or query count with numbers to prove it. SKIP — minor refactors, readability or style changes, and correctness bugs that are not performance-related (use cf-fix).
cf-plan
Brainstorm and write an implementation plan before coding. TRIGGER — the user wants to plan, build, create, or implement something: "let's build", "let's create", "add feature", "implement", "set up", "design a solution", "architect", "scaffold", "plan out", "what's the best way to build"; any multi-step or multi-file work that needs sequencing. SKIP — a single obvious edit, a reported bug (use cf-fix), deciding whether to build at all (use /cf-advise), or resuming an existing plan (use /cf-plan-resume).
cf-remember
Save project knowledge to docs/memory for AI recall (unlike $cf-learn, which writes educational notes for the human). TRIGGER — "remember this", "save this to memory", "document what we did", "capture this decision", "write this down", "note this", "record this convention"; after a non-obvious bug fix → bugs/, an architecture decision → decisions/, a new convention → conventions/, a feature flow or gotcha → features/. SKIP — trivial fixes, simple config changes, or educational exchanges (use $cf-learn).
cf-research
In-depth research with web search and structured output. Triggers: "research this", "look into this library", "investigate how X works", "compare these options", "best practices for", "deep dive into", "study this technology".
cf-review-in
Collect and act on an external AI review. Reads the result file, presents findings, offers to fix. Triggers: "review in", "collect review", "check review results", "cf-review-in", "import review".
cf-review-out
Generate a review prompt for an external AI (Gemini, Codex, ChatGPT, or a human). Triggers: "get a second opinion", "external review", "review out", "send for review", "cf-review-out", "prepare review for gemini".
cf-review
Dispatch a multi-agent code review of the current changes and report Critical / Important / Suggestions / Summary. TRIGGER — "review this", "review my changes", "check the code", "code review", "any issues with this?", "review before merge", "review the diff"; reviewing specific files, commits, or branches; automatically after cf-plan, cf-fix, and cf-optimize complete. SKIP — reviewing a plan document (use $cf-plan-review), quick questions about how code works (use $cf-ask), and formatting-only changes.
cf-scan
Scan the project and populate memory (architecture, conventions, stack, features). Triggers: "scan the project", "scan the codebase", "bootstrap memory", "populate memory", "analyze the project". Token-heavy — always warn before proceeding.
cf-ship
Verify, commit, push, and create PR. Use when the user wants to ship their work — e.g. "ship it", "push and create PR", "let's ship", "deploy this", "send it", "push my changes", "create a PR", "open a pull request", "ready to merge", "let's get this merged". Also triggers when the user is done with a feature branch and wants the full verify → commit → push → PR workflow. Supports --dry-run to preview without pushing.
cf-plan-resume
Resume an existing implementation plan created by /cf-plan, continuing from where execution last stopped. Use when the user wants to continue, resume, pick up, or finish a previously saved plan — e.g. "resume the plan", "continue the plan", "pick up where we left off", "finish the plan", "continue implementing the plan", "resume <slug>". Requires an existing plan file under docs/plans/. Does NOT create new plans — use /cf-plan for that.
cf-fix
Quick bug fix workflow. Use when the user reports a bug, error, or broken behavior — e.g. "fix this", "it's broken", "not working", "there's a bug", "I'm getting an error", "this crashes", "something is wrong", "why does this fail", "debug this", "it throws", "fix the issue", "resolve this error", "help me fix", "can you fix", "this doesn't work", "stopped working", "regression", "unexpected behavior", "failing test", "broken after update". Also triggers on stack traces, error messages, or descriptions of incorrect program behavior.
cf-later-do
Work through deferred side-tasks in docs/later/. Triggers: "do the later tasks", "process docs/later", "work through the backlog", "what did we defer", "resolve deferred items", "cf-later-do". Routes to $cf-fix or $cf-plan; removes the file only after verified-done. Slash-only — NOT auto-invoked. Does NOT capture new items (that is capture-later.sh).
cf-teach
Personal teacher skill — after any task, explains what happened in a conversational, storytelling way (like a sharp friend over coffee). Covers: approach taken, alternatives rejected, how parts connect, tools used, tradeoffs, mistakes made, pitfalls to watch, expert observations, and transferable lessons. Unlike $cf-learn (concise structured reference notes), this creates a narrative deep-dive for the human to truly understand what happened and why.
cf-plan-review
Review a saved $cf-plan folder with a fresh reviewer before implementing; triggers "review the plan", "plan review", "second opinion on the plan", "check the plan before implementing", "cf-plan-review"; does NOT review code (use $cf-review).
cf-verification
Verify before claiming work is complete
cf-session
Continue or resume Google Antigravity conversations with the native session controls. Use when the user asks to resume, continue, or restore an Antigravity session. Antigravity owns its transcript format, so Coding Friend does not copy or rewrite session files.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.