Skill Claude CodeCodex
Run npm run format and stage any formatting changes before proceeding.
not rated 4 yesterday A 0 tokens
original MIT
4Stars on the repository
53Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Force trigger: If the task description contains --skill or --agent flag → strip the flag from the description, pre-select the type (skill or agent) for the Skill Type Decision later, and skip detection + confirmation — go directly to the challenge below.
not rated 4
changed 1mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
After the standard review completes, check if any changed files require documentation updates.
not rated 4 yesterday A 0 tokens
original MIT
Skill Claude CodeCodex
This is a version bump + ship + release operation. Run these steps BEFORE the standard cf-ship workflow.
not rated 4
changed 12d ago A 0 tokens
original MIT
cf-advise
05Skill Claude Code
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…
not rated 4
changed 1mo ago A 94 tokens
original MIT
cf-ask
06Skill Claude Code
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.
not rated 4
changed 1mo ago A 68 tokens
original MIT
Skill Claude Code
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).
not rated 4
changed 1mo ago A 73 tokens
original MIT
Skill Claude Code
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…
not rated 4
changed 1mo ago B 77 tokens
original MIT
cf-commit
09Skill Claude Code
Smart conventional commit with diff analysis. Triggers: "commit this", "commit my changes", "save my work", "create a commit", "git commit", "stage and commit".
not rated 4
changed 1mo ago A 42 tokens
original MIT
cf-design
10Skill Claude Code
UI design workflow — scan patterns, design new UI, or modify UI consistently. Use to redesign a component/page, change colors/typography/style, or extract the design system. Triggers: "make it look like", "update the styling", "redesign this", "match the existing style", "add a dark mode", "make it more minimal".
not rated 4
changed 1mo ago A 76 tokens
original MIT
cf-fix
11Skill Claude Code
Quick bug-fix workflow — reproduce, find the root cause, fix via cf-implementer, verify, auto-review. TRIGGER — the user reports a bug or broken behavior: "fix this", "it's broken", "not working", "there's a bug", "this crashes", "debug this", "it throws", "failing test", "regression", "unexpected behavior"; a pasted…
not rated 4
changed 20d ago A 133 tokens
original MIT
cf-help
12Skill Claude Code
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…
not rated 4
changed 3d ago A 108 tokens
original MIT
cf-later-do
13Skill Claude Code
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…
not rated 4
changed 1mo ago A 96 tokens
original MIT
cf-learn
14Skill Claude Code
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"…
not rated 4
changed 1mo ago A 104 tokens
original MIT
cf-optimize
15Skill Claude Code
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…
not rated 4
changed 1mo ago A 112 tokens
original MIT
Skill Claude Code
Resume an existing /cf-plan from where execution last stopped. Triggers: "resume the plan", "continue the plan", "pick up where we left off", "finish the plan", "resume ". Requires a plan under docs/plans/. Does NOT create new plans (use /cf-plan).
not rated 4
changed 19d ago A 67 tokens
original MIT
cf-plan
17Skill Claude Code
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…
not rated 4
changed 5d ago A 132 tokens
original MIT
cf-remember
18Skill Claude Code
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…
not rated 4
changed 1mo ago A 119 tokens
original MIT
cf-research
19Skill Claude Code
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".
not rated 4
changed 1mo ago B 54 tokens
original MIT
cf-review-in
20Skill Claude Code
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".
not rated 4
changed 1mo ago A 50 tokens
original MIT
Skill Claude Code
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".
not rated 4
changed 1mo ago A 60 tokens
original MIT
cf-review
22Skill Claude Code
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…
not rated 4
changed 19d ago A 129 tokens
original MIT
cf-scan
23Skill Claude Code
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.
not rated 4
changed 1mo ago A 55 tokens
original MIT
cf-session
24Skill Claude CodeCodex
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.
not rated 4 yesterday A 54 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: