NeVibeCode · 5,391 items
Skills for Agent setup: memory, context, orchestration
Skills for Agent setup: memory, context, orchestration: what each one does, an install command and example prompts.
email-creative-builder skill Builds one email creative: subject-line variants, preheader, body copy, a single CTA and a plain-text alternate. Useful when the email has to match a landing page.
CX Codex +1
1,000installs
voice-dossier-builder skill Turns your own posts, emails and decks into a versioned voice dossier for a brand and its founder. Handy before you let an AI write in your name.
CX Codex +1
1,000installs
engagement-inbox-manager skill Triage social comments, DMs, and mentions with register detection and commenter classification. The skill drafts human-reviewed replies and logs UGC permissions.
CX Codex +1
1,000installs
social-quality-auditor skill Audits a batch of posts or a channel before publishing: channel truth, claims, disclosures, engagement manipulation and UGC rights. Useful when a queue is paused.
CX Codex +1
1,000installs
social-calendar-builder skill Builds an ongoing social posting calendar with channel slots, queue depth, evergreen rotation and trend gaps. Use it when setting up or rebalancing a publishing rhythm.
CX Codex +1
1,000installs
crisis-response-planner skill Writes your social crisis protocol before you need it, then runs it: a severity ladder, the queue-pause rule, and pre-approved holding statements.
CX Codex +1
1,000installs
social-creative-builder skill Turns a single approved idea into ready-to-paste post packages for X, LinkedIn, Threads and 小红书, plus a carousel slide spec.
CX Codex +1
1,000installs
message-test-designer skill Designs the message test before you spend on scale: hypothesis, panel, protocols, success thresholds and a stop-or-revise rule.
CX Codex +1
1,000installs
narrative-baseline-mapper skill Walks every surface you own — homepage, pricing, docs, deck, bios, email footers — and records what each one claims today, plus the gap against your intended message.
CX Codex +1
1,000installs
proof-point-packager skill Packages approved evidence into reusable proof modules and ties each one to a message-house pillar. It also surfaces claims that lack supporting proof.
CX Codex +1
1,000installs
category-narrative-mapper skill This skill maps the stories a category repeats, breaks down competitor messaging, and compares current copy with archived versions.
CX Codex +1
1,000installs
strategic-narrative-designer skill Turns positioning facts and a belief map into a five-beat change narrative: old world, the shift, winners and losers, the promised land, and the evidence behind it.
CX Codex +1
1,000installs
brand-language-codifier skill This skill drafts brand voice and naming rules for products, features, and tiers. Use it to establish a shared language guide before adapting copy for individual channels.
CX Codex +1
1,000installs
narrative-resonance-monitor skill Measures how a brand narrative lands: echo rate, how AI answer engines describe the brand, and share of voice on a locked panel.
CX Codex +1
1,000installs
setup-codemap-cli skill Configures the Codemap CLI utility to inspect project file trees and module dependencies. Helpful when giving an AI agent clear architectural context across Git branches.
CX Codex +1
1,200installs
load-issues skill The skill pulls every open issue from the current repository with gh and writes each one to its own markdown file. Handy when you want tasks outside GitHub.
CX Codex +1
1,200installs
propose-hypotheses skill Runs the whole First Principles Framework cycle: generates competing hypotheses, verifies logic, validates evidence and produces a decision record.
CX Codex +1
1,200installs
create-command skill Interactive helper for drafting custom slash commands. Configures frontmatter, argument handling, and pre-run bash context.
CX Codex +1
1,200installs
setup-arxiv-mcp skill Sets up an academic paper search MCP server through Docker MCP and records its tools in CLAUDE.md. Use it when an agent needs to search or read research papers.
CX Codex +1
1,200installs
attach-review-to-pr skill This skill shows the agent how to post review comments on specific lines of a pull request using GitHub CLI or an MCP tool. Handy when review happens in the terminal.
CX Codex +1
1,200installs
actualize skill Checks an FPF knowledge base against Git changes and flags evidence or decisions that may need review. Use it before new work or after repository changes.
CX Codex +1
1,200installs
create-hook skill The skill scans your project and suggests hooks for your stack: type checks, formatting, linting, tests. Then it writes the script and tests it.
CX Codex +1
1,200installs
apply-anthropic-skill-best-practices skill A skill that walks you through Anthropic's official skill-authoring rules while you build your own. Useful once a skill file grows past a few screens.
CX Codex +1
1,200installs
create-agent skill Scaffolds autonomous subagents for Claude Code with valid YAML frontmatter, isolated contexts, and triggering examples.
CX Codex +1
1,200installs
do-competitively skill Runs three agents on the same task in parallel, scores their output with judges, then synthesizes the best result. Built for work where quality beats speed.
CX Codex +1
1,200installs
plan-do-check-act skill Walks your agent through four PDCA phases: plan, do, check, act. Useful when you want to improve a process instead of guessing at it.
CX Codex +1
1,200installs
create-skill skill Helps create or update skills with TDD, using subagent scenarios to test an instruction before it is revised.
CX Codex +1
1,200installs
create-ideas skill This skill makes the model return six candidate answers with probabilities: three likely ones and three pulled from the tails of the distribution.
CX Codex +1
1,200installs
cause-and-effect skill Runs structured Ishikawa diagram investigations on development bottlenecks. Pinpoints root causes across technical and team factors.
CX Codex +1
1,200installs
test-prompt skill Runs your prompt scenario with and without the prompt on a subagent, so you can see exactly what the instruction changes.
CX Codex +1
1,200installs
test-skill skill Tests agent skills before deployment using a TDD cycle with pressure scenarios. Reveals when an assistant bypasses rules and invents excuses.
CX Codex +1
1,200installs
tree-of-thoughts skill Runs a hard task through three parallel agents, a pruning vote and a synthesis pass. Useful when the right approach isn't obvious up front.
CX Codex +1
1,200installs
create-rule skill A skill that walks you through writing a rule file in .claude/rules/ so your agent stops repeating the same mistake.
CX Codex +1
1,200installs
launch-sub-agent skill Dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification.
CX Codex +1
1,200installs
do-and-judge skill This skill sends a task to an implementation sub-agent, checks the result with an independent judge, and retries with feedback when needed.
CX Codex +1
1,200installs
review-pr skill Reviews an open GitHub pull request and leaves inline comments on the diff. Handy when the work sits in a PR, not in your local tree.
CX Codex +1
1,200installs
judge skill The skill runs a two-stage review of work from the current conversation: one sub-agent sets the criteria, another scores the result with evidence.
CX Codex +1
1,200installs
add-task skill Turns your request into a task file under .specs/tasks/draft/, with a verb-first title, a type and your original wording. The first step of a spec-driven workflow.
CX Codex +1
1,200installs
do-in-parallel skill Runs isolated tasks across separate files concurrently via sub-agents and validates work with automated judges. Fits batch refactoring and doc generation.
CX Codex +1
1,200installs
analyse-problem skill This skill turns a problem into a one-page A3 document: background, current condition, goal, root cause and an action plan.
CX Codex +1
1,200installs
2,521–2,560 of 5,391
