NeVibeCode · repository · 161 items
continuous-claude-v3: a set by parcadei
The parcadei/continuous-claude-v3 repository on GitHub: 161 cards with a description and an install command. Inside: 131 skills, 27 subagents and 3 rules. They work in Claude Code, Codex, Cursor — 9 platforms in total.
About the repository
- GitHub
- parcadei/continuous-claude-v3
- Stars
- ★ 3,951
- Installs across cards
- 43,707
- License
- MIT
- Source updated
- 2026-01-26
- In the catalog since
- 2026-10-25
discovery-interview skill discovery-interview runs a detailed product interview that turns a vague idea into a specification. Use it when requirements need to be worked out before implementation.
CX Codex +1
4,200installs
premortem skill Runs structured risk analysis before writing code or merging a PR. Uses pre-mortem thinking to catch critical failure modes and blind spots.
CX Codex +1
914installs
math skill Routes mathematical computations and conceptual questions to SymPy, Z3 constraint solver, or Pint unit conversion scripts.
CX Codex +1
887installs
github-search skill A skill for Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI that queries GitHub code, repositories, issues, and pull requests through MCP. It accepts a search type and a query string with full GitHub Search syntax.
CX Codex +1
746installs
dead-code skill Finds unused functions and dead code with TLDR static analysis. Runs on demand, whenever a codebase needs a cleanup pass.
CX Codex +1
745installs
refactor skill refactor is a Claude Code skill that guides code changes through analysis, planning, implementation, review, and test validation. It activates for refactoring requests that should preserve existing behavior.
CX Codex +1
625installs
recall-reasoning skill recall-reasoning — a Claude Code skill that digs through past sessions for decisions, working approaches, and dead ends. Query it before starting work similar to something already done.
CX Codex +1
605installs
graceful-degradation skill graceful-degradation — a skill that has the agent check optional services up front and explain what broke and how to fix it instead of returning nothing.
CX Codex +1
603installs
explore skill explore is a Claude Code skill that examines a codebase at a chosen depth. Run /explore with quick, deep, or architecture to inspect structure, patterns, or dependencies.
CX Codex +1
581installs
math-help skill math-help is a Claude Code skill that guides the agent in choosing SymPy, Z3, SciPy, Lean 4, or verification scripts for mathematical tasks.
CX Codex +1
548installs
sub-agents skill Configures specialized Claude Code sub-agents with isolated contexts, dedicated models, and restricted toolsets for specific coding workflows.
CX Codex +1
539installs
perplexity-search skill perplexity-search runs Perplexity AI web search, deep research, and chain-of-thought reasoning directly from the agent terminal.
CX Codex +1
536installs
security skill Runs a two-phase security audit workflow. Scans the project for OWASP Top 10 vulnerabilities, SQL injections, hardcoded secrets and dependency issues through the aegis subagent, then verifies fixes through arbiter.
CX Codex +1
534installs
research-agent skill research-agent — a subagent that gathers external documentation, code examples and best practices through MCP tools, then writes a handoff for the next agent.
CX Codex +1
532installs
ast-grep-find skill ast-grep-find runs AST-based code search and refactoring using language syntax trees. Helps locate and replace function calls, imports, and variables without matching text inside strings or comments.
CX Codex +1
524installs
repo-research-analyst skill repo-research-analyst examines repository structure, documentation, and project conventions. Use it before changing an unfamiliar codebase or preparing a contribution.
CX Codex +1
524installs
remember skill Writes learnings, patterns and decisions to PostgreSQL with BGE embeddings. Triggered via /remember during a session.
CX Codex +1
524installs
review skill review runs parallel specialized subagents to evaluate code quality, architecture, and impact, then synthesizes a final merge verdict.
CX Codex +1
523installs
planning-agent skill planning-agent — a subagent that turns conversation context into an implementation plan, researches the codebase and writes a handoff before returning.
CX Codex +1
522installs
repoprompt skill Explores codebases through the RepoPrompt CLI without reading entire files. Useful for fetching code signatures and line slices with lower token use.
CX Codex +1
518installs
create-handoff skill The create-handoff skill writes a YAML handoff document so the next agent session picks up your task without losing context.
CX Codex +1
513installs
continuity-ledger skill The continuity-ledger skill writes a YAML handoff with goals, decisions and next steps so a new session picks up right after /clear.
CX Codex +1
513installs
compound-learnings skill compound-learnings transforms ephemeral session learnings into permanent rules, skills, and hooks. It turns repeated coding patterns into lasting project capabilities.
CX Codex +1
511installs
debug skill debug is a Claude Code skill that investigates issues through logs, database state, and Git history. It starts during manual testing or implementation when something goes wrong.
CX Codex +1
511installs
tldr-code skill tldr-code — a skill that gives the agent tldr CLI commands for file trees, call graphs, data flow and dead code. Cheaper on tokens than reading whole files.
CX Codex +1
509installs
hook-developer skill hook-developer is a Claude Code skill with hook schemas, settings.json registration, and testing guidance for writing custom hooks.
CX Codex +1
507installs
commit skill This skill turns session changes into git commits, shows you the plan first, and keeps Claude's name out of the messages. Handy when an agent has piled up edits.
CX Codex +1
505installs
research-external skill research-external — a skill for Claude Code, Codex, Cursor, Copilot, and Gemini CLI that fetches information from external sources — library docs, web search, and scraped pages.
CX Codex +1
505installs
debug-hooks skill debug-hooks is a Claude Code skill for systematically debugging hooks that fail to fire, run twice, or hide runtime errors.
CX Codex +1
504installs
describe-pr skill describe-pr builds pull request descriptions from the repository template after reviewing changes and checks. Use it before updating a PR body with GitHub CLI.
CX Codex +1
504installs
implement_plan skill implement_plan takes an approved plan from thoughts/shared/plans/, works through its phases one by one and checks each against the plan's success criteria. Handy once the design is settled and code is next.
CX Codex +1
502installs
shapely-compute skill shapely-compute runs computational geometry with Shapely: builds shapes, checks spatial predicates, and measures areas directly from your coding agent.
CX Codex +1
501installs
braintrust-tracing skill braintrust-tracing — a skill for Claude Code, Codex, Cursor and other platforms that sends session, turn and tool-use traces to Braintrust. Works via hooks; sub-agents create separate traces with their own root_span_id.
CX Codex +1
499installs
workflow-router skill workflow-router picks the right specialist agent for your goal — research, planning, building or debugging — and allocates resources. Useful when you don't know where to start.
CX Codex +1
499installs
math-router skill The math-router skill maps a math request to an exact CLI command and returns it as JSON. Useful when the agent needs to integrate, prove or plot something.
CX Codex +1
497installs
recall skill recall — a semantic memory skill for Claude Code and Codex. Pulls relevant learnings from earlier sessions out of PostgreSQL and BGE embeddings.
CX Codex +1
496installs
firecrawl-scrape skill firecrawl-scrape — a skill for Claude Code, Codex, Cursor and other agents that fetches web pages through Firecrawl MCP and returns content as markdown, HTML or plain text. Accepts a direct URL or a search query.
CX Codex +1
495installs
help skill help is a Claude Code skill that interactively maps Continuous-Claude-v3 workflows, agents, hooks, and CLI tools to your current task.
CX Codex +1
495installs
completion-check skill completion-check is a Claude Code skill that checks whether infrastructure is connected to the execution path. It guides the agent through call tracing and an end-to-end run before a task is marked complete.
CX Codex +1
493installs
cli-reference skill cli-reference is a Claude Code skill that documents CLI commands, flags, and automation patterns. It helps configure agents for non-interactive execution and CI/CD.
CX Codex +1
493installs
1–40 of 161