Showing 30 of 23013 results
Light-prompt reflection skill. Single forcing question + structured journal capture. Path-B sibling of capture from megaprompt 08.
Passively watches every session for moments the agent didn't meet expectations, logs them, nudges /reflect at session end, and synthesizes root-cause-attributed improvement reports
from DennisLiuCk/cc-toolkit
Use when verifying that a deployed web feature actually works for real users β post-deployment / production verification. Drives a real browser against your live URL via the Reflex MCP tools (mcp__reflex__*).
Event-driven hooks that react to Claude Code session lifecycle events
Motion-graphics videos as addressable data β generate, tweak, regenerate without losing human edits.
Slovak Register of Contracts (CentrΓ‘lny register zmlΓΊv, crz.gov.sk) - search public-sector contracts by subject, contracting parties, IΔO, value, and contract date
Czech Register of Contracts (smlouvy.gov.cz) - search public-sector contracts by subject, contracting parties, IΔO, value, and conclusion date
Exhaustively explore any web-app area and write tiered regression runbooks (manual + automated), self-improving after every run.
Regression testing scopes β define rerunnable confidence across changed and high-risk areas before automation selection
Regulatory change management skills for impact assessment, obligation extraction, policy diffing, implementation planning, and exam brief preparation.
Financial-regulatory & compliance specialist team β 6 function agents (AML/KYC, regulatory-reporting, risk-and-controls, policy & procedure, examination-prep, Bermuda-insurance) PLUS 6 jurisdiction/regulator specialists: BMA financial-institutions (banking, trust, corporate-services, fund-admin, investment-business, money-service, digital-assets β the primary build-out, with deep AML/ATF + supervision/fees + licensing-classification trees), CIMA (Cayman), Bahamas, Channel Islands (Jersey JFSC + Guernsey GFSC), UK PRA, and US federal+state. 19 primary-source-cited regulator knowledge files, 37 best-practice rules, 10 skills, 11 templates, 1 defensive PreToolUse hook (PII scrub β SSN/IBAN/credit-card/Bermuda TIN/wire instructions). Positioning reflects field experience inside a Tier-1 financial regulator (BMA). Inherits ravenclaude-core protocols.
[market-research/methodology] Use when the user asks to "analyze regulations", "regulatory landscape", "compliance requirements", "legal considerations", "regulatory risk", "industry regulations", "compliance analysis", "regulatory trends", or needs guidance on regulato
Portable AFK development orchestrator: /plan-prd, /ship, /grill across Claude Code and Codex.
Prompt-based hierarchical agent team framework for Claude Code. Define expert personas, build layered teams, and delegate across Claude and external LLMs β no code required.
Cut and bump releases with safe defaults β no push, no tag, no tag push without an explicit flag β and roll new releases out to every downstream consumer repo with CI verification
Release planning, changelogs, versioning, rollout, deployment checks, rollback, and post-release review
Create a rollout, validation, and rollback checklist for a change before shipping it
Opt-in, backward-compatible relevance-scoped rule injection plus a tiered always-on safety core. Off by default: with the flag unset, all rules load exactly as before. When enabled, surfaces a pointer to the task-relevant rule subset while always including the safety core.
Relic SDD: the 12 workflow commands plus ambient skills that make spec-driven development Claude's default working practice
A /reload-claude-md command that re-reads the in-effect CLAUDE.md memory files from disk and re-anchors the session to their current content, so mid-session edits take effect without a restart. Claude Code loads CLAUDE.md only at session start and has no native reload; this fills that gap. Read-only and user-invoked.
REM sleep for Claude sessions β auto-prunes stale memory on session start, crystallizes learnings on session stop, maintains .claude/memory/ with timestamps and 90-day eviction.
Process sandboxed and individual managed markdown files in a remargin vault, and surface what changed since the caller last touched the workspace. Provides /remargin:process-file, /remargin:consolidate, /remargin:process-sandbox-group, /remargin:process-sandbox, and /remargin:activity slash commands plus a natural-language skill layer.
Remediate existing PDFs: auto-tag with PDF/UA semantic structure via the Nutrient DWS Accessibility API, then check the result with the bundled verifier.