CommunityArte y diseñogithub.com

LevNas/ccaudit

Record and preserve audit trails of AI-assisted Claude Code sessions: auto-flush to a remote trail repository on session end, plus /audit-flush for manual inspection.

Compatible conClaude Code~Codex CLI~Cursor
npx skills add LevNas/ccaudit

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentación

audit-flush

Manual counterpart to the Stop hook. Same logic, invoked on demand.

When to use

  • The user asks to inspect staged trail entries before they auto-flush.
  • The user wants to retry entries that moved to $CCAUDIT_PENDING_DIR after an earlier failure (secret hit or push error).
  • Auto-flush is disabled (CCAUDIT_MANUAL=1) and entries must be flushed explicitly.
  • The user needs a written record that " inspected and approved this flush at time X" — running /audit-flush leaves a trace (the commit author and timestamp) that an unattended Stop hook cannot.

Flags

FlagBehavior
(none)Same flow as hooks/auto-flush.sh: scan, secret-check, push, clear staging.
--dry-runList what would be flushed, exit without touching anything.
--forceInclude $CCAUDIT_PENDING_DIR contents in addition to staging; retry everything.

Procedure

Follow skills/audit-flush/procedure.md step by step. Do not invent additional safety checks — the hook and this skill must stay behavior-identical, so divergence creates undefined state.

What this skill does NOT do

  • It does not modify trail entries. Entries are append-only once written to staging.
  • It does not delete from the remote trail repository. If a bad entry was pushed, the correction is a new entry referring to the bad one by hash — never a rewrite.
  • It does not reconfigure the remote. CCAUDIT_TRAIL_REPO is read-only from this skill's perspective.

Skills relacionados

dumkin03/Hexa-Design-System

Design system resources and Claude skills

community

mtschoen/skills-cost-estimator

Claude Code skill: retrospective cost analysis from local session JSONLs (per-session, daily, waste patterns); predictive companion in design

community

assistant-ui/tools

Registers LLM tools and renders custom tool-call UI in assistant-ui (@assistant-ui/react). Use when adding frontend-only tools with makeAssistantTool / useAssistantTool (browser actions like clipboard, navigation, localStorage, async-generator streaming, AbortSignal), rendering backend AI SDK tool() calls with makeAssistantToolUI / useAssistantToolUI (status.type running/complete/incomplete/requires-action, args, result, artifact via ToolCallMessagePartProps), building generative UI from tool results, or implementing human-in-the-loop and approval flows (addResult, resume with context.human(), respondToApproval for server-side needsApproval gates). Covers registering tool components inside AssistantRuntimeProvider and the case-sensitive toolName matching that connects a tool to its UI. Reach for this when tool UI is not rendering, a tool is not being called, or a result is not showing.

community

sciman-top/skills-manager

Windows + PowerShell skills manager for Claude, Codex, Gemini, and Trae. Aggregate, curate, build, and sync AI agent skills from multiple upstream repos.

community

UmbertoDiP/claude-skill-framework

Production-ready framework for creating reusable Claude Code skills. Includes templates, guides, examples and validation tools.

community

zultiAvi/klodTalk

An easier/safer way to work with Claude code. easily harness the power of team of sub-agents specifically designed to do your work.

community