认证鉴权
认证与授权
product-antifraud
vasilyu1983
Use when building log-based fraud detection for fintech applications, analyzing registration or authentication logs for behavioral patterns, bot detection, credential stuffing, velocity abuse, GDPR PII exposure in logs, or designing rule-based antifraud systems with tunable thresholds.
auramaxx
Aura-Industry
Securely store, retrieve, and share sensitive data with your human. Use when the user asks for credentials, API keys, credit cards, passwords, or any kind of secret that should not be exposed.
pr-creation
TechDufus
"MUST be used when creating pull requests. Handles context gathering, title generation (conventional commit format), body formatting, and PR creation via GitHub CLI. Creates PRs as drafts by default. Triggers on: 'create PR', 'open PR', 'ready for review', 'push for PR', 'send for review'."
worktree
TechDufus
"Git worktree automation for isolated feature development. Triggers on: '/worktree create', '/worktree list', '/worktree remove'. Creates isolated working directories with automatic setup."
map-reduce
ElliotJLT
Orchestration pattern for large-scale processing where work is distributed, processed independently, then combined. Map phase splits and processes, Reduce phase aggregates results. Use for codebase-wide analysis, bulk transformations, or any task where "do X to everything, then summarize."
learn-from-this
ElliotJLT
When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be written.
Audit Trail
reggiechan74
This skill should be used when the user asks to "show audit trail", "why did we make this decision", "what happened after this", "trace this decision", "show decision history", "search audit log", or needs to understand the decision history and rationale behind code changes verified through coherence check.
skill-gate
ElliotJLT
Before starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill, state YES/NO with reasoning. Only proceed to implementation after skills have been consciously evaluated and activated. Prevents the ~50% "coin flip" activation rate that occurs when skills are passively available but not deliberately considered.
drip
ElliotJLT
Track and surface the estimated water cost of Claude interactions. Every query has a physical footprint - data centers need cooling, electricity needs generation. This skill adds environmental accountability by estimating water consumption per session and surfacing it at meaningful moments. Not to induce guilt, but to create awareness of the physical cost of intelligence.
zero-in
ElliotJLT
Before searching a codebase, forces you to zero in on the target: what exactly are you looking for, what would it look like, where would it live, what else might it be called. Activates on "find", "where is", "search for", or when exploration begins. Prevents grep-and-pray.
rubber-duck
ElliotJLT
When a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions. First, force structured problem articulation through targeted questions: What did you expect? What happened instead? What have you tried? Only after the problem is clearly defined, propose solutions.
pair-mode
ElliotJLT
When activated, Claude becomes a pair programming partner rather than a code-generation tool. Explains reasoning, teaches patterns, asks questions that build understanding, and adjusts depth based on the person's goals. Balances getting work done with building lasting knowledge. Activate with "let's pair on this" or by setting a learning focus at session start.
sanity-check
ElliotJLT
Before building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens. Prevents assumption cascades where one wrong guess leads to a completely wrong solution.
obsidian-session-sync
ElliotJLT
End-of-session ritual that syncs Claude Code session artifacts to an Obsidian vault. Chains breadcrumbs, retrospective, note creation, and daily driver into a single flow. Creates session notes, updates daily note, and leaves breadcrumbs. Activates on "sync to obsidian", "save session", "end session", or when user wraps up significant work in a vault-connected project.
skill-forge
ElliotJLT
When Claude discovers a non-obvious solution, unusual pattern, or hard-won insight during a session, automatically forge it into a new skill. Don't just note the learning - create the actual skill file so future sessions benefit immediately. This is the flywheel: work → discovery → skill → smarter future sessions → repeat.
breadcrumbs
ElliotJLT
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.
debug-to-fix
ElliotJLT
When debugging frustration appears ("why isn't this working?", "it should work", "I don't understand"), orchestrate the full debug cycle: clarify → investigate → fix → verify. Prevents the common failure of jumping to fixes before understanding the problem. An elixir that chains rubber-duck and prove-it with investigation.
retrospective
ElliotJLT
After completing a significant task or experiment, documents what worked, what failed, and key learnings. Activates when a multi-step task finishes or when user says "done", "finished", "that worked", or asks for a summary. Failed attempts get documented first - they're read more than successes.
auth
agentproto
Authenticate an agentproto agent or MCP connector to a service via
review
rube-de
Deep-validate a single GitHub issue against the codebase: cross-reference file paths, detect already-implemented features, check for related PRs, verify dependencies, and deliver a structured verdict with recommended action. Triggers: review issue, validate issue, check issue status, is this issue still needed, issue review.
laravel-tdd
SeuPut0705
Laravel testing strategies with PHPUnit, Pest, model factories, HTTP tests, Sanctum authentication testing, mocking, and coverage. Use when writing Laravel tests with PHPUnit or Pest, or driving a Laravel feature test-first.
ap-tunnels
agentproto
Expose a local port publicly via agentproto tunnels — tunnel_create on cloudflare-quick/cloudflare-named/ngrok, tunnel_list to avoid duplicates, remote_enable to publish the MCP gateway bearer-gated. Trigger when asked to share a dev server, tunnel localhost, get a public URL, or expose the agent gateway remotely.
extend-agentproto
agentproto
"Extend the agentproto daemon with new capabilities — bundle agents and workflows as APPs, build multi-stage session pipelines, import external MCP servers, install adapters, add auth profiles and presets, or author agent packs. Triggers: build an app, workflow pipeline, import MCP, install adapter, agent pack, extend daemon."
ap-lifecycle
agentproto
Kill, interrupt, restart, archive, pin, and garbage-collect agentproto sessions safely — including cleaning up a spawn tree's children. Triggers — "kill this session", "stop the agent", "archive old sessions", "restart a crashed session", "clean up sessions", "garbage collect", "pin this session so it doesn't get reaped".