认证鉴权
认证与授权
change-journal
agentika-labs
Query the change journal for cross-session and cross-workspace change history. Use when you need to understand what other agents changed, what happened in prior sessions, or to investigate changes to specific files. Invoke when the user says "what changed", "show changes", "change history", "what did agent X do", "what was modified", "change journal", "change log", "recent changes", or "who changed [file]".
pr-creator
peopleforrester
Create well-structured pull request descriptions. Use when the user wants to create a PR, needs help with PR descriptions, or is preparing changes for review. Generates clear titles and comprehensive descriptions.
stackone-connect
StackOneHQ
Implement account linking using StackOne Connect Sessions and the Hub React component. Use when user asks to "connect a provider", "embed the integration picker", "add BambooHR to my app", "create a connect session", "set up auth links", or "handle account webhooks". Covers the full flow from session creation to webhook handling. Do NOT use for making API calls after linking (use stackone-platform) or building AI agents (use stackone-agents).
workleap-telemetry-v2
workleap
Guide for Workleap's telemetry solution (@workleap/telemetry) that unifies Honeycomb, LogRocket, and Mixpanel with consistent correlation IDs. Use this skill when: (1) Initializing wl-telemetry in a frontend application (2) Working with correlation values (Telemetry Id, Device Id) and their lifecycle (3) Using Honeycomb for distributed tracing and performance analysis (4) Creating and enriching Honeycomb traces/spans using OpenTelemetry (5) Using LogRocket for session replay and frontend debugging (6) Using Mixpanel for product analytics and event tracking (7) Understanding Honeycomb, LogRocket, and Mixpanel roles in wl-telemetry (8) Correlating data across Honeycomb, LogRocket, and Mixpanel (9) Configuring loggers for wl-telemetry diagnostics (10) Using Noop telemetry clients to disable/mock telemetry (11) Reviewing PRs that add or modify telemetry instrumentation (12) Troubleshooting missing or inconsistent telemetry across tools
open
spm1001
Re-orient to session context on demand. Loads companion skills (bon, todoist-gtd) based on what's present. Use when you missed the startup context, want a fresh look at what's available, or after cd'ing to a different project. Triggers on /open, 'what were we working on', 'where did we leave off'. Pairs with /ground and /close. (user)
close
spm1001
Orchestrates end-of-session capture via 5-phase GODAR framework — prevents work loss between sessions by surfacing learnings, triaging incomplete work into Now/Bon/Handoff, writing cross-session handoff, and staging memory extraction while context is rich. MANDATORY before /exit. Invoke FIRST on 'wrap up', 'lets finish', 'close out', '/close'. Pairs with /open. (user)
zscaler
dvmrry
Answer questions about the Zscaler portfolio — full operational depth (Tier 1, with SDK / TF / OneAPI exposure) on ZIA, ZPA (including AppProtection inline WAF/IPS and Browser Access), ZCC (Client Connector), ZDX (Digital Experience), ZBI (Zero Trust Browser / Cloud Browser Isolation), ZIdentity (unified identity + OneAPI authentication + step-up auth), Cloud & Branch Connector (ZTW/ZTC — VM-based traffic forwarding for cloud workloads and branch offices), and ZWA (Workflow Automation — DLP incident lifecycle); plus extended awareness with reasoning docs (Tier 2a, portal-only / no SDK) on Deception (decoys/honeypots for post-perimeter detection), Risk360 (cyber risk quantification / Monte Carlo / CISO board reporting), the AI Security family (AI Guard runtime guardrails for LLM prompt-injection / jailbreak / sensitive-data / toxicity / refusal detection plus AI Red Teaming / AI Guardrails / four-pillar governance), and ZMS (workload microsegmentation east-west, host-agent + WFP/nftables enforcement); plus paragraph-level awareness (Tier 2b) of ZINS (shadow-IT NSS Collector), EASM, Federal Cloud variants, ITDR, DSPM, Posture Control, and others. Covers URL category coverage, URL filtering rule precedence, wildcard matching semantics, SSL inspection ordering, cloud app control interaction with URL filtering, DLP three-layer model, sandbox / malware / ATP, firewall filtering, ZPA app-segment matching and policy evaluation order, AppProtection profiles / paranoia levels, Browser Access wildcard certificate rules, ZCC forwarding-profile / trusted-network decisions (which decide whether traffic reaches ZIA or ZPA in the first place), ZDX score / probe / diagnostic-session questions about user experience, browser isolation (Isolate action, Smart Browser Isolation, isolation profiles), Cloud Connector provisioning and activation, and Zscaler portfolio breadth ("what is X?", "does Zscaler do Y?"). Use whenever the user mentions Zscaler, ZIA, ZPA, ZCC, ZDX, ZBI, ZWA, ZTW, ZTC, CBC, Zero Trust Browser, Cloud Browser Isolation, Client Connector, AppProtection, Browser Access, Deception, Risk360, AI Guard, AI Guardrails, AI Red Teaming, AI Security, ZMS, microsegmentation, east-west traffic, ZINS, EASM, URL categories, URL filtering, cloud app control, SSL inspection, DLP, sandbox, app segments, forwarding profiles, trusted networks, ZDX score, probes, diagnostic sessions / deeptraces, isolation profiles, prompt injection, jailbreak detection, LLM guardrails, or asks "is $URL covered / blocked / allowed". Also use for "why does this rule win", "what happens when these policies overlap", "why is this user's app slow", "what happens when traffic gets isolated", "what is $product", or "does Zscaler have something for $use-case" questions, even if the user does not explicitly name Zscaler.
stackone-platform
StackOneHQ
Manage StackOne resources including API keys, linked accounts, logs, and webhooks. Use when user asks to "set up StackOne", "list my accounts", "debug API errors", "check integration status", or "configure webhooks". Covers authentication, account management, and troubleshooting. Do NOT use for building AI agents (use stackone-agents) or discovering connector capabilities (use stackone-connectors).
canvas-component-upload
drupal-canvas
Upload validated components to Drupal Canvas and recover from common upload
problem-definition
ddunnock
Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms scattered failure data into precise, measurable problem statements that bound investigation scope without embedding cause or solution. Use when defining problems for root cause analysis, writing D2 sections of 8D reports, analyzing nonconformances, investigating failures, or when user mentions problem definition, problem statement, RCCA, 8D, failure analysis, or corrective action.
MVP Builder
daffy0208
Rapid MVP development and feature prioritization for fast product validation. Use when building minimum viable products, prioritizing features, validating ideas quickly, or when users need to ship products fast while avoiding over-engineering.
Context Preserver
daffy0208
Automatically save and restore development context to minimize cognitive load when resuming work. Use when switching tasks, taking breaks, or returning after interruptions. Captures mental state, file locations, and next steps. Designed for ADHD developers with high context-switching costs.
Focus Session Manager
daffy0208
Automatically manage focus sessions, breaks, and hyperfocus protection. Uses ADHD-optimized Pomodoro technique with flexible timers, health reminders, and gentle interruptions. Protects against hyperfocus burnout while maximizing productive time.
product-analytics
daffy0208
Measure what matters with proper event tracking, funnels, cohorts, and metrics. Use when setting up analytics, tracking features, or understanding behavior.
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.
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.