Loading...
Loading...
Found 798 Skills
Unified setup hub: project init, tool setup, 2-agent config, harness-mem, codex CLI, and rule localization. Use when user mentions setup, initialization, new projects, workflow files, CI setup, LSP setup, MCP setup, codex setup, opencode setup, 2-Agent setup, PM coordination, Cursor setup, harness-mem, claude-mem integration, cross-session memory, localize rules, adapt rules. Do NOT load for: implementation work, reviews, build verification, or deployments.
Creates and manages Cloudflare Access service tokens for automated infrastructure verification and non-human access. Use when setting up automation, verification scripts, monitoring systems, or need to test services without Google OAuth. Triggers on "create service token", "setup automation access", "verify without OAuth", "automated monitoring", or "service token for testing". Works with Cloudflare Access Service Auth, .env credential storage, and cf-service-token.sh script for testing and management.
Provides 3-tier validation approach for Home Assistant dashboards including pre-publish validation (entity checks, config structure), post-publish verification (log analysis), and visual validation (browser console, rendering). Use when validating HA dashboards, checking dashboard configs, verifying entity IDs, debugging rendering issues, or before deploying dashboard changes. Triggers on "validate dashboard", "check HA config", "dashboard errors", "entity not found", or "test dashboard". Works with Home Assistant WebSocket/REST APIs, Chrome extension MCP tools, Python dashboard builders, and YAML dashboard configurations.
Receive and verify Chargebee webhooks. Use when setting up Chargebee webhook handlers, debugging Basic Auth verification, or handling subscription billing events.
Use when you need to generate/update test plans, test cases, test suites or test reports during the verification phase of Spec Pack, and require strict access control, traceable artifact storage, and no unauthorized routing.
Use when you need to create defect reports that can be directly pasted into external defect systems (without saving bug files in the Spec Pack) during the verification phase of the Spec Pack, and write the defect references back to `{FEATURE_DIR}/verification/report-*.md`.
Fixes N+1 queries, redundant fetches, over-fetching with keep/discard verification
Universal execution engine consuming .task/*.json directory format. Serial task execution with convergence verification, progress tracking via execution.md + execution-events.md.
Use this skill when installing, adding, or updating packages, checking latest versions, scaffolding projects with dependencies, or generating code that imports third-party packages. Triggers on npm install, pip install, cargo add, gem install, go get, dependency resolution, package management, module installation, crate addition, or any task requiring live version verification across npm, pip, Go modules, Rust/cargo, and Ruby/gem ecosystems. Covers synonyms: dependency, package, module, crate, gem, library.
Explicit anti-rationalization enforcement for maximum-rigor task execution. Loads all anti-rationalization patterns, gate enforcement, and pressure resistance as a composable modifier on any task. Use when executing critical production changes, security-sensitive code, complex multi-file refactors, or any task where shortcuts could cause harm. Use for "with rigor", "carefully", "maximum verification", or "no shortcuts". Do NOT use for trivial lookups, documentation-only edits, or simple typo fixes where full gate enforcement would be disproportionate overhead.
4-phase code review methodology: UNDERSTAND changes, VERIFY claims against code, ASSESS security/performance/architecture risks, DOCUMENT findings with severity classification. Use when reviewing pull requests, auditing code before release, evaluating external contributions, or pre-merge verification. Use for "review PR", "code review", "audit code", "check this PR", or "review my changes". Do NOT use for writing new code or implementing features.
Validate email addresses before campaign sending. Takes a contact CSV, validates each email via a verification provider, removes invalid/do_not_mail/abuse/unknown addresses, and optionally cleans them from sequencer campaigns. Outputs a verified CSV ready for campaign-sending. Fits between email-generation and campaign-sending in the pipeline. Triggers on: "verify emails", "validate emails", "email verification", "clean emails", "check emails before sending", "remove bad emails", "email hygiene".