Afegits recentment
Els últims skills afegits al catàleg. Descobreix les novetats!
apple-ecosystem-automation
magnusthovsland
"Class-level umbrella for operating Apple/macOS personal apps and desktop automation: Notes, Reminders, Messages, Find My, and background computer-use workflows."
hermes-gateway-operations
magnusthovsland
"Operate and verify Hermes messaging gateways after updates/config changes, especially from gateway-hosted sessions where self-restart is guarded."
belai-verifier
Vulnetix
Independently verifies a patcher's or scout's security claim (fixed, false positive, no known fix, needs a human) by re-deriving it from the scanner, lockfiles, resolution output and the shipped artefact, then records one verdict with a VEX justification. Use when a card carries needs-verify, a fix on a branch, a finding that vanished from the report, or a not-affected claim, and a phantom fix or false closure must be ruled out.
belai-scout
Vulnetix
Test-gap, coverage and flaky-test scouting for a kanban card in a delivery crew. Surveys a repository read-only, runs its own detected suites, ranks untested or weakly tested risk (uncovered branches, failing or flaky tests, packages with no tests, mutation survivors), and files at most five small build items with evidence and gates. Use for quality-labelled cards, requests to find missing tests, coverage analysis or test planning.
belai-reviewer
Vulnetix
Review a built branch against the kanban item it was made for, run its build, tests and scanners on the exact head commit, then approve with shown evidence or send it back with precise, ordered notes. Use when judging a diff, pull request or merge request for correctness, scope, test adequacy, security, supply chain, migrations and API compatibility.
belai-patcher
Vulnetix
Remediates one vulnerability finding on its own branch: finds the resolution path, picks the lowest fixed version, applies the narrowest per-ecosystem mechanism (lockfile update, parent bump, override, replacement, code fix), re-scans, and files an honest verdict. Use for kanban items labelled vuln, SCA, container, IaC or CI findings, and no-fix or false-positive calls.
belai-builder
Vulnetix
Implements one kanban build item on its own worktree branch with the smallest change, proves it with a check that failed before, and publishes a draft pull request for review. Use when the claimed item is labelled build, when review notes need addressing, or when a change must match a repository's build, test, lint and commit conventions across languages, monorepos, CI systems and forges.
genpm
GenPM-net
Add complete, production-ready modules to a project with GenPM instead of writing them from scratch — authentication (GitHub/Google OAuth, sessions, roles), Stripe subscriptions and checkout, transactional email, AI chat, file storage, background jobs, search, forms, newsletter, comments, SEO, and whole app sections (online store, blog, CMS, landing page, dropshipping). Use when the user asks to add, set up or scaffold any of these, or asks what GenPM can install.
web-audit
PaulKinlan
"Audit a URL for modern web quality and (optionally) fix it. This is a FULLY AGENTIC audit. YOU
beads
PaulKinlan
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or choose between local planning and persistent project tracking.
spec
griffinwork40
"Takes a loose idea and transforms it into a structured, actionable spec ready for implementation. Use when the user passes an idea, feature request, or problem description that needs scoping before building."
simplify
griffinwork40
"Discovers incidental complexity, duplication, and dead code in a codebase and produces a ranked, behavior-preserving reduction plan — optionally applying safe changes. Dispatches four parallel read-only discovery lenses (clone detection, dead code, complexity hotspots, wrong abstraction), synthesizes into a prioritized reduction plan, and gates apply mode behind /refactor and a hard test check."
ship
griffinwork40
"Release pipeline for already-done local work. Dispatches /ground-state pre-flight, runs the project test suite, drafts a commit message, pushes, and opens a PR with a structured verification summary. Use when local changes are ready to hand off to review — e.g. 'ship this', 'push and open a PR', 'release this work'. Add --verify to trigger an adversarial verifier wave on the diff before a human reads the PR."
shadow-verify
griffinwork40
"Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap analyses) — or whenever a sub-agent asserts a claim with high-confidence language, since confidence is a trigger, not a verdict. Use when sub-agent output will drive decisions, file changes, commits, or external side-effects."
research
griffinwork40
"Dispatches two sub-agents in parallel to gather external and local context for the current task."
refactor
griffinwork40
"Orchestrates safe, large-scale structural changes across a codebase — symbol renames, API migrations, pattern standardizations, layer restructurings. Enumerates all affected sites, groups them into dependency layers via the DAG executor, applies changes in parallel per layer with worktree isolation, and verifies behavioral preservation at each layer boundary before proceeding. Exits immediately on first regression, surfacing the exact site, diff, and behavioral delta before any commit."
polish
griffinwork40
"Iteratively refines any artifact (prose, spec, prompt, API design, SKILL.md, code snippet) by running a decoupled evaluator → generator loop until explicit criteria are met or an iteration cap is reached. Locks criteria in Wave 1, isolates the evaluator from generation history to prevent sycophancy, and emits the best version with any remaining gaps flagged at cap."
parallelize
griffinwork40
"When finished creating the plan in plan mode, run /parallelize so Claude dispatches one planning agent to transform the current approach into a plan to orchestrate waves of parallel sub-agents."
supabase
darrellpoe06
"Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); debugging and troubleshooting errors or unexpected behavior on Supabase projects (HTTP errors, Postgres errors, RLS surprises, permission denied, schema cache issues, timeouts, Edge Function crashes, Realtime drops, Storage failures) and reading or querying logs (Logs Explorer, ClickHouse)."
review
griffinwork40
"Dispatches parallel dimension agents across a diff, PR (URL or number), commit SHA, branch, staged changes, or patch file — covering security, correctness, api-compat, test-coverage, and perf-observability — synthesizes findings by severity, and emits a merge recommendation. Use when changes are ready for review before merge. Read-only: this skill analyzes and reports only — it never edits files, commits, pushes, comments on a PR, or modifies the PR description."
belai-vuln-scout
Vulnetix
Specialist brief for the Belai vulnerability scout. Triage and prioritise findings from Vulnetix SCA, SAST, secrets, IaC and container scans in any customer repository: ground each finding in manifests, scope, reachability and exploitation evidence (KEV, EPSS), group by package and fix, then hand off at most five vuln cards with an exact fix. Use when a request asks for a vulnerability scan, advisory triage, CVE prioritisation or a fix plan.
orient
griffinwork40
At end-of-session, dispatches a read-only sub-agent to survey recent work and drafts a vaguely-specific priming prompt the next session can paste to orient itself and plan its next sprint. Produces orientation, not prescription — candidate directions are framed as questions, not decisions.
ground-state
griffinwork40
"Before starting any non-trivial implementation, run a pre-flight reconnaissance pass to triangulate git state, project infrastructure, and prior-session memory. Auto-assembles a verified grounding preamble — a session-scoped artifact the orchestrator pastes verbatim into every subsequent sub-agent brief — eliminating stale-worktree reads and silent wrong-path errors before the first edit."
ground-claim
griffinwork40
"Grounds capability claims with file-read evidence. Default mode answers meta-capability questions ('what does X enable') with path:line citations. Pass mode: runtime-wiring with a claims list to trace actual runtime execution paths — call sites, DI registration, middleware — and get CONFIRMED/UNVERIFIED/REFUTED verdicts per claim. Blocks sign-off on any non-CONFIRMED claim."