Skills directory · page 50

Create a namespaced custom package with explicit public/private choice, documentation, a plan, implementation and tests. Use for /palarran:package:create; --plan is offline and writes nothing.

Install an explicitly selected SHA256-pinned custom package into one existing framework project. Use for /palarran:package:install; --plan is offline and writes nothing.

List project-installed packages and optionally the caller's registry releases; route explicit owner delist/delete actions. Use for /palarran:package:list; --plan is offline and writes nothing.

Find visible custom packages in the configured registry with bounded complete results. Use for /palarran:package:search; --plan is offline and writes nothing.

Remove only an installed custom package's unmodified receipt-owned files and discovery links. Use for /palarran:package:uninstall; --plan is offline and writes nothing.

Update an installed custom package using exact versions, receipts and local-edit preservation. Use for /palarran:package:update; --plan is offline and writes nothing.

Research alternatives' audience channels: paid search, TikTok/Meta, native/creator, organic/SEO, referral and partnerships; produce evidence-backed funnels/tests. Use for /palarran:product:acquisition; no ad launches/outreach.

Plan sales to the first small B2B customers: qualification, pain hypotheses, offer and outreach plan. Use for /palarran:product:b2b before development and after polish; research only, no messages sent.

Define B2C audience and free/inexpensive first-customer channels, including native video, creators and Telegram; check prices and plan tests. Use for /palarran:product:b2c; no publishing/ad purchases.

Compare a product with direct competitors and substitutes on customer jobs, pricing, limitations and positioning. Use for /palarran:product:compare; GitLab/Buffer cases and evidence, no redesign/implementation.

Define a product from an idea or README: ICP/JTBD, value proposition, business model, MVP and verifiable startup-case-based success criteria. Use for /palarran:product:define; research/planning only, no implementation.

Research market and demand through startup cases: segments, search trends, alternatives, TAM/SAM/SOM and sourced hypothesis tests. Use for /palarran:product:market; no advertising launches or product implementation.

Research revenue/economics of alternatives: official disclosures, founder reports, provider estimates and separate ranged scenarios. Use for /palarran:product:revenue; never invent unavailable figures.

Recall bounded quick notes, owner context and relevant verified cross-project findings. Use for /palarran:remember.

Load and validate a saved JSON session, optionally resolving its VPS reference. Use for /palarran:remember:session.

Create a LaTeX research report from existing experiments with verifiable results, references, limitations and claim-to-evidence mapping. Use for /palarran:science:preprint; no training/publication.

Audit application code for authentication, object/tenant/property/function authorization, business invariants and dangerous execution paths. Use for /palarran:security:code; readonly review and evidence-backed proposals, no automatic remediation.

Audit current dependency advisories against exact installed/deployed versions, lockfiles, transitive graphs and exposure. Use for /palarran:security:cve; Keenable first when available within permitted scope, primary-source fallback, no guessed CVEs or automatic upgrades.

Audit outbound network requests and application data leaving through responses, exports, webhooks and third parties. Use for /palarran:security:egress; default local read-only review, --plan executes nothing.

Audit infrastructure identities, exposure, privilege and recovery boundaries from scoped evidence. Use for /palarran:security:infrastructure; default local read-only review, --plan executes nothing.

Audit application input and ingress trust boundaries across forms, routes, parsers, uploads, webhooks and proxies. Use for /palarran:security:ingress; review/report only, no automatic fixes or live probes.

Audit log usefulness, noise, sensitive content, readers, integrity and retention across a logging pipeline. Use for /palarran:security:log; default local read-only review, --plan executes nothing.

Install or safely update selected Palarran packages, preserve local edits, configure language preferences and check global memory. Use for /palarran:setup; --plan is offline and writes nothing.

Create responsive visual design from UX concepts and references, choosing among ten established design systems or custom references. Use for /palarran:ui:design; creates visual previews, tokens and components, generates required images and preserves decision explanations for later tasks.

Design responsive application UX from a business description or README with research into 3–4 analogs, diagrams for every screen and states. Use for /palarran:ux:design; preserves concepts and decision rationale for later tasks. Does not define visual style or implement the interface without a separate request.

Review and clean explicitly disposable intermediates while preserving plans, results and active memory. Use for /palarran:vacuum.

Inspect an authorized VPS over SSH without changes or credential exposure. Use for /palarran:vps:inspect; --plan never accesses targets.

Plan and perform authorized VPS operations over SSH, including application-stack deployment from a repository without installing agent skills on the server. Use for /palarran:vps:manage; --plan never connects.

Adaptador (bloqueado) dos folhetos do Pão de Açúcar da praça Grande São Paulo (SP), pelo índice de campanhas e pelos viewers FlipHTML5. Use quando o usuário mencionar "encartes Pão de Açúcar", "encartes Pao de Acucar" ou colar a URL folhetos.paodeacucar.com.

This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use this skill for tasks involving paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources.

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, work product review, or help finding things in the Paperclip web UI.

Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.

Decide whether Paperclip work needs delegation, and connect justified tasks with owners and real dependencies. Use when turning an authorized plan into work.

Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.

Create and develop external Paperclip plugins with the CLI-first workflow. Use when scaffolding a plugin, iterating on a local plugin, installing it into Paperclip, or updating plugin authoring docs.

Run, verify, reseed, and repair Paperclip isolated dev workspace services. Use when asked to start or fix a managed project/worktree service and prove health, login readiness, cloned data, runtime visibility, and correct port ownership.

Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.

Choose, inspect, validate, and report Paperclip Runner or Product E2E evaluations while preserving evidence, provenance, cost, and failure classification.

Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host. Use when asked to deploy, host, or share a persistent page, viewer, prototype, report, or static site without here.now.

Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.

Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions. Trigger on saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory.

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

Use when the user wants to significantly accelerate tasks through parallel work, concurrent agents, batch tool calls, isolated worktrees, or multiple independent verification channels without sacrificing correctness.

Speed up a task by turning it into a dependency graph of parallel lanes with a lane matrix, batched reads and checks, write surfaces isolated by file, worktree, branch, or service, and a final verification table. Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, many independent verification lanes, or bounded homogeneous work that reuses shared preparation while record operations remain sequential, without losing correctness.

Use when deciding whether to sign a partner, at which tier (referral, reseller, OEM, SI, alliance), with what joint GTM and revshare. Runs partner_tier_classifier.py, revshare_modeler.py and joint_gtm_planner.py.

Use when a passive investor shares a private deal (syndication, preferred equity, bridge fund, private credit) to screen as an LP. Stress-tests it, computes fee drag with fee_drag_calculator.py and compares terms with benchmark_comparator.py.

Use for prior-art search, freedom-to-operate, patent landscape, acquisition diligence or litigation prior art. Picks the use case with sub_use_case_router.py, searches Google Patents, Espacenet and USPTO and writes a .docx; not legal advice.