Shape agent capabilities into your workflow.

Crafting Portfolio Essays starts with finished writing samples rather than guessing at a personal voice. It asks for essays, transcripts, or informal notes, then produces a `tone-and-soul.md` voice guide and an essay-specific specification through interview questions and one of six narrative archetypes. The skill does not scan files, query Notion, or invent quotations, and it is aimed at personal portfolio essays rather than technical documentation.

D3OXY/skills is a small pack of independently installable capabilities for coding agents. The included skills cover frontend design with an optional cinematic glass aesthetic, pull request preparation, and extraction of a domain glossary with ambiguity flags. The Skills CLI can list the pack, install one named skill, or install everything, so teams can keep their tool surface focused.

Devloop turns Claude Code into an unattended worker for a repository’s issue queue. For each task it branches, implements in small steps, builds and tests, opens a pull request, requests a fresh code review, merges, checks the live deployment, and logs the result before moving on. ScheduleWakeup controls pacing, while explicit stop conditions pause the loop for conflicts, product decisions, credentials, or guardrail violations. Because it can push and merge, permissions deserve careful setup.

Neighbourhood Due Diligence Report creates a use-case-specific research checklist for Canadian neighbourhoods, with British Columbia as the primary focus. It adjusts priorities for families, long-term rental investors, short-term rental investors, and commercial users, then covers market data, zoning, transit, schools, safety, demographics, amenities, environmental risks, and investment signals. Each item points to a direct data source, but users outside BC must substitute equivalent local agencies.

site-security-assessment tests websites only after an ownership gate: a matching session email domain unlocks passive reconnaissance, while a token file placed under the target domain unlocks deeper levels. The four levels cover passive checks, limited active probes, authenticated DAST, and webhook threat modeling, with per-test approval, evidence-based findings, and false-positive checks. It refuses third-party targets, denial-of-service or load tests, brute force, active automated scanners, and production-data access, and does not bypass harness denials.

Session Handoff packages a Claude session into a structured file and copies a ready-to-paste opening message for the next chat. It detects a development context and creates a compact, plan-linked pointer, or switches to a fuller research handoff with findings, decisions, rejected alternatives, and open questions. Clipboard support uses pbcopy on macOS, with xclip or xsel as Linux alternatives.

Publish Skill turns the current chat's problem, steps, requirements, and anti-patterns into a reusable package: a local SKILL.md, a public GitHub repository with a bilingual README, and a GitHub Pages landing page. It can also generate a cover and add a card to a personal site; raster output is used in Codex with SVG fallback when image generation is unavailable. It requires authenticated gh, git, and bash; a site-repository path is only needed for the optional card.

kaizen-consulting-skill helps consultants plan organizational or tool changes as stages instead of a single Big Bang rollout. From a project brief, it sets transition criteria around roughly 70% acceptance, segments employees into four response groups, and proposes communication, risks, anti-patterns, and a next step with an owner and deadline. Its trigger phrases are primarily German, so English activation may be unreliable.

Start Goal converts a vague request into a measurable goal brief before autonomous work begins. It restates assumptions, classifies the task, gathers the needed context and constraints, defines deliverables and stop conditions, and writes a concrete “Done when” checklist. Creative or product tasks pass through brainstorming first, and long-running work is handed to /goal only after acceptance criteria are specific.

Scroll-Scrub Hero guides Claude Code, Codex, or Gemini from two generated images to a roughly seven-second video and a scroll-controlled hero. The result lets users reveal an assembly or transformation as they scroll, with staged tooltips and mobile autoplay or reduced-motion fallbacks. It supports Next.js 16+ or vanilla HTML and requires image and video service accounts.

Lingshu makes a primary agent the control plane for multi-model work. It defines scope and acceptance criteria before delegating to models, CLIs, scripts, or connectors, then reviews their increments and performs final acceptance. Phase reports, plus treating existing tests as protected contracts, help prevent drift, unauthorized actions, and weakening tests just to make a run pass.

seo-for-ai helps websites improve visibility in both traditional search and AI-agent answers. Its multi-agent audit checks server-rendered HTML, structured data, crawler rules, and FAQ extractability, then returns prioritized fixes from a URL, codebase, or template. It is aimed at sites that want agents such as ChatGPT and Claude to read and cite their content.

distill-ui reverse-engineers a codebase into a design system that people and coding agents can reuse, then builds an interactive showcase to prove the extraction matches the product. It produces design docs, canonical tokens, a component registry, and agent instructions, with optional Tailwind or React output, and can flag common AI-design patterns. It works from source code rather than guessing from screenshots.

Competitive Intel to Conversion Site turns real search results, competitor pages, and buyer reviews into a conversion-focused site strategy. It captures positioning, pricing, trust signals, and customer language, then ties each proposed section to a buyer job, objection, and proof source. The handoff includes an HTML report, site structure, wireframe, and copy pack; WebSearch/WebFetch or Firecrawl can automate collection, but manual use needs no API key.

roundtable-personas is a persona library for claude-roundtable. Each subdirectory is an independently installable perspective skill that the roundtable can discover automatically. The repository currently provides a Feynman perspective focused on scientific reasoning and logical verification, and documents the shared SKILL.md shape for adding more personas.

st-pricebook documents ServiceTitan Pricebook v2 schemas, endpoints, fields that silently disappear on writes, bulk Excel or CSV imports, configurable equipment, estimate templates, and static versus dynamic pricing. Its update pattern combines dry runs, HMAC confirmation, and read-after-write hash checks, with an incident log for recurring mistakes. The skill is tenant-agnostic, so users must replace the supplied tenant and sync placeholders before use.

Article Analyzer deconstructs an article instead of declaring it good or bad. It classifies sentences, checks factual claims against primary sources, surfaces hidden premises and skipped logical steps, and tags rhetorical framing. Its final audit-style opinion is limited to factual claims, with no-opinion boundaries for political, religious, illegal, and certain entertainment content. It can report that a source was not found without treating that absence as proof of falsehood.

Focusgroup dynamically tests conversational systems by combining reusable personas, feature scenarios, and a system under test. It runs real multi-turn conversations, then evaluates them with state checks, safety invariants, performance metrics, persona debriefs, or an LLM judge as a last resort. Reports cluster themes, segment failures by persona axes, and compare regressions. The current scope excludes browser interfaces, batch jobs, and pure classifiers.