Start with the job, then find an open-source answer

aitunnel-docs packages a local Markdown mirror of AITUNNEL documentation as a Claude skill. Its routing file points questions about models, limits, endpoints, authentication, errors, and integrations to 46 reference pages, while scripts can regenerate the mirror with crawl4ai. Refreshing the mirror requires Python, Playwright Chromium, and network access; the repository is primarily a documentation aid rather than an API client.

Name Forge turns a product description into a shortlist of candidate names. Four strategies generate ideas in parallel, survivors are checked across GitHub, npm, PyPI, crates.io, and the open web, and the remaining names are scored for memorability, typing, pronunciation, distinctiveness, and domain potential. The report ranks ten names and expands on the top three, but it is not a trademark clearance service.

Deep Review is an experimental Claude skill for finding problems that a generic file pass may miss. After a short calibration interview, it decomposes a paper or technical artifact into specialist checks, tests claims against sources and computations where possible, and returns a severity-ranked report. Optional review memory is written only after approval, and the tool is best treated as preparation for expert judgment rather than a replacement.

Writers Room coordinates a multi-agent editorial workflow from brief intake through research, outlining, drafting, quality passes, linking, verification, and publication metadata. A Python checker measures paragraph and sentence lengths, link policy, banned phrases, and heading hierarchy, while an optional design pass derives CSS and renders a self-contained HTML preview. Configuration controls voice, length, sources, and output, so the workflow is better suited to substantial articles than quick edits.

brand-coherence-audit compares a brand or person across up to 15 public web sources, extracting claims about positioning, offers, expertise, and proof. It produces weighted scores, a cross-source comparison matrix, quoted inconsistencies, and a prioritized update plan aimed at clearer AI-search understanding. The skill orchestrates external collection tools, so API access may be needed for social and search sources.

Session Connector keeps multi-day research, experiments, and notebook work coherent across Claude Code sessions. Its save operation snapshots progress and updates each thread, resume surfaces all active threads, and status gives a quick survey without reopening every note. State normally lives under the project’s `.claude/sessions/` directory, with an optional constrained external-drive location. It never deletes old sessions automatically.

shva-marketplace is a small personal plugin collection for Claude Code, separate from the author’s product-specific tools. Its `shva` pack includes briefing, LinkedIn and Medium writing, teaching design, worksheet generation, GenAI use-case discovery, source finding, and persona profiling from text. Install it by adding the local marketplace and then the plugin; the marketplace is intentionally narrow and may grow over time.

Put AI To Work is a curated repository for senior managers and directors who want practical AI support without losing their voice. It organizes installable skills, standalone prompts, printable cheat sheets, and recipe-style workflows; the current featured skill audits drafts for vocabulary, structure, tone, and punctuation patterns associated with machine-written copy, then suggests a cleaner rewrite. Artifacts are refreshed quarterly and can be pinned to release tags.

Waypoint adds a structured planning layer to Claude Code. Work is split into independent milestones and strictly ordered phases; completion checks track acceptance criteria, deferred stubs, and architecture decisions, and a phase cannot start until the previous one is complete. A milestone remains open when required verification is missing or tracked stubs remain in the codebase, making it useful for projects that span multiple sessions.

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.