Shape agent capabilities into your workflow.

Flutter Localization Audit Skill scans Flutter and Dart projects for hardcoded strings, incomplete ARB files, intl setup problems, plural and gender forms, RTL gaps, locale-unaware formatting, interpolation errors, and fallback issues. Its report combines per-locale coverage with file-level evidence, severity, positive findings, and prioritized fixes. A project with pubspec.yaml and ARB files is required, and the skill reports issues without editing translations.

Flutter Store Readiness Skill audits a Flutter project for iOS privacy manifests, Android Data Safety, permission explanations, screenshots, age ratings, metadata limits, signing, target SDK, and release configuration. It returns per-platform readiness states, item-level checklists, blocking issues, and positive findings before submission. The project must contain iOS or Android sources, and some final checks still belong in App Store Connect or Play Console.

wayamzpost turns an Amazon seller's daily topic into researched copy, six to nine rendered cards, and a platform-ready Markdown post in Chinese or English. It supports platform-specific limits for Xiaohongshu, LinkedIn, X, and Instagram, plus source-health checks. Some gated sources are fetched through Chrome, while automatic publishing is disabled and enabling the adapter requires considering platform terms and account risk.

dependabot-triage handles npm, pnpm, yarn, and bun alerts by ranking impact, exposure, and CVSS, mapping import sites, selecting a minimal patched version, and checking the changelog for breaking changes. It updates every package-manager override in play, regenerates lockfiles, and aborts when resolved versions drift across local and CI tooling. The skill pauses for explicit approval before applying a bump or opening a pull request.

thorough-review structures code review into scope, contextual reading, tagged findings, verification, and adversarial self-validation. Final findings need reproducible file-and-line evidence, hypotheses must be promoted or dropped, and proposed fix snippets must be executed before they are posted. It works with GitHub, GitLab, or local branches and is aimed at security, payments, migrations, infrastructure, and other high-stakes changes.

jd-interview-arsenal turns a job description into six libraries of reusable interview cards covering concepts, company context, industry framing, domain application, B2B judgment, and numbers or stories. Each card rehearses five realistic follow-up questions, supplies answer material, opposing language, and source labels, then exports a printable single-file HTML with a rapid-reference section. It complements a broader preparation map and still needs the candidate's real experience.

agentic-windows-bootstrap builds an unattended Windows 11 USB, wipes and reinstalls a target PC, then enrolls it into Tailscale with OpenSSH for remote access. The agent handles preparation, media creation, post-install setup, and recording, while the user must still insert the USB and choose it from the boot menu. Because it erases the target disk, use it only after verifying the target and recovery path.

asuka-persona gives Claude a bilingual Asuka Langley voice, switching between the Soryu and Shikinami versions when the conversation supplies matching story cues. It loads deeper character, lore, and relationship references only when needed and can use an optional knowledge-base MCP for grounded recall. The project is an unofficial fan work, so its roleplay and lore references are not a substitute for licensed canon.

slack-daily-digest reads Slack channel history and writes Feishu documents containing prioritized highlights, TODOs, business movement, risks, statistics, and unabridged channel context, then sends a compact Lark card. It supports two daily slots and a watchdog that checks required sections and retries with backoff. A Slack app, a Feishu app, and companion document skills are required; credentials stay in local mode-0600 files.

product-view keeps Claude in a product-language lens that describes what a customer, player, reader, or developer experiences. Its explain, reframe, and plan modes cover existing flows, bugs, and new functionality, with view on and view off for persistence. It deliberately stays out of algorithmic, performance, infrastructure, and code-style questions where technical language is the more useful level.

palamedes combines multi-agent research prompts, an agent-loadable skill, calibration scenarios, a browser UI, and offline report templates around a strict evidence discipline. Load-bearing claims need retrievable source text and verbatim quotes, while missing evidence is marked instead of filled from intuition; agreement among agents does not count as independent support. Stakes determine the depth of the workflow, and the browser UI uses the user's own API key.

job-hunt-skill turns a job description and an experience bank into a one-page tailored CV, a cover letter, a short outreach message, application answers, a submission tracker, and feedback rules across eight phases. The master CV remains untouched, metrics must be confirmed, and the final Submit action stays with the applicant. It began with UK AI startup roles, so senior, non-technical, or other-market searches need adaptation.

past-paper-topic-analyzer reads a chosen window of exam PDFs end to end, clusters topics inductively, and exports a three-sheet Excel workbook with coverage, every question grouped by topic, and a year-by-topic frequency heatmap. It counts an essay once, records cross-topic material separately, and preserves enough question detail to defend the tally. The workflow depends on accessible public PDFs and an explicit board, level, section, and year scope.

skill-triage turns a task into a routing plan with a restatement, complexity tier, risk flags, ranked skill choices, rejected options, execution order, and a proceed-or-ask verdict. Destructive or irreversible work always gets a confirmation gate, while an empty local match can trigger scrubbed discovery from a small registry allow-list. The tool is advisory: it recommends a route but does not block the caller or run the task itself.

theaccessible converts a PDF through theaccessible.org API into an accessible HTML rendition, a tagged PDF, and a veraPDF PDF/UA-1 conformance report. It returns download links and explains failing rules such as missing tags or alternative text instead of claiming compliance prematurely. The skill requires an API key and outbound HTTPS.

claude-tabletop inspects a project's files to choose a relevant incident or continuity scenario, then creates a facilitator runbook and an interactive HTML version. The runbook supports a timer, staged inject reveals, decision logging, and JSON state export. A companion skill turns that export into an After-Action Report with a timeline, gaps, and severity-tagged actions. It covers nine domains, including security, SRE, privacy, data/ML, and AI safety.

sd-coach turns Claude Code into a system-design interview coach for L3–L4 software roles. Choose a teacher-led coach, timed mock, Socratic tutor, rapid drill, or concept teach mode; sessions cover scoping, capacity, high-level design, APIs, schemas, low-level design, and failure modes. Mock sessions produce rubric-based scorecards, while Teach writes reusable notes to a personal concepts wiki.

OpenOrder helps an AI agent maintain a local investment-research wiki instead of leaving insights in chat history. It reads an index before answering, ingests pasted articles or earnings material into immutable raw files, updates company and industry pages, logs every write, and can lint for contradictions or stale gaps. The same Markdown-based wiki works across Claude Code, Cursor, Codex, and other supported agents.