AI Agent Skills

Audit and rewrite a LinkedIn profile to attract the right people: a buzzword scan, scored sections, three headline variants, an About rewrite, achievement-first experience bullets and a checklist for how well the profile surfaces in AI search.

Google's workflows for making BigQuery cheaper and faster: SQL rewrites, partitioning and clustering, storage billing, editions and acceleration structures.

Security-first coding practice: threat model first, a three-tier Always / Ask first / Never boundary, and concrete controls for input, auth, sessions, headers, SSRF, secrets, dependencies, privacy and LLM features.

Review the changes since a commit, branch or tag along two separate axes: Standards (does it follow the repo's documented conventions and a baseline of common code smells) and Spec (does it do what the issue or spec asked), run in parallel and reported side by side.

Give an AI coding agent the right information at the right time: a rules file, the relevant spec and source, trimmed error output and a managed conversation, with packing strategies and rules for handling confusion.

Google's guidance for adding Sign In With Google to a web app: backend-mediated architectures first, ID token verification, CSP/COOP headers and sign-out.

Official Redis guidance for hardening a production instance: authentication and TLS, least-privilege ACL users, network exposure and dangerous commands.

Write and critique cold email, SMS, LinkedIn notes and freelance proposals with an ICP-first, value-first framework: copywriting formulas, ready templates, a five-touch follow-up sequence, benchmarks and a deliverability checklist.

Searches the last days of news on any topic and returns a briefing grouped by event, labeled multi-source or single-source, with outlet, date and link.

Design stable APIs and module interfaces: contract first, one error format, consistent naming, validation at the boundary, additive changes, plus REST resource and pagination patterns and TypeScript interface patterns.

Give an AI coding agent a CONSTRAINTS.md of mechanical checks it cannot talk its way around: a non-negotiable floor, numeric limits, a ratchet for what exists today, and a diff review that catches weakened tests and suppressions.

Turns code review into one line per finding: location, problem and fix, with an optional severity tag.

Makes your coding agent answer first and drop the filler, while keeping code, commands, paths and error messages exactly as they are.

Shrinks memory files such as CLAUDE.md so they cost fewer input tokens, with validation and a backup of the original.

Audit and improve how product content can be found, extracted, and cited in AI answers.

Add a relevant Claude Academy learning resource to answers about using Claude, only when there is a strong match.

Guides you from an idea to a finished Agent Skill: intent capture, a SKILL.md draft, test prompts, optional eval runs and description tuning.

Analyze a specified stock’s daily trend, momentum, volume, and support/resistance using reproducible calculations.

Writes terse Conventional Commits messages that explain why, not what.