285 skills
Write structured run logs for agent work that the next run can actually use: timestamp conventions, a greppable JSONL event schema, decision trails, failure…
Run a repeatable daily and weekly inbox triage operating system on the user's email account: batch windows, a reply/delegate/archive/unsubscribe…
Write effective image-generation prompts: subject blocking, composition and camera terms, reusable style tokens, negative-prompt patterns, and a disciplined…
Keep a personal decision journal: write down each decision with its context and a predicted outcome plus a confidence number BEFORE the result is known,…
Keeps a calendar clean and trustworthy: event naming conventions, default durations, buffer rules, dead-event pruning, and a weekly defrag pass. Triggers…
Repair recorded speech (dialogue, voiceover, podcast): measure noise floor and loudness first, reduce steady background noise, tame sibilance, gate pauses,…
Write code documentation developers actually read: pick the right doc type (docstring, comment, ADR, README), document WHY over WHAT, and lead with working…
Adversarially test your own agent's prompts and instructions with a probe battery (direct override, indirect injection, multi-turn manipulation, role…
Analyze onchain activity programmatically: profile addresses, decode ERC-20 Transfer events from logs, measure holder concentration, and flag suspicious…
Test AI prompts and model behavior like code: build a small case suite with scorers, run prompt variants against it, and require the new version to beat or…
Organize a project's whole documentation set: information architecture, README vs docs/ split, navigation depth, versioning strategy, and anti-rot…
Keep a real CHANGELOG.md in Keep-a-Changelog format: what earns an entry, Unreleased discipline, release hygiene, and the changelog as a contract for…
Write architecture decision records (ADRs): when a decision deserves one, the format (Nygard vs MADR), the immutable lifecycle, and a CLI to create numbered…
Design or repair an engineering on-call rotation that pages only on real user impact and doesn't burn people out: alert hygiene from the Google SRE…
Design a testing strategy for a codebase: unit/integration/E2E balance, coverage gates that actually mean something, and flaky-test triage with quarantine…
Design HTTP APIs that age well: resource modeling, versioning and deprecation policy, error conventions (RFC 9457 problem details), pagination, idempotency,…
Diagnose and fix slow SQL queries: read EXPLAIN / EXPLAIN ANALYZE output, choose and verify indexes, and fix common performance anti-patterns (N+1, SELECT…
Design REST APIs: resource naming conventions, which HTTP status code to use when, offset vs cursor pagination, URL versioning, and error-envelope…
Design server-side caching with Redis: cache-aside, write-through, write-behind patterns, TTL selection with jitter, thundering-herd/stampede protection…
Design async task queues: when to queue vs do work inline, producers/consumers, dead-letter queues, retry with exponential backoff + jitter, idempotent…