Connect your repo to evals.tessary.ai and work with your evals from the coding agent — wire trace ingestion over OTLP, tag your call sites, assess graders, query failing traces, read the cases and root-cause reports the platform opens, and author per-call-site SOP-conformance files (derive from the code, reconcile on…
Sovereignty and session core: the prime/state-check/checkpoint skills, the standalone sovereignty guard hooks, and the session checkpoint system - a context-usage sensor, a threshold offer, a pre-compaction brief that states what the summary must keep verbatim, a redacted post-compact save, and a resume injector, all…
Ops and thinking: draft an implementation plan (create-plan), reason through a hard decision (deep-think), and run a structural editorial pass (editorial-review). Reserved (data/daemon/key-bound): dashboard, radar, queue, sync, next, recall, council.
revenantworks-foundation — ten standalone wrights for building, auditing, and maintaining skills, prompts, messages, agent specs, standing Claude configuration, research docs, eval suites, brand identity, token budgets, and multi-agent fan-out dispatch.
revenantworks-gamedev — game-development skills on the -smith motif. First member: pixelsmith, art direction for pixel art that must read at several zoom scales at once.
Zhan Isaakian's personal marketplace of custom AI-agent skills — a growing collection, hand-built and distilled from battle-tested production pipelines + adversarial design.
Zhan Isaakian's growing collection of custom AI-agent skills — each hand-built, most distilled from battle-tested production pipelines and/or honed through adversarial design panels (autopilot is additionally eval-tested). Installing this plugin makes every skill available; see the repo README for the current list and.
The everyday dev loop as three stack-neutral commands: fix debugs a bug or batch-applies a review report by severity, commit runs pre-flight checks and drafts a conventional message behind a sensitive-file gate, ship chains review, fix, and commit with a gate between each phase.
Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…
Professional writing humans actually read: clear, frictionless messages (WhatsApp, email, Slack) that move work forward. A concise, logical core plus a growing library of situation playbooks.
Iterative code review toolkit. Bundles two skills: code-review (diff-based PR review or holistic codebase audit with gap detection and tracked fix loop) and address-pr-review (validate GitHub PR comments, fix, reply, and resolve threads).
Deep requirements gathering skill that interviews users through thoughtful, in-depth questions before implementation. Extracts technical, UX, architectural, and edge case requirements.