← All creators

AntreasAntoniou

User

A Git-backed, agent-readable workspace for durable knowledge and long-horizon work.

17 indexed · 0 Featured · 3 stars · avg score 72
Prolific

Categories

Indexed Skills (17)

AI & Automation Listed

archivum

Operate a Git-backed Archivum as durable agent memory for projects, research, decisions, meetings, tasks, sources, and outputs. Use when the user asks to capture, find, connect, update, audit, or resume work in an Archivum, or to initialize an Archivum workspace. Do not use merely because a repository contains Markdown.

3 Updated 5 days ago
AntreasAntoniou
AI & Automation Listed

cross-agent-sync

Reconcile recent Claude Code and Codex sessions for one project, create a local evidence packet, and maintain a small curated progress ledger both harnesses can read. Use for cross-agent handoffs, resuming work, surfacing conflicts, and recording verified decisions, evidence, blockers, next actions, and artifacts.

0 Updated 6 days ago
AntreasAntoniou
DevOps & Infrastructure Listed

gcp-keyless

Operate Google Cloud without recurring browser OAuth or service-account key files. Use when an agent needs GCP access, local gcloud credentials expire, a project needs GitHub OIDC Workload Identity Federation, or cloud workloads should use attached managed service accounts.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

agent-orchestra

Design and compose multi-agent graphs for correctness, coverage, or creativity. Use when a task benefits from isolated proposals, explicit arbitration, adversarial verification, committees, recursive review, cross-modal checks, or saturation loops. Applies across agent runtimes; the included JavaScript workflow is one adapter.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

token-efficient-orchestra

Assign model capability tiers deliberately across an Agent Orchestra graph. Use when redundant workers can be economical but arbiters, adversaries, integrators, and irreversible actions need stronger judgment. Provider-neutral; map the tier names to models available in the current host.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

mailbutler

Narrative-aware inbox triage that reads real mail through an approved mailbox adapter, surfaces only what deserves the owner's attention, recommends reply or read actions, and maintains an evidence-backed local narrative. Use when asked to triage an inbox, identify what needs attention today, catch up across accounts, prepare a reply draft, or review what was handled quietly. Triage is read-only; drafts and sends require separate explicit per-message approval.

0 Updated 6 days ago
AntreasAntoniou
Code & Development Listed

argus

Preserve durable context from conversations and completed work by routing commitments, evidence, decisions, preferences, and project state to their canonical Git-backed records. Use when the user asks to archive, remember, checkpoint, capture context, update an Archivum-style workspace, or close the loop; also use at natural milestones when workspace instructions require durable-state capture.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

chronicle

Preserve operational history and intent across agent sessions. Use when resuming work, recording a decision, preparing a destructive or bulk operation, verifying a deployment, correcting a claim, reconstructing a captured file version, or handing off unfinished work.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

bitwarden-lease

Install, operate, diagnose, and safely consume an owner-only macOS Bitwarden CLI lease that uses one native hidden-answer unlock interaction for a 24-hour process-continuity window. Use when repeated `bw unlock` prompts or agent handoffs disrupt work, when local agents need Bitwarden-backed credentials without persisting `BW_SESSION`, when checking whether the lease is usable, or when repairing the `io.github.antreasantoniou.bitwarden-lease` LaunchAgent. Bitwarden only; never substitute another credential store implicitly.

0 Updated 6 days ago
AntreasAntoniou
Code & Development Listed

doppel

Build a consent-first, provenance-aware digital twin of a person's own writing voice from local subject-authored material, then use that writing-voice Doppel to draft or revise text for the subject's review. Use when someone wants a digital twin of their own cadence, reasoning movement, and registers across essays, technical writing, outreach, or social posts without uploading a private corpus. Not a personality twin, believed-human simulation, third-party clone, or autonomous publisher.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

agent-collaboration-control

Establish, actively monitor, and operate project-agnostic collaboration control for multi-agent programmes, research campaigns, live experiments, long-running automation, consequential artifact production, incident recovery, evidence promotion, and cross-agent handoffs. Use when work needs ongoing agent support, a recurring independent watch, proactive anomaly or ambiguity reporting, explicit human authority, one writer per mutable surface, risk-scaled Agent Orchestra topology, transition journals, liveness proof, adversarial review, provenance, succession rules, or calibrated claim states across any project.

0 Updated 6 days ago
AntreasAntoniou
Testing & QA Listed

visual-qa

Review a rendered interface with an isolated committee of orthogonal visual experts. Use for UI audits, responsive and theme checks, edge-state coverage, screenshot-based accessibility review, adversarial finding validation, and optional fix-and-recapture loops.

0 Updated 6 days ago
AntreasAntoniou
Data & Documents Listed

grade-a-pipeline

Map a codebase, decompose requested work into a dependency graph, and run a test-sandwiched multi-agent software pipeline with isolated worktrees, per-wave regression checks, adversarial review, and an explicit quality rubric. Use for substantial builds, fixes, or refactors that benefit from parallel implementation and conservative integration.

0 Updated 6 days ago
AntreasAntoniou
AI & Automation Listed

plus-ultra

Run a Byzantine 2+1 plan before consequential work and a fresh, plan-blind reality check afterward. Use when the user asks for Plus Ultra, maximum rigor, independent proposals, enforced verification, or help responding to a Plus Ultra hook gate. Claude Code can enforce the loop through the included hook adapter; on Codex and other hosts it is a convention unless separately wired and verified.

0 Updated 6 days ago
AntreasAntoniou
Testing & QA Listed

heimdall

Author and run evidence-backed browser and API test plans with honest blocked and non-run semantics. Use when an agent needs to exercise a live web app or API through Playwright/CDP, an isolated Docker browser, or a human-controlled logged-in browser lane.

0 Updated yesterday
AntreasAntoniou
Web & Frontend Listed

local-uis

Discover locally running HTTP interfaces, identify their listening ports and processes, and build a browsable launcher dashboard. Use when the user asks what web apps, dashboards, notebooks, or development servers are running locally or wants a single page from which to open them.

0 Updated 6 days ago
AntreasAntoniou
Data & Documents Listed

beautiful-pdf

Produce polished, print-ready PDFs from Markdown or HTML with Pandoc, WeasyPrint, reusable CSS, and a mandatory rendered-page review loop. Use for reports, proposals, briefs, CVs, invoices, letters, dossiers, and other documents where layout quality matters.

0 Updated 6 days ago
AntreasAntoniou

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.