AI Eval

Career planning — log roles, compare offers, track applications, salary benchmark, with planning/job-search/salary variants.

55 skills · 27 commands · 2 agents

Product research and procurement skills with a particular focus on technical specification conformance — does this part actually meet the requirement, and can you show your working. Marketplace-agnostic: spec definition from a vague want or a photograph, annotated search vocabulary, versioned spec-as-code, manufacturer datasheet retrieval, cross-region part-number equivalence, conformance evaluation matrices, bills of materials and RFQ packages. Plus the surrounding process: intake, research, compare, evaluate, recommend, market-check, spec-driven market landscape surveys, live price/delivery scanning through your own VPN egress, preference memory and hardware-rig profiling. Hands off to the marketplace-specific plugins (shopping, israel-shopping, amazon, aliexpress-israel-skills) once a question becomes about a particular shop.

14 skills · 34 commands · 7 agents

Smart home — Home Assistant, Snapcast multi-room audio, Plex media server ops, with HA/audio/media-server variants.

3 skills · 47 commands · 5 agents

Audio production — normalize, VAD, transcribe, diarize, podcast assembly, with engineering/podcast/transcript variants.

17 skills · 34 commands · 1 agent

Image production — editing, format conversion, batch ops, and filesystem organisation by resolution, aspect ratio, orientation, format, EXIF time, camera, plus dedupe and metadata scrubbing.

29 skills · 19 commands

PR and media monitoring — scan coverage, summarize press, draft responses, comms strategy, with monitoring/response/strategy variants.

1 skill · 28 commands · 17 agents

DocSpring's engineering principles, AGENTS.md templates and six workflow skills (ticket kickoff, PR review, second-opinion review, fix CI, browser QA, session wrap-up) for Claude Code, Codex and other agents.

6 skills

Multi-Agent Driven Development for Claude Code (formerly Claude Memory Kit): you talk to one main agent, it orchestrates three full sessions and their subagents through brief, report and acceptance files; memory as plain dated files in your repository (nothing becomes a rule without your yes) lets any session be cleared without losing the work; guards for git, secrets and tests.

10 skills · 4 agents · hooks

Record browser sessions with the Replay Browser through the host agent browser, analyze recordings through Replay MCP tools or Replay QA, and upload pending recordings when the turn ends.

2 skills · app connector

Manual and exploratory testing: scripted test cases, session-based exploratory charters, decision-table and state-transition test design, and bug bashes. Covers SBTM, Whittaker's tours, Bach and Bolton's heuristics, UAT scripts, and PROOF debriefs. A critic agent (test-script-quality-critic) flags vague preconditions and bundled steps in authored scripts.

6 skills · 1 agent

Plan → Confirm → Implement → Verify discipline for Claude Code. Tiered session boot, deterministic hooks (quality gate, protect-changes, branch-protect, secret-scan, conventional-commit, loop-detect, and more), 37 user-invocable skills across audit / workflow / meta categories, 6 review agents (code-reviewer, security-reviewer, qa-reviewer, planner, dead-code-remover, devils-advocate), a CLAUDE.md ruleset, lessons-as-memory, ADR decisions, plus the optional wiki and HTML-artifacts modules of the `cck` CLI.

40 skills · 6 agents · hooks

Continuous agent orchestration where the plugin IS a schema and a set of skills — there is no CLI. `tursodb` already executes SQL, so guild members reach the board by writing their own SQL against a guide, and the guild's rules live IN the database: CHECK constraints are the status vocabularies, VIEWS are the derived rules (the cursor, the review gate, node readiness, the board, the brief — each with ONE definition, so two members cannot get two answers), and TRIGGERS write the `event` record on every mutation. A member can forget to call a command; a member cannot bypass a trigger or a CHECK. A ticket names a required CAPABILITY rather than an agent, and the roster is not in the database at all — who exists and what each can do is the `capabilities:` frontmatter of the agent files, read at dispatch time across every subagent available to you, so writing an agent file is the whole of hiring with nothing to sync. Each requirement runs an execution graph with exactly two gates — the plan is approved before anything is built, and findings, bugs and failures are presented together as one decision after review — and it can work a shift unattended, stopping at the next gate because a gate is the one decision no subagent can make. The library is a knowledge graph: documents carry a kind — business rules, technical pages, DECISIONS, research, runbooks — and typed edges link them to the requirements, plans, tasks and bugs they describe, decide, supersede or contradict, so 'why is it like this' is a SELECT rather than an archaeology session. A trigger snapshots every rewrite, so the documentation has its own history, and two views make the library maintain itself: one reports pages whose subject moved after they were written, the other reports shipped work nobody wrote down. Every requirement documents itself — the last node of the build template is `document`. An independent QA discipline files bugs and maps risk coverage as rows. The guild deletes nothing: there is no board

20 skills · 15 agents