zoto-agents

Guided workflow for launching and interpreting the cursor-top TUI. Covers process discovery, hierarchy expansion, log tail interpretation, and recommended flags for different scenarios. Use when the user wants to monitor every Cursor agent on their machine in real time, or to capture a snapshot for a report.

Writes .zoto/eval-system/config.yml from field values pre-collected by /z-eval-configure (command-owned askQuestion). Refuses bundled update.preserveUserAuthoredCases:false or update.writeMetaMarker:false (including nested payload mirrors) before any manifest read or config write. Validates against templates/schema/config.schema.json. Diffs the chosen config against the manifest snapshot (discovery_config.static.framework) to produce a cleanup_plan validated against templates/schema/cleanup-plan.schema.json, and stamps _meta.primitive_analysis.invalidate=true on every cached primitive analysis when the static framework changes. The unified LLM eval harness ships one JSON-first co-located eval per target, with no per-repo selector axis — only the static framework matters here. Never calls askQuestion — returns needs_user_input if validation cannot proceed without user clarification.

Scaffolds static pytest and LLM (@cursor/sdk) eval backends into a host repository, generates eval cases with _meta.generated markers for approved skills/commands/agents/hooks, merges eval scripts into package.json, and writes the persistent manifest plus append-only history. Expects the invoking command to pre-collect approved targets — does not call askQuestion.

Invocation reference for all eval-system CLI commands. Use this skill when you need to run eval scripts — never reference script paths directly; always invoke via the package.json aliases documented here.

Executes eval runs via the host repo's package.json scripts (pnpm run eval, eval:full, eval:llm, eval:judge). Forwards --model to the LLM runner via both a CLI flag and the ZOTO_EVAL_MODEL environment variable. After each run, calls eval:update --check and appends the drift status to the run report as a warn-only line. Does not call askQuestion — credential gaps use needs_user_input for the command.

Adversarial judge for eval runs. Identifies weak graders, under-covered assertions, verbosity spikes, and accuracy/confidence regressions. Produces an enriched llm.yml with soft-metric annotations. Does not call askQuestion — handoff to /z-eval-update is expressed as needs_user_input for the command to confirm via askQuestion and resume. Uses the configured judgeModel (default claude-opus-4-8[]).

Diff-aware eval updater. Detects drift between covered targets and generated eval cases for skills and central plugin eval files (commands/agents/hooks), classifies changes as critical or non-critical, and preserves user-authored cases verbatim. Apply-mode regeneration re-invokes the LLM analyser per drifted primitive and dispatches per-framework static stamping plus the single unified LLM regeneration (`regenerateLlm`) (CI defaults to cached analyser payloads unless `--with-analyser`). The `_meta.generated === true` (case) and `// _meta.generated\: true` (file) contracts are enforced at runtime AND compile time. Supports targeted mode, rediscovery mode, `--no-analyser` / CI cache reuse, and CI `--check` (exit 2 on critical drift).

Project-tailored help for the Eval System plugin. Loads plugins/zoto-eval-system/README.md as the source of truth, inspects current project state (.zoto/eval-system/config.yml, manifest.yml, .env*, evals/_runs/, package.json scripts), and composes an answer that is grounded in the chosen README section, tailored to the host repo's actual configuration and artefacts, and cited with `start:end:path` code references back to the README. Pre-collected `help_context` arrives from the /z-eval-help command (command-owned askQuestion). The skill itself never calls askQuestion — missing context is returned as `needs_user_input`.

Consolidate, promote, demote, and archive memories based on strength, usage patterns, and type transition rules. Use when running REM sleep, rebalancing memory strength, detecting conflicts, or cleaning up orphaned trackers.

Guided workflow for scaffolding a new Cursor plugin in this monorepo. Gathers requirements, creates the directory structure, generates all component files (manifest, agents, skills, commands, rules, hooks), adds skill evaluations, registers in the marketplace manifest, and runs validation. Use when creating a new plugin from scratch.

Cross-run analysis across two or more eval runs driven by **`report.yml`**. Inputs are resolved per run directory under `{evalsDir}/_runs/<ts>/`; per-backend summaries are nested under **`report.static`** and **`report.llm`**. Emits a flat dataset (runs × cases × dimensions) plus the /canvas hand-off prompt, instructing the host agent to invoke Cursor's built-in /canvas tool. The skill never renders charts itself. Drill-down opens per-case log files. Does not call askQuestion — when a fragment (e.g. `20260503`) matches multiple hourly folders and the Task lacks a disambiguator, emit schema-valid **`needs_user_input`** whose **`options[].label`** lists every full **`{evalsDir}/_runs/<ts>/`** candidate path (`/z-eval-compare` surfaces this without **`askQuestion`**).

Executes an engineering spec by spawning subagents for each subtask, tracking progress, adversarial verification, and final quality checks. Use when a spec exists under the configured specs directory and is ready for execution.

Build a prioritised memory index from all memory files and reference trackers. Use when rebuilding the memory index, after memory CRUD operations, or when agents need a sorted discovery list.

Guided workflow for creating engineering specs. Gathers requirements, explores the codebase, proposes a spec structure, and generates spec files under the configured specs directory. Use when planning a new feature, refactor, or multi-step initiative before implementation.

Independent assessment of a repository or Spec System engineering specs. Reviews quality, feasibility, completeness, risk, and structure. After producing a spec assessment, offers to apply recommended fixes directly to the spec files. Use to audit a codebase or to assess and improve a spec before running zoto-execute-spec.

Coverage gap analyser for eval suites. Scans the codebase across five dimensions — trigger-phrase coverage, schema validation, regression baselines, context citation verification, and status checklist completeness — and produces a structured adviser_report with per-target, per-dimension findings and deterministic recommendations. Read-only: never modifies files. Does not call askQuestion — uses needs_user_input at two breakpoints (summary drill-down and action recommendations) for the command to drive via askQuestion and resume.

Multi-purpose utility for CRUX compression workflows. Provides token estimation and checksum calculation. Use when estimating tokens for compression, comparing file sizes, or getting checksums for sourceChecksum tracking.