Arasz
- 132 skills
- 0 followers
- last month last updated
- ▌ Cron Watchdog Authoring · araszUse when scheduling a Hermes cron job or writing a watchdog script: recurring schedules need 'every 30m' (bare '30m' is ONE-SHOT — check repeat), no_agent+script shape, silent-unless-action stdout discipline, version-gated rollout watchdogs (marker files, surgical port-kill), idempotent ticks, and verifying CLI verb paths before the rollout branch can run.
- ▌ Evidence First Research · arasz bundleUse when a question needs investigating and the answer will be acted on — "research X", "look into whether Y", "find out how Z works", "is this worth doing", "compare these options", a benchmark someone will quote, or a claim that has to survive being challenged. Produces a dated record where every finding carries how it is known — measured, read, inferred, or unverified — plus a self-contained HTML view. Not for locating code (that is explore-codebase), tracing one symptom (debug-issue), or judging a diff (review-changes); reach for this when the output is a set of findings someone else will rely on.
- ▌ Worktree Agent Isolation · arasz bundleUse when running multiple agents in parallel, or when the user says 'worktrees only', 'agent isolation', 'parallel workstreams', or 'don't touch main': give each agent its own git worktree branched from origin/main (fetch first), integrate via GitHub PRs, keep the main checkout read-only, and avoid shared obj/ races and file-modification conflicts.
- ▌ Hermes Plugin Development · arasz bundleUse when writing or debugging Hermes Agent Python plugins — including the memory-provider specialized plugin type: directory-plugin packaging (plugin.yaml + __init__.py with register(ctx) — flat .py files are INVISIBLE), VALID_HOOKS list, per-hook payload keys (no cwd; tool_name vs function_name), plugins.enabled opt-in, pre_llm_call context injection, stash/pop for post_tool_call, HERMES_PLUGINS_DEBUG=1, and the MemoryProvider ABC with its threading & lifecycle contract.
- ▌ Code Review Evidence · arasz bundleUse when reviewing code that wraps external libs/extensions/SDKs/CLIs, or QA-reviewing a test harness: verify wrapped-library semantics from the upstream source (not comments/spec), query the real store read-only for data claims, and hunt tautological tests that assert values the code constructed itself. Catches spec-vs-coverage gaps, fake honesty, hygiene.
- ▌ Sqlite Schema Review · araszUse when reviewing SQLite schema/migration changes: DDL, on-open migrations, unique indexes, insert-path dedup, ON CONFLICT DO NOTHING scope, last_insert_rowid staleness, trigger fire-time failures, UNIQUE-index NULL semantics. Core rule: verify every semantics claim against a scratch DB — never the plan, PR, or docs.
- ▌ Artifact Verification · arasz bundleUse when verifying changed artifacts that lack a canonical test gate — specs, docs, manifests, generated files, published packages: use the workflow-defined checker first (spec_holes.py), review manual fresh-install protocols against the false-pass checklist, and verify 'installed build contains merged PR X' by tree comparison, never squash-ancestry.
- ▌ Research Record Audit · arasz bundleUse when auditing a research record's factual accuracy, citation truth, or grade correctness: adversarially re-derive every load-bearing claim from cited sources, verify quotes verbatim at cited lines, re-run MEASURED claims, audit grade honesty (INFERRED hedged, UNVERIFIED plain), check negative claims for prune/retention explanations, and report ACCURATE/CORRECTED/OVERCLAIMED.
- ▌ MCP Tool Surface Testing · arasz bundleUse when testing every tool an MCP server exports: black-box expectations-first audit (expectations → call → compare), live contract vs docs-drift findings, destructive-tool safety controls, dependency-ordered execution, and a results doc committed to the repo. Triggers: 'test all tools', 'does every MCP tool work', server surface changed.
- ▌ Pre Push Gate Debugging · araszUse when a pre-push quality gate blocks git push or a lane fails: read the gate's own logs first (reproduce one lane), run single lanes for fast iteration, test the working tree you intend to push, handle E2E/infra cross-run state contamination, worktree node_modules gotchas, and build a manual repro harness when lane output hides the real error.
- ▌ Spec Driven Refactoring · arasz bundleUse when the user says 'refactor', 'migrate', or 'rename across the codebase', or a change touches 5+ files across schemas, scripts, tests, and docs: write a spec, run two review gates (pre-implementation consistency + post-implementation quality), then implement against it. Covers schema migrations, concept renames, structural reorganizations.
- ▌ Scripts Tooling Refactor · arasz bundleUse when refactoring a repo's scripts/ directory: convert non-python scripts to the repo's tooling language, move logic to src/ with tests in tests/ (TDD first), prune dead scripts on usage evidence (git ls-files inventory, LIVE/HISTORICAL classification, three-way sync contracts), and preserve call sites with thin wrappers.
- ▌ Documentation Drift Audit · arasz bundleUse when auditing docs for drift vs code ('audit and fix documentation drift'): inventory claims with path:line, verify each against real files (scaffolders, manifests, hooks), classify verifiably-false vs design-position vs ambiguous vs historical, fix only the false, and report A/B/C. Also for post-merge doc-gap audits and user-facing doc compaction rewrites.
- ▌ Multi Lane Report Assembly · arasz bundleUse when assembling outputs from 2+ parallel research/review lanes into one evidence-graded record: lift finding blocks verbatim from the authoritative full summaries (never the truncated delegation transcripts), enforce the lane contract (### F# — claim [GRADE], Evidence line), truncate at embedded '## Still open' headers, renumber, and gate the result.
- ▌ Sqlite Bank Space Diagnosis · araszUse when a SQLite bank file or WAL is bloated: diagnose space read-only first (snapshot backup, sqlite3_analyzer, wal_checkpoint(TRUNCATE), VACUUM INTO to quantify reclaim), explain WAL growth mechanics (checkpointed-but-untruncated frames under pooling), the vec0 chunk count(*) trap, and VACUUM/checkpoint/ANALYZE ordering.
- ▌ Complete Project Scope Code Review · arasz bundleUse when the whole project — not a diff — is the review target and the result must survive being acted on: "review the entire codebase", "full quality review", "MoE review", "what is wrong with this project", "audit everything before the next release", or a review whose findings will become a plan someone implements. Runs ground-truth baseline, parallel expert lanes, integration, an adversarial pass that tries to falsify the findings, severity calibration against production reality, a reviewed plan, waved implementation in isolated worktrees, and a join review on every merge. Not for judging one diff or PR (that is review-changes plus code-review-checklist), one design document's gates (design-gate-audit), or one question (evidence-first-research).
- ▌ Review Gate Diff Verification · araszUse when a review gate judges a branch diff: verify the diff base FIRST — merge-base vs moved origin/main ref (phantom D/M files), grep anchors after the status tab, exclude bin/obj from symbol greps, and diff the committed plan against the accepted amended version before judging implementation.
- ▌ AI Raccoon Manual Checklist · arasz bundleUse when hand-verifying a live AiRaccoon build — a pre-flight or release checklist, a manual smoke test after installing the global tool, a "does this actually work end to end" pass before shipping, or any question `dotnet test` cannot answer because it needs a real install, a real server and a real bank. Derives the version and tool surface from the product instead of pinning them, records the command and the output behind every answer, and writes the filled checklist to docs/work/checklist/.
- ▌ Update Documentation · arasz bundleUse whenever documentation must change to match something that already changed — after a code change, ADR, schema change or PR lands, and when the user says "update the docs", "document this", "add a how-to for X", "the README is wrong", "this doc is stale", or a reviewer reports docs drift. Also use before creating any new document, to decide where it belongs. Triggers include a doc that contradicts the code, a fact nobody can source, and a new page with no obvious home. Not for creating the docs tree (use scaffold-documentation) and not for reorganising it wholesale (use migrate-documentation).
- ▌ Migrate Documentation · araszUse when an existing documentation tree must be reorganised wholesale — "migrate the docs", "reorganise docs/", hundreds of files with no structure, overlapping documents that contradict each other, a docs directory nobody can navigate, or documentation whose accuracy is unknown and must be established before anyone relies on it. Also use to resume a migration already in progress. Not for creating a tree that does not exist (use scaffold-documentation) and not for a single documentation change (use update-documentation).
- ▌ Scaffold Documentation · arasz bundleUse when a repository has no documentation tree yet, or the canonical docs layout is missing, incomplete or was hand-created — "set up docs", "scaffold documentation", "create the docs structure", a fresh repo with only a README, a docs directory missing its directory READMEs, or a structure check that reports absent directories. Not for adding or editing a document (use update-documentation), and not for reorganising docs that already exist (use migrate-documentation).
- ▌ Dotnet MCP Server · arasz bundleUse when adding MCP (Model Context Protocol) tools or servers to a .NET project: tool/prompt registration with [McpServerTool]/[McpServerPrompt], stdio or Streamable-HTTP host wiring (dual-mode, port traps), DI + typed HttpClient for REST-backed tools, unit tests with mock HTTP handlers, tool-inventory tests that assert the REGISTERED surface, and SDK 2.x specifics (McpException error signaling, request filters, tool-name derivation).
- ▌ Dotnet Bdd Testing · arasz bundleUse when adding Gherkin .feature files / a BDD runner to a .NET project: Reqnroll is the only live option (SpecFlow is EOL — never recommend it), xunit.v3 + CPM integration, tags/@ignore/Skip and Rule: blocks, or un-ignoring dormant scenarios. Includes the build-time code-behind recipe, feature-file overlap policy, and verified package facts.
- ▌ Dotnet Domain Modeling · arasz bundleUse when modeling immutable C#/.NET domain layers: sealed records with required/init props, CommunityToolkit.Diagnostics guards (and when to hand-roll them), state-transition methods, policy objects, extension-point interfaces (DIM), FluentValidation nested validators, ArchUnitNET purity enforcement — with TDD for pure domain layers. Triggers: DDD aggregates/value objects, domain-purity rules, validator design.
- ▌ Dotnet Tool Publishing · arasz bundleUse when packaging or publishing a .NET CLI tool (PackAsTool) or library to NuGet: the MSB3030 build-before-pack trap (and its Web-SDK inversion), multi-RID matrix shells + the shell-race fix, gitignored bundled assets, Trusted Publishing/OIDC with human approval gates, the 409-published-nothing diagnosis, ToolCommandName/PATH shim rules, and full fresh-install verification for MCP tools with bundled models.
- ▌ Dotnet System Commandline · arasz bundleUse when adding CLI argument parsing to a .NET app or dotnet tool: System.CommandLine 2.0.x GA idioms (parse-first, HelpAction/VersionOptionAction detection, Option.Validators, FromAmong), parser-landscape verdicts (Cocona archived — don't adopt), and the stdio-MCP trap where help/version must render to stderr. Includes Cocona-maintenance guidance for existing tools.
- ▌ Dotnet Flaky Test Diagnosis · arasz bundleUse when a .NET test fails in the full suite but passes alone (or flakes intermittently): classify via the ladder — intra-test race (lock-guard fake collections), inter-test contention (xunit v3 DisableParallelization collections), or environmental flakes (child PATH/env, cold-worktree asset provisioning) — before blaming the branch. Includes the clean-main baseline check and gate discipline.
- ▌ Dotnet Sqlcipher Encryption · arasz bundleUse when working with SQLCipher-encrypted SQLite in .NET (e_sqlite3mc / SQLitePCLRaw bundle): raw 256-bit keys via Password='x'<hex>'', deriving keys from ed25519 SSH keys, PRAGMA rekey constraints (WAL unsupported), pluggable key-source providers (env/keychain/vault) with the pre-open sidecar pattern, and Dapper-over-SQLite3MC mapping traps.
- ▌ Dotnet Hosted Service Review · araszUse when reviewing a PR that adds or modifies a .NET BackgroundService/IHostedService — background extraction loops, watchers, sync, sweep, or any poll loop. Checklist: ExecuteAsync try/catch coverage (StopHost kills the process), cancellation filtering, PeriodicTimer semantics, store-level idempotency vs TOCTOU, settings-channel parsing, LoggerMessage invariants. Produces numbered findings + severity + file:line.
- ▌ Dotnet Logger Message Design · arasz bundleUse when designing or testing [LoggerMessage] log lines in .NET: nested static partial Log classes, explicit EventIds with per-category ranges, no call-site interpolation, collection parameters (pre-join at the call site), per-item detail logs vs counts, and FakeLogger-based log assertions (generic vs non-generic compile contract, LatestRecord/AllRecords, RED-first EventId tests).
- ▌ Dotnet Hosted Service Testing · arasz bundleUse when writing or reviewing .NET BackgroundService tests with FakeTimeProvider/TimeProvider: lost-first-Advance semantics, inline-vs-threadpool timer callbacks, poll-loop test honesty (invocation counters, not side-effect counts), tick derivation from timeouts, DI registration smoke tests, vacuous-gate detection. Verified on .NET 10; includes an empirical probe script.
- ▌ Observability Contract Review · arasz bundleUse when reviewing claims that 'all calls are instrumented': span+metrics helper diffs, tool-layer try/catch instrumentation, N/N tool-surface parity tests. Checks path coverage, not call-site presence — filtered-catch escape holes, exactly-once recording, Activity status/tag ordering, instrumentation-test honesty, CI Speed-trait blind spots, metrics-unchanged verification.