Skills en tendència
Els skills que estan guanyant popularitat a la comunitat.
Fix Issue Pipeline
matiaszanolli
"Fetch a GitHub issue, investigate, plan, implement, test, and commit the fix"
Flow Tracer
matiaszanolli
"Trace a data flow through the engine — from ECS to GPU or from file to entity"
legacy-lookup
matiaszanolli
"Look up a Gamebryo class, function, or pattern in the legacy 2.3 source"
Tech-Debt Audit
matiaszanolli
"Audit accumulated technical debt — stale markers, dead code, duplication, magic numbers, stub impls, doc rot, oversized files"
Audit Suite Orchestrator
matiaszanolli
"Run a preset suite of audits in parallel — or derive one from a code area / diff via the ownership map"
Physics / PHYSAL Audit
matiaszanolli
"Deep audit of PHYSAL — the Havok→Rapier physics layer: collider classification, fixed-step determinism + explosion recovery, 4-phase ECS sync, ragdoll articulation, character/NPC kinematic controller, WATAL buoyancy sink"
Save / Load Subsystem Audit (M45 + M45.1)
matiaszanolli
"Deep audit of the M45 save/load subsystem — full-ECS-snapshot capture, type-erased registry, format-version discipline, atomic disk write + ring, save-side refusal/validation gates, and the M45.1 live load-apply (cell reload + FormId-keyed deltas + player-pose restore)"
Oblivion Compatibility Audit
matiaszanolli
"Per-game audit of Oblivion (TES4) compatibility — NIF v20.0.0.4 + the v10.x NetImmerse family, BSA v103, live ESM path"
Runtime Telemetry Audit
matiaszanolli
"Runtime telemetry regression audit — drives a headless engine on per-game cells, diffs against checked-in baselines, and reports the state of the smoke / golden-frame gate matrix"
Audit → GitHub Issues Publisher
matiaszanolli
"Convert an audit report's findings into GitHub issues with completeness checks"
Safety Audit
matiaszanolli
"Safety audit — unsafe blocks, memory leaks, undefined behavior, Vulkan spec violations"
Starfield Compatibility Audit
matiaszanolli
"Per-game audit of Starfield compatibility — BA2 v2/v3 + LZ4 block, CDB materials, BSGeometry .mesh resolution, walkable Cydonia interior"
NIFAL Audit — Canonical Translation Layer
matiaszanolli
"Deep audit of NIFAL — the NIF Abstraction Layer (canonical translation tier): Imported* → translate() → Canonical, single-boundary / no-fabrication / no-render-time-fallback"
Skyrim Compatibility Audit (SE + LE)
matiaszanolli
"Per-game audit of Skyrim (SE + LE) compatibility — BSTriShape packed geometry, BSLightingShaderProperty shader-type dispatch, NPC equip/FaceGen, multi-master load order"
control-ui
openclaw
"Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways."
slack-e2e
openclaw
Test Slack with Convex-leased user OAuth or QA bots; check credentials, exercise owned messages, prove Gateway behavior, and distinguish API evidence from real Slack client interactions.
hermes-agent-operator
hermeum
Scaffold a complete, commented HermesAgent custom resource YAML manifest. Reads the HermesAgent CRD schema from the live cluster (or falls back to the repo CRD file) so the output always matches the deployed spec version.
fixing-flaky-tests
PostHog
Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when hogli ci:insights or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a flaky job, when asked to check Trunk Flaky Tests for a test, PR, or master, or when asked to deflake, stabilize, or fix a flaky Jest, pytest, or Playwright test. Core discipline: reproduce locally before changing anything, fix the root cause (never mask it with sleeps, retries, or bigger timeouts), and prove the fix with an N-run validation loop sized to the observed failure rate. Stabilizing is not the only valid outcome — the skill also gates whether the test should exist, so deleting a test that catches nothing real, or re-leveling one that flakes because of the level it runs at, are first-class endings.
agent-orchestration
Jamie-BitFlight
Scientific delegation framework for orchestrators coordinating sub-agents. Provides WHERE-WHAT-WHY context patterns while preserving agent autonomy. Use when delegating tasks, structuring sub-agent prompts, planning multi-agent workflows, or coordinating specialist agents.
lsp
atopile
"How the atopile Language Server works (pygls), how it builds per-document graphs for completion/hover/defs, and the invariants for keeping it fast and crash-proof."
youlianvr
Work with Gmail — send and read emails on behalf of the user using the local SMTP/IMAP script. This skill is a legacy/local fallback; the canonical primary route for Google Workspace operations is the configured google-workspace MCP when its exact operation is verified. Can: send emails with attachments, read the inbox with Gmail-query search (from:, subject:, etc.), check mail. Use this skill when the user asks to: - Send an email / write to someone / write to email - Check mail / see what arrived / is there a reply - Write to someone on my behalf / reply to an email - Attach a file to an email / send with attachment - Get an archive password / request access via email - Any email-related task (send, read, check, monitor inbox) ⚠️ REQUIRES GMAIL_ADDRESS + GMAIL_APP_PASSWORD in .env. Without them, every email command will fail at auth. NOT for: Telegram messaging, SMS, or other non-email communication channels.
contract-and-proposal-writer
youlianvr
"Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs. Structured Markdown output with docx conversion instructions. Covers US (Delaware), EU (GDPR), UK, and DACH (German law) jurisdictions. Not a substitute for legal counsel — use as strong starting points. Use when drafting a freelance contract, preparing a client proposal, writing an SOW for a new engagement, or producing an NDA before sharing sensitive material."
deep-research
youlianvr
"Run a disciplined, multi-source research investigation for a high-stakes question or decision — fan-out web search across many channels, parallel batched searches, source triangulation (each claim backed by ≥3 independent sources), an adversarial review pass, and every source saved to its own file with verbatim quotes for reuse. Use when a low-quality answer is expensive: strategy work, comparing N products/methods/markets, validating a hypothesis with external data, or mapping how a field works. NOT for quick fact-checks (answer directly), structured 12-dimension competitor scoring (use competitive-teardown), or fast topic overviews where the decision risk is low (use the research router instead)."
diagnosing-bugs
youlianvr
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.