Results for “upstream”

Ensure design docs explicitly capture risks, assumptions, and open questions with owners, deadlines, and mitigation plans.

The English summary is being prepared. Showing the original description.

Detect undefined or inconsistent cache strategies (layers, consistency, invalidation, TTL, failure handling) in design documents.

The English summary is being prepared. Showing the original description.

Ensure design changes stay consistent across ADRs, diagrams, and specs; decisions are traceable; and drift is explicitly managed.

The English summary is being prepared. Showing the original description.

Ensure API design follows RESTful naming and consistent conventions.

The English summary is being prepared. Showing the original description.

Checks whether AI-assisted work defines review criteria, accessible context, explicit review loop, human judgment boundary, and feedback capture before delegating to an agent.

The English summary is being prepared. Showing the original description.

Ensure architecture docs capture availability targets, failover strategy, capacity headroom, and resilience trade-offs for critical services.

The English summary is being prepared. Showing the original description.

Ensure architecture updates document affected stakeholders, notification plan, and deprecation/retirement signals to keep knowledge aligned.

The English summary is being prepared. Showing the original description.

Enforces error handling standards: silent error prohibition, custom error class hierarchy (AppError base with category never-fallback / transient / permanent, cause preservation, ValidationError / UnauthorizedError / UpstreamError etc. — canonical definitions in ERRORS.md), external-boundary normalization (normalizeExternalError), Result pattern (Result.ok/Result.fail), proper try-catch with error type checking, structured error logging with a single Logger contract, fallback prohibition categories (isNeverFallback), and HTTP status code mapping. Use when implementing error handling, reviewing catch blocks, or designing error responses.

The English summary is being prepared. Showing the original description.

Provenance inventory for pinned upstream SEO/GEO Claude skills covering search, generative-engine optimization, schema, content, backlink, and rank categories. Use to inspect recorded paths and hashes or plan one candidate's future gated import; this wrapper does not evaluate or execute those workflows.

The English summary is being prepared. Showing the original description.

Captures completed operational knowledge as a standalone global skill and prepares an authorized upstream feature request with complete compressed code. Use when the user asks to preserve a setup workflow, or when the capture workflow has been explicitly adopted for completion offers.

The English summary is being prepared. Showing the original description.

Coordinate OmniRoute update workflows, including upstream skill discovery, consolidated LocalSetup coverage comparison, freshness validation, and report-first import, update, modification, or removal planning. Use when listing, checking, updating, modifying, importing, or removing OmniRoute-derived LocalSetup skills.

The English summary is being prepared. Showing the original description.

Semantically merge upstream kit changes while preserving project-specific values and recording sync state

The English summary is being prepared. Showing the original description.

Use when working with Caddy — caddy web server management, automatic TLS certificate handling, reverse proxy configuration, site management, and plugin inspection. Covers Caddyfile analysis, admin API usage, access logs, and upstream health monitoring. Read this skill before any Caddy operations — it enforces discovery-first patterns, anti-hallucination rules, and safety constraints.

The English summary is being prepared. Showing the original description.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

The English summary is being prepared. Showing the original description.

Contribute skills back to upstream via branch and PR

The English summary is being prepared. Showing the original description.

Sync local skills repository with upstream changes from obra/superpowers-skills

The English summary is being prepared. Showing the original description.

Integrate Convex static self hosting into existing apps using the latest upstream instructions from get-convex/self-hosting every time. Use when setting up upload APIs, HTTP routes, deployment scripts, migration from external hosting, or troubleshooting static deploy issues across React, Vite, Next.js, and other frontends.

The English summary is being prepared. Showing the original description.

Focused Signals scout for PostHog projects using revenue analytics. Watches the derived revenue product for upstream failures (Stripe sync stalls, capture regressions), config drift (missing subscription property, currency mix surprises, broken Stripe↔person joins, deferred-revenue gaps), and goal-miss escalations. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.

The English summary is being prepared. Showing the original description.

Install or update ToolUniverse in Claude Science — create the conda env, install the tooluniverse pip package, and (re)build the tooluniverse-research skill by fetching the current workflow library from GitHub. Use for first-time setup, upgrading the ToolUniverse version, refreshing the bundled workflows after an upstream release, or reinstalling on a new machine.

The English summary is being prepared. Showing the original description.

Turns untargeted LC-MS/MS features (m/z, RT, MS/MS) into confidence-stratified metabolite annotations using spectral-library matching (matchms), in-silico tools (SIRIUS/CSI:FingerID, MetFrag) and molecular networking, and assigns a defensible MSI/Schymanski confidence level to each. Use when naming detected features, scoring MS/MS against a reference library, running SIRIUS, or deciding what confidence level an evidence set actually supports. For upstream feature extraction see metabolomics/xcms-preprocessing and metabolomics/msdial-preprocessing; for downstream enrichment that must respect these levels see metabolomics/pathway-mapping; for lipid-specific structural annotation see metabolomics/lipidomics.

The English summary is being prepared. Showing the original description.

Refresh drift-prone documentation against current code. Reads docs/architecture/freshness-catalog.yml, diffs against the last sweep's upstream/main anchor, regenerates mechanical entries, processes editorial markers, and opens one PR per sweep with a report file.

The English summary is being prepared. Showing the original description.

Installs Scenic, the probabilistic scenario description language, for the CARLA in use — pip installing it into the same interpreter that holds the CARLA client, optionally cloning the upstream repo for the example scenarios the wheel does not ship, and verifying that the `scenic` CLI, the client and Scenic's version-keyed blueprint table all agree. Use when the user asks to "install Scenic", "set up Scenic", "download Scenic", "pip install scenic", wants to run `.scenic` files, or has a Scenic whose model import or blueprint lookup fails.

The English summary is being prepared. Showing the original description.

Imports a custom RoadRunner map (FBX geometry + XODR OpenDRIVE) into a CARLA source build as a drivable map — reads the map from the directory the user names, runs CARLA's Import.py to cook the level, Traffic Manager graph and (standard maps only) pedestrian navmesh, and verifies it loads on a server. Handles both standard maps and large tiled maps; large maps get no navmesh, matching upstream CARLA. Use when the user asks to "import a map into CARLA", "add a custom/RoadRunner map", "ingest an FBX+XODR map", "make import", bring in a "large/tiled map", or fix missing walkers / a missing pedestrian navmesh.

The English summary is being prepared. Showing the original description.

Parses, queries, converts, and extracts from GTF and GFF3 gene-model annotation files - walking the gene/transcript/exon/CDS hierarchy with gffutils (queryable SQLite DB), converting formats and extracting transcript/CDS/protein FASTA with gffread, slurping to dataframes with gtfparse/pyranges, and sanitizing malformed files with AGAT. Covers the 1-based-inclusive vs 0-based BED coordinate conversion (start-1 only), deriving implicit features (introns/UTRs/TSS), phase-not-frame, the stop-codon-in-or-out-of-CDS convention, and the chr1-vs-1 seqid and gene-ID-version mismatches that silently produce all-zero count matrices and dropped joins. Use when extracting features or sequences from an annotation, converting GTF<->GFF3 or GTF->BED, traversing the gene tree, or diagnosing a coordinate/provenance mismatch upstream of counting or DE.

The English summary is being prepared. Showing the original description.