stx-linalg
Linear algebra utilities — distance metrics, geometric median, cosine similarity, NaN-aware norm, vector projection, and coordinate reconstruction. Use when computing distances between arrays, finding robust centroids, or working with vector geometry.
workspace
Multi-repo workspace management: clone repos, create execution runs, track papers/datasets/artifacts, manage snapshots, and review audit logs. Use when the user wants to organize multi-repo work, run experiments in sandboxes, or track research resources.
monitoring-feature-observability
Add or adjust monitoring for a Hypeman feature using repository standards for logs, traces, and metrics. Use when a user asks for instrumentation, observability reviews, telemetry consistency changes, metric design, or production-signal improvements.
experiment-log-summarizer
summarize machine learning experiment logs in chinese when the input includes training logs, eval results, hyperparameter changes, user notes, or multiple runs and the user needs a grounded experiment summary, error analysis, best configuration recap, or a weekly update ready abstract.
stx-dataset
Scientific dataset discovery and access for neuroscience (OpenNeuro, PhysioNet, DANDI) and general domains.
vendor-submodules
to interact with the specs of Wasm and WASI (wasp-p3), or the implementations of wasm-tools and wasmtime
zot-vault-review
Periodic review skill for zot vaults. Use when the user asks for weekly review, vault maintenance, linting, retrospective, meta-learning analysis, or to turn accumulated notes into clearer understanding and output drills. Include QMD refresh and search checks, and use the smoke test when local workflow wiring needs verification. Not for first-time ingest of new sources or large cross-operation wiki rewrites.
ce-standards-gap-analyzer
Analyze standards compliance by interpreting the standards's intent, verifying that implementation and RTD satisfy every decision, and producing a dated gap report with only unresolved items.
pump-token-lifecycle
Full token lifecycle from creation through bonding curve trading, graduation detection, AMM migration, fee collection, and volume tracking on Solana using PumpSdk and OnlinePumpSdk.
medical-imaging-review
Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray imaging. Triggers on requests for "review paper", "survey", "literature review", "综述", or mentions of writing academic reviews on deep learning for medical imaging.
lvms-analyzer
Analyzes LVMS must-gather data to diagnose storage issues
task-observer
Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where Claude is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers during post-task feedback discussions and when the user explicitly mentions skill observations, improvements, the observation log, skill taxonomy, or asks Claude to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: this skill should be invoked at the start of every task-oriented session — if you are about to use tools to produce deliverables, invoke this skill first.
critical-thinking-logical-reasoning
Critical thinking and logical reasoning analysis skills for when you are explicitly asked to critically analyse written content such as articles, blogs, transcripts and reports (not code).
extract-wisdom
Extract wisdom, insights, and actionable takeaways from text sources. Use when asked to analyse, summarise, or extract key learnings from blog posts, articles, markdown files, or other text content.
monitor-experiments
Monitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.
analyze-experiments
Designs A/B tests with proper metrics and variants, analyzes running or completed experiments, and interprets results with statistical rigor. Use when setting up experiments, checking experiment status, analyzing results, or making ship decisions.
integration-astro-static
PostHog integration for static Astro sites using SSG
score-task
Score a completed task's quality (0-100) for tracking per-agent quality metrics.
record-learning
Quickly record a learning or discovery while working on a task.
output-eval-validate-judge
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.
