Explore skills

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

Use when looking up journal or magazine name abbreviations, converting between full names and ISO 4/MEDLINE abbreviations, processing BibTeX files for journal name standardization, or answering questions about 期刊缩写/杂志缩写. Triggers on "journal abbreviation", "abbreviate journal", "journal name", "期刊缩写", "杂志缩写", "ISO 4", "LTWA", "BibTeX journal". PROACTIVELY USE when user mentions citation formatting

Python collections (namedtuple, defaultdict, Counter, set) and regex for bioinformatics, covering k-mer counting, FASTA/FASTQ streaming, restriction maps, and PROSITE patterns.

Infrastructure management orchestrator for CI/CD pipelines, deployments, and cloud services. Routes to specialized subagents for GitHub, Cloudflare, Railway, and Stripe. Handles pipeline analysis, deployment coordination, troubleshooting, and secret management. Trigger keywords: devops, deploy, infrastructure, GitHub Actions, Cloudflare, Railway, Stripe, CI/CD, secrets, workflow.

Evaluate if a delegation decision is healthy (amplifying what you love) or harmful (abdicating what you don't understand), based on Chesky's principles. Use this when deciding whether to delegate or stay involved.

Sets and Counter for bioinformatics: gene list operations (intersection/union/difference), k-mer deduplication, and unique element tracking. Bio-specific patterns only.

Python string operations for biological sequences: reverse complement, codon extraction, motif scanning, FASTA parsing. Bio-specific patterns and pitfalls.

Use when user asks "will this scale", "scalability", "capacity planning", "what breaks at 10x", when projecting cost at growth milestones, when identifying the next bottleneck before it hits production, or when planning a migration from monolith to distributed architecture.

Use when .forge/prd.md and .forge/architecture.md exist and the work needs to be decomposed before implementation, when sizing tasks for a sprint, when mapping dependencies between modules, or when a critical path needs to be identified before parallel work begins.

Python control flow patterns specific to bioinformatics, including codon iteration, frame scanning, motif search, and sequence classification.

Use when 3+ independent tasks are ready in .forge/tasks.yaml and multiple agents will work concurrently, when assessing file-conflict risk before dispatching parallel work, when planning branch and merge sequencing for a sprint, or when prior parallel runs have caused merge nightmares.

Python decorator patterns for bioinformatics: timing, validation, memoization, and stacking.