Research

Core principles of SEO including E-E-A-T, Core Web Vitals, technical foundations, content quality, and how modern search engines evaluate pages.

Security-focused code review for PRs, commits, and diffs.

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance iss...

Context optimization extends the effective capacity of limited context windows through strategic compression, masking, caching, and partitioning. The goal is not to magically increase context windows but to make better use of available capacity.

Core principles of SEO including E-E-A-T, Core Web Vitals, technical foundations, content quality, and how modern search engines evaluate pages. This skill explains *why* SEO works, not how to execute specific optimizations.

Analyze command history to identify which skills work, which fail, and where to improve.

Analyze command history to identify which skills work, which fail, and where to improve.

Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues

On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Auto-activation on session cleanup/session-end signals is OPT-IN (default OFF) — requires an explicit project/user directive. Use when explicitly auditing recent work for harness gaps.

Research-validated planning — research → plan → verify cycle for high-confidence implementation plans

Capture W3C PROV-O data lineage for DERIVED RDF, or explain a missing BGP target binding: record CONSTRUCT/DESCRIBE, SPARQL UPDATE, and reasoner-materialization lineage; under the opt-in `why-not` feature, report exactly which grounded BGP triple patterns are absent. Off by default; does not touch sparq-core/sparq-engine's lean build.

Use when turning a sparq contribution into an academic paper — identifying a genuinely-novel contribution (the re-runnable intake), classifying it and picking a venue (ISWC/ESWC Resource for the engine, PVLDB/SIGMOD/EDBT for DB-systems, arXiv/workshop for not-yet-sound ZK/MPC), drafting a single-source Typst (.typ) paper whose eval section binds to live benchmark data via --input/sys.inputs, building both a PDF and an in-site HTML page from that one source, and reviewing claims↔evidence under...

Cost model and optimisation reference for Noir circuits on the UltraHonk / Aztec Barretenberg stack. Use when sizing constraint budgets, deciding whether to push work into an `unconstrained` Brillig hint with an in-circuit verifier, comparing Field-arith vs typed `u64` bit operations, reading `bb gates` / `nargo info` / `noir-profiler gates` output, or weighing ACIR-opcode against backend-gate regressions. Companion to `noir-circuit-patterns` — that skill covers SPARQL-primitive shapes; this ...

Use when mining external JS/TS libraries, runtimes, papers, benchmark suites, bug corpora, or production systems for ideas that should become local tests, fuzzers, benchmarks, or evidence notes.

Use when creating or updating JS/TS performance evidence notes, iteration logs, research notes, generated docs/perf indexes, or searchable benchmark/result summaries.

Use when creating, adapting, reviewing, or debugging JS/TS fuzzers, corpus fixtures, replay files, shrinkers, repro writers, or deterministic random test harnesses.

Use for JS/TS performance-sensitive changes, benchmark additions, benchmark regressions, benchmark result JSON, or any claim that code is faster, smaller, cheaper, or not slower.

4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

Financial factsheet analysis with key metrics extraction and investment rationale

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.

Enter talk mode — conversation and research, no repo changes. ONLY invoke when the user explicitly types `/talk` or `$talk`; never auto-select from a natural-language question or design discussion.

Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.