lift-the-reference
Use when the user provides a reference implementation (URL, repo path, branch, file) plus a verb like "use", "copy", "adapt", "port", "model after" - mandates fetching/reading the reference before designing, and lifting the structure rather than reimagining it.
What this skill does
# Lift the Reference, Don't Redesign ## Why this skill exists The single most-corrected behavior across sessions (14+ incidents): the user points at an existing implementation - "use the ripgrep impl from oh-my-pi", "use playwright_rs instead of building your own renderer", "I told you to copy as much as possible from those tools" - and the agent designs a "cleaner" alternative instead. The user has to repeat the directive, sometimes multiple times in the same thread. ## When this fires User message contains BOTH: 1. A reference: URL (GitHub, docs site), filesystem path, branch name, or `@filename` mention. 2. A lift-verb: use, copy, adapt, port, mirror, model after, base on, follow, like X does, take from. Also fires on phrases like "don't redesign", "don't rewrite from scratch", "don't reinvent". ## Required behavior 1. **Fetch first.** Use Read / WebFetch / `gh` / `git show` to load the reference content into your context. Quote the relevant section back to the user in 5-15 lines. 2. **Map the structure.** State the reference's shape: file layout, key types, entry points, public API. One paragraph. 3. **Identify deltas.** State what (if anything) needs to differ for the user's use case, and why. Default to "no delta". 4. **Then implement.** Mirror the reference's naming, ordering, error handling, and idioms. If you are tempted to rename, reorder, or "improve", articulate the cost-benefit out loud before doing so. ## What "lifting" is NOT - Reading the reference, then writing your own version from memory. - Cherry-picking only the API surface and rebuilding internals. - "I read it and the spirit of it is X" - the user wants the letter, not the spirit. - Proposing an alternative architecture in the same turn. ## Anti-pattern to refuse "Want me to revise the plan to use a slightly different approach that..." - No. The user already chose the approach. Implement it. ## Override The only valid reason to deviate from the reference is a *technical* incompatibility with the target environment (different language, missing dependency, breaking API change). State it explicitly; do not deviate for aesthetic reasons.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.