whamp
- 56 skills
- 0 followers
- 14 hours ago last updated
- ▌ Docs To Types · whamp bundleConverts grill-with-docs output — CONTEXT.md glossaries, ADRs, and approved domain decisions — into typed architecture. Use after grill-with-docs when the user wants domain types, seams, adapters, errors, call stacks, and dependency rules expressed in code before business behavior.
- ▌ No Mistakes · whampValidate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.
- ▌ Ponytail Help · whampQuick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
- ▌ Testing 2 · whamp bundleTesting design and maintenance for selecting test seams and levels, writing explicit regression, unit, integration, contract, or browser tests, proving bug fixes, reviewing tests, diagnosing flakes, and interpreting coverage or mutation results. Use `property-based-testing` directly for broad generated domains, invariants, operation sequences, or schedules; use `fuzzing` directly for coverage-guided exploration of parsers, protocols, unsafe code, or untrusted input.
- ▌ Testing 3 · whamp bundleTesting strategy and explicit behavioral evidence. Use for selecting test seams and levels, writing regression, unit, integration, contract, or browser tests, proving fixes, reviewing tests, diagnosing flakes, and interpreting coverage or mutation results. Use it to choose explicit examples, property-based testing, or fuzzing as the primary search mechanism for each risk.
- ▌ Fuzzing 2 · whamp bundleCoverage-guided fuzzing for implementation and test work on input-processing and memory-safety boundaries. Use when a feature or bug touches parsers, lexers, decoders, deserializers, codecs, file formats, protocol handlers, malformed, chunked, or adversarial input, unsafe or FFI code, or crash, hang, and resource-exhaustion risks; also use when designing or running fuzz targets, engines, oracles, seeds and corpora, coverage campaigns, crash minimization, and regression conversion.
- ▌ Testing 4 · whamp bundleTesting strategy and explicit behavioral evidence. Use for selecting test seams and levels, writing regression, unit, integration, contract, or browser tests, proving fixes, reviewing tests, diagnosing flakes, and interpreting coverage or mutation results. Use it to map plausible failures to explicit examples, property-based testing, or fuzzing after inspecting the relevant code and tests.
- ▌ Codegraph 2 · whamp bundleCodeGraph scout before broad grep/read. Use for repo explanation, navigation, diagnosis, runtime/reconnect flow, contract/RPC/schema tracing, refactor/cycle seams, dead-code cleanup, test targeting, and code review.
- ▌ Property Based Testing 2 · whamp bundleProperty-based testing for implementation and test work with broad structured behavior. Use when a feature or bug spans input combinations, round trips, encoding and decoding, serialization, normalization or idempotence, ordering or pagination, schema variants, stateful operation sequences, distributed or concurrent schedules, parsers or codecs with semantic invariants, or differential models; also use when designing or reviewing generators, shrinkers, properties, and counterexample handling.
- ▌ Codegraph 3 · whamp bundleCodeGraph scout before broad grep/read. Use for repo explanation, navigation, diagnosis, runtime/reconnect flow, contract/RPC/schema tracing, refactor/cycle seams, dead-code cleanup, test targeting, and code review.
- ▌ Brain · whamp bundleUse when working on a project with Brain agent memory management. Triggers on memory_commit, memory_branch tool usage, or when the project has a .memory/ directory.
- ▌ Conductor · whamp bundleContext-driven development with spec-driven workflows, TDD-based task execution, track management, and phase checkpointing
- ▌ Summary Judge · whamp bundleCompare and judge file summaries from pi-read-map vs standard read tool. Use when evaluating summary quality on large files (>2k lines). Trigger with "/skill:summary-judge <file-path>" to run full automated comparison and update demo/README.md.
- ▌ Rlm · whamp bundleProcess files too large to fit in context (>100KB, >2000 lines). Uses Python REPL for structural analysis, LLM queries for semantic reasoning, and subagents for final synthesis. Triggers - large file, big document, massive log, full codebase, entire repo, long transcript, context window exceeded.
- ▌ Axi · whampAgent eXperience Interface (AXI) — ergonomic standards for building CLI tools that agents use via shell execution. Use when building, modifying, or reviewing any agent-facing CLI.
- ▌ Playwright CLI Axi · whampUse playwright-cli-axi when controlling Playwright from an agent shell and when video recording, TOON output, or AXI-friendly browser automation matters.
- ▌ Browser Tools · whamp bundleLightweight Chrome automation toolkit with shared configuration, JSON-first output, and six focused scripts for starting, navigating, inspecting, capturing, evaluating, and cleaning up browser sessions.
- ▌ Gemini CLI Integration · whamp bundleUse the gemini-cli-integration skill PROACTIVELY when analyzing large codebases, multiple files, or directories. Leverages Google Gemini's massive context window with @ syntax for file inclusion to handle comprehensive codebase analysis, implementation verification, and architectural understanding.
- ▌ Kv Store Skill · whamp bundleA skill for interacting with a simple key-value store. Use this skill to get, set, and delete values from the store.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Runboard · whamp bundleOpen a Herdr tail tab for a harness run when the user explicitly asks for a runboard, tail, Herdr tab, or raw log view. For new harness/run_batch.py monitoring, prefer the structured dashboard at scripts/run_dashboard.py reading results/_runs/<run_id>; this skill is the compatibility/tail workflow.
- ▌ X Thread Fetch · whamp bundleFetch a full X/Twitter thread — all posts with untruncated text plus images — without auth or the paid API. Use when the user wants to retrieve, extract, scrape, pull, save, or download an X/Twitter thread, tweet text, or tweet images, mentions a status URL or tweet id, or asks to get the content of a thread/post.
- ▌ Benchmark Launch · whampUse before preparing or executing a confirmed deep-swe-bench launch, especially when configs use advisor, observational-memory workers, subagents, local-vLLM shims, or any model beyond the main executor; use before claiming a launch is working.
- ▌ Write Benchmark Thread · whampWrite a viral-but-honest X/Twitter thread for a benchmark or eval result (e.g. DeepSWE, ProgramBench, ponytail, pi-observational-memory runs). Use when the user asks to write, draft, rewrite, iterate on, or render a tweet thread about benchmark results, eval findings, A/B comparisons, agent evaluations, or model measurements, or says "thread", "tweet", "X post", or references the tweet-craft process. Enforces accuracy, human voice, and the accumulated review lessons. Read FEEDBACK_LOG.md before drafting.
- ▌ Benchmark Social Graphics · whamp bundleBenchmark graphics. Use when creating social cards, README benchmark tables, chart images, X/Twitter graphics, or visual summaries from eval result artifacts where exact numbers, axes, labels, or datapoint placement matter.
- ▌ Prompt Embedding Analysis · whampPrompt embedding analysis. Use when clustering benchmark prompt/config text, comparing semantic neighbors, or separating prompt-shaped effects from behavioral wrappers in deep-swe-bench results.
- ▌ Paired Trajectory Analysis · whamp bundlePaired trajectory analysis for benchmark churn. Use when comparing two configs on matched task/rep cells, explaining solve flips, diagnosing a local model against a frontier reference, separating net score from churn, or preparing evidence to improve a skill, prompt, tool, or harness surface from trajectory differences.
- ▌ Benchmark Config Validation · whampUse before adding or changing a deep-swe-bench config release, model leaf, provider/model API path, config lock, role declaration, usage parser, smoke contract, or extension/subagent worker usage accounting.
- ▌ Codegraph · whampLocal symbol-and-relationship map of the repo. Use to see who calls what (blast radius) before editing a function, class, or method. The binary is at /arm/bin/cg.
- ▌ Fuzzing · whamp bundleCoverage-guided fuzzing. Use when selecting or writing fuzz targets for parsers, decoders, protocol handlers, unsafe or FFI code, or untrusted inputs; running cargo-fuzz, libFuzzer, AFL++, or Go fuzzing; designing fuzz oracles and corpora; analyzing coverage plateaus; or reproducing, minimizing, deduplicating, and converting crashes into regressions.
- ▌ Testing · whamp bundleTesting design and maintenance. Use when choosing a test seam or level; writing or reviewing regression, unit, integration, contract, browser, JavaScript/TypeScript, or Rust tests; proving a bug fix; auditing AI-generated tests or suspected test slop; diagnosing flaky tests; interpreting coverage or mutation results; or deciding whether tests should be improved, quarantined, or removed. Routes property testing and fuzzing.
- ▌
- ▌ Ponytail · whampForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
- ▌ Property Based Testing · whamp bundleProperty-based testing. Use for tests and reviews involving broad structured domains, parsers and codecs, canonicalizers and validators, compact postcondition oracles, differential models, stateful APIs and protocols, or concurrent schedules.
- ▌
- ▌ Herdr · whamp bundleUse Herdr sidecars for persistent or continuously observable work when `HERDR_ENV=1`. Also use when asked to control panes, layout, workspaces, or coding agents through Herdr.
- ▌
- ▌ Repo Cleanup · whamp bundleAudit and safely remove obsolete Git worktrees, repository-owned temporary artifacts, and inactive development databases.
- ▌ Model Routing · whamp bundleRoute delegated model portfolios across independent provider and subscription pools. Use when selecting models for delegated roles, planning multi-family review and synthesis, handling quota pressure, watching long-running work, or adding family diversity to implementation, debugging, visual work, and adversarial review.
- ▌ Worktree First · whamp bundleWorktree-first isolation routes substantive implementation through Lane in adopted repositories and a plain Git worktree elsewhere. Use before a feature, nontrivial fix, substantial refactor, delegated implementation, or deliberate Lane adoption.
- ▌ Clear Writing · whamp bundleWrite or revise durable human-facing prose with plain force. Use for docs, READMEs, API guides, runbooks, commit messages, PR descriptions, reports, error messages, UI copy, or explicit requests for clearer, shorter, sharper, more direct, or less AI-sounding prose.
- ▌ Explain Diff HTML · whamp bundleBuild an interactive HTML explainer of a code change (a diff, branch, or PR). Use when the user wants a rich walkthrough of what changed and why.
- ▌ First Principles · whamp bundleInteractive first-principles reasoning that separates facts, constraints, assumptions, analogies, and unknowns before rebuilding options from fundamentals.
- ▌ Distilling Skills · whampUse when the user wants to find, evaluate, and combine agent skills on a topic into a single best-of-breed version. Triggers on requests to search skills.sh, improve an existing skill by finding alternatives, or build a concentrated skill from multiple sources.
- ▌ Ban Type Assertions · whamp bundleBan `as` type assertions via the native oxlint `typescript/consistent-type-assertions` rule (`assertionStyle: 'never'`), replacing them with compiler-verified type-safe alternatives. Use when enabling the assertion ban in a project or fixing violations in an existing one.
- ▌ Nvidia Cuda Performance · whamp bundleNVIDIA CUDA performance engineering. Use when estimating, diagnosing, designing, reviewing, implementing, or validating GPU performance for CUDA kernels, CUDA-backed applications, RTX 3090 or SM86 targets, LLM inference, or intra-host multi-GPU scaling.
- ▌ Omarchy Free Disk Space · whamp bundleSafely audit and reclaim disk space on Omarchy and Arch Linux systems. Use when asked to free up disk space, clean an Omarchy computer, find what is using storage, audit disk usage, clean Arch package caches, or check Snapper disk usage.
- ▌
- ▌ Dynamic Workflow Patterns · whampUse when the user asks for a workflow, dynamic workflow, fan-out, multi-agent orchestration, ultracode-style work, large-scale verification, adversarial review, tournament selection, or decomposable research/refactor tasks. Teaches when to use Pi's workflow tool and which orchestration pattern to choose.
- ▌ Perform Like Jeff And Sanjay · whamp bundlePerformance engineering for a single binary. Use when designing or reviewing performance-sensitive code, estimating resource costs, diagnosing a measured bottleneck or flat profile, implementing a performance change, or validating a claimed speedup.
- ▌ Integrate Napkin Agent Skills · whamp bundleIntegrate a Napkin vault with the files created by setup-matt-pocock-skills.