Menu
SkillsMP has collected 24 skills from Whamp/deep-swe-bench. Open a skill to review its source and details.
Showing 24 of 24 collected skills.
Write 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…
Fetch 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…
Use 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.
Paired 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,…
Use 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.
Prompt 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.
Coverage-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…
Property-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…
Testing 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.…
Testing 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.…
Testing 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.…
Property-based testing for quantified generated search, property review, and counterexample triage. Use when a broad domain, invariant, round trip, normalization rule, ordering relation, operation sequence, or schedule can challenge a compact independent…
Fuzzing for coverage-guided input search, target and campaign design, failure minimization, and regression replay. Use to assess or execute fuzzing at input-processing, protocol, file-format, unsafe-code, FFI, or memory-safety boundaries; also use for…
Coverage-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…
Property-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…
Testing 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…
Coverage-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…
Property-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.
Testing 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;…
CodeGraph 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.
CodeGraph 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.
Open 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…
Local 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.
Benchmark 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.