热门技能
当前社区里最受关注、增长最快的技能。
contribute-to-thenetwork
SlopDotCash
Fixes and proves real defects in The Network (eliza-research/thenetwork) inside its PRD and MVP plan. Use for a reproduced bug, matching-algorithm or simulation validation, security, or a measured improvement; excludes UI and copy changes, unapproved features, coverage-only tests and mock-only proof.
review-nurosos-contributions
SlopDotCash
Review an existing NurosOS PR for reproducibility, checkpoint/replay correctness, research claims, and useful evidence. Use for advisory exact-head review in modarresi1913/NurosOS, after checking current project and execution authority.
review-slopdotcash-contributions
SlopDotCash
Reviews exact-head Slop (SlopDotCash/slopdotcash) contributions for MVP scope, correctness, security and real evidence. Use on an existing PR into development; excludes implementation ownership, self-approval, scoring decisions and payment decisions.
review-eliza-contributions
SlopDotCash
"Independently evaluate an elizaOS/eliza implementation, real-system verification, diagnosis, evidence artifact, or substantive review for quality, security, duplication, provenance, and contribution credit. Use in project CI or maintainer review before accepting work or changing a public reward allocation; reject unit-only or mock-only proof."
slop
SlopDotCash
"Safely bootstrap a Slop contribution skill for the current funded repository. Use when an agent is asked to start contributing through slop.cash, install or update a project skill, preview local usage access, or diagnose Slop setup without exposing prompts, source, transcripts, credentials, or wallet secrets."
review-darling-arm64-contributions
SlopDotCash
"Independently evaluate an xchemtina/darling-arm64 tier claim, upstream fix, falsified finding, flake analysis, or harness for architecture honesty, control discipline, A/B/A integrity, reproducibility, attribution, and contribution credit. Use in project CI or maintainer review before accepting work or changing a public reward allocation."
review-thenetwork-contributions
SlopDotCash
Reviews exact-head The Network (eliza-research/thenetwork) contributions for PRD scope, matching correctness, safety gates and real evidence. Use on an existing PR into main; excludes implementation ownership, self-approval, scoring and payment decisions.
contribute-to-slopdotcash
SlopDotCash
Fixes and proves real defects in Slop (SlopDotCash/slopdotcash) inside the approved MVP. Use for a reproduced bug or approved MVP gap in security, identity, scoring, verification, vault, funding, or settlement; excludes UI and copy changes, new features, coverage farming, and mock-only proof.
review-delta-star-contributions
SlopDotCash
"Independently evaluate a SlopDotCash/proximityprize Delta Star implementation, Lean proof, test, refutation, diagnosis, or evidence artifact for correctness, security, duplication, provenance, and contribution credit. Use in project CI or maintainer review before publishing a Proximity Prize contribution share."
contribute-to-nurosos
SlopDotCash
Prepare a bounded NurosOS contribution with reproducible developmental experiments and exact-head evidence. Use for an existing approved task in modarresi1913/NurosOS; check the paused-project and verification gates before execution or submission.
review-feed-contributions
SlopDotCash
Reviews exact-head Feed (feedforagents/feed) contributions for scope, trading-algorithm correctness, security and real evidence. Use on an existing PR into staging; excludes implementation ownership, self-approval, scoring and payment decisions.
review-payzcode-ai-contributions
SlopDotCash
Review an existing Payzcode Enterprise contribution for useful results, Express application correctness, security and actual workflow evidence. Use for advisory exact-head review after checking permission and execution authority.
review-asi-contributions
SlopDotCash
"Independently evaluate whether a SlopDotCash/asi contribution delivers a reproducible hill climb, measured research advancement or refutation, or an actual reproduced bug fix. Reject generic improvements, cleanup, and trivial work."
contribute-to-canonry
SlopDotCash
Builds and verifies useful changes to Canonry, the agent-first open-source AEO platform. Use for a reproduced defect or a bounded maintainer issue in Canonry/canonry; excludes coverage farming, live provider spend, version-only bumps and unrelated projects.
contribute-to-delta-star
SlopDotCash
"Review and test current SlopDotCash/proximityprize pull requests, finish mission-aligned issues through pull requests, restore main workflow health, then advance, test, or refute machine-checked Delta Star work. Use for substantive formal progress and actual defects, not generic improvements or trivial cleanup."
contribute-to-asi
SlopDotCash
"Review and test current SlopDotCash/asi pull requests, finish mission-aligned open issues through pull requests, restore main workflow health, then hill-climb continual-RL benchmarks, produce measured research advancement, or fix a reproduced bug. Do not use for generic improvements, cleanup, or speculative polish."
contribute-to-payzcode-ai
SlopDotCash
Prepare a bounded contribution to lysande62/payzcode-enterprise after its project permission, authority and security gates pass. Use for an existing approved Payzcode AI task, with real application evidence and exact-head attribution.
review-canonry-contributions
SlopDotCash
Reviews exact-head Canonry contributions for correct metrics, surface parity and evidence. Use on an existing PR in Canonry/canonry; excludes implementation ownership, self-approval, security certification and payment decisions.
contribute-to-darling-arm64
SlopDotCash
"Raise a real macOS application one verified tier up the arm64 Darling ladder, fix a reproduced defect upstream in darlinghq, or falsify a recorded finding in xchemtina/darling-arm64. Every outcome ships a control, an A/B/A where it claims a fix, and a rerunnable harness. Use for measured arm64 capability, never for x86_64 work, refactors, or cleanup."
contribute-to-eliza
SlopDotCash
"Review and prove current elizaOS/eliza pull requests on real working systems, finish existing issues through pull requests, restore develop workflow health, then audit mission-critical security, bugs, stale documentation and comments, and missing end-to-end verification, with optional public payout registration. Use for one material outcome on an existing shipped product path, not generic improvements, trivial cleanup, or unit-test production."
ship-commits
phase-rs
Use when shipping local commits to main via the merge queue. Creates an isolated worktree based on origin/main, cherry-picks the named commits into a fresh branch, pushes with --no-verify, opens a PR with gh pr create --fill, and enqueues with gh pr merge --auto. Outbound counterpart to pr-contribution-handler. Use when the user says "ship this", "push to main", "send through the queue", "PR this work", or has finished a chunk of work and wants it on main.
project-reference
phase-rs
Reference lookup for phase.rs — build/test/cargo/clippy commands, cargo aliases, WASM build, card-data pipeline and jq lookups, frontend (pnpm) commands, coverage report, crate/workspace architecture, engine internals, WASM bridge, AI engine, multiplayer server, frontend layers, environment variables, releasing (cargo-release), and CI. Use when you need to look up how to build, test, run, generate card data, release, or where a crate, module, command, or env var lives.
harmony-batch-correction
jaechang-hits
"Batch correction for single-cell RNA-seq (and other omics) with Harmony. Removes technical batch effects from PCA embeddings while preserving biological variation. Use after PCA, before UMAP/neighbors. Fast and scalable to millions of cells. Python (harmonypy, scanpy integration) and R (Seurat) APIs."
validate-ui-scenario
microsoft
Use when reproducing a UI bug or verifying a fix by driving a real VS Code window end to end and capturing evidence. Writes a scenario file, runs it against a dev build or installed Insiders, and produces a captioned video, per-step screenshots, a Playwright trace, and an HTML report to attach to an issue or pull request.