Comments
Code comments and annotations
loom-builder
by rjwalters
"Implements issues labeled loom:issue (human-approved work)"
grill-me
by laneworkapp
"Grill me — a relentless design interview run on a Lanework board. Interrogates the user in rounds until a plan or design is a shared understanding, mapping every decision as a design tree, and accumulates the questions, the owner's rulings, the facts dug up along the way and the resulting glossary and decision records on a grill board (a <Topic> Grill.lanework folder the skill founds when none exists). Every question is a card, every ruling is written into that card in the owner's words, and the board is the record a later session resumes from. Use this skill whenever the user says 'grill me', 'grill me on X', 'interview me about', 'interrogate me', 'sharpen this plan', 'let's think through X properly', 'design session for X', or wants a plan or feature examined question by question before anything is built. Not for founding general boards (lanework-boards), sweeping a pipeline board (pitlane), or standing watch on one (pitwall)."
review-round
by jamesarich
Work a CodeRabbit review round on a Meshtastic PR to completion - read the unresolved threads, fix or answer each, push ONCE, reply and resolve every thread, confirm CodeRabbit actually reviewed the new head (not a reply wrapper), and only then wait on checks. Also the pre-PR step - a local just review on a finished change. Use whenever a PR has CodeRabbit threads, a merge is BLOCKED with everything green, or before opening a PR in a repo where CodeRabbit runs (org-wide since 2026-09).
react-hook-composition
by mutav-finance
Use when creating data fetching hooks — enforces single-purpose hooks with no side effects; toasts, analytics, and error handling belong in view model hooks, not data hooks
staged-spec-review
by phazei
Review one stage of a multi-stage specification against the full plan to catch forward-compatibility gaps before they compound. Use whenever the user asks for a review of a single phase, prompt, RFC section, migration step, or implementation that is part of a larger sequence — especially when they provide both the artifact under review AND the full multi-stage spec. Triggers on phrases like "review prompt N against the full spec", "check this phase against the others", "did stage 1 set up correctly for stages 2-5", "is this RFC consistent with the rest", or any request to audit a single piece of a sequenced plan with the rest of the plan as context. Use this even when the user doesn't explicitly say "staged" — if the structure is clearly sequential (prompt 1 of 5, phase A of D, migration step 2, etc.) and they're asking about one piece, this skill applies.
backlog-synthesis
by zheref
Reconcile a long backlog into a smaller one — group open issues that target the same rule/clause, machinery file or root cause, propose a consolidation plan as an iterable Artifact, and on approval file one consolidated issue, attach the originals as sub-issues and close them with a reference. Use when the maintainer invokes $backlog-synthesis <critical high medium low all> [<repo>], or asks to consolidate, synthesize, dedupe or shrink a backlog.
paperproof-protocol
by PaperProofLabs
Operate the PaperProof protocol for AI agents and developer assistants. Use when a user asks to publish, update, query, verify, inspect, or explain PaperProof artifacts, versions, comments, governance, native prompts, Agent Memory registrations, Walrus content, Sui package/object bindings, wallet readiness, or SDK-based PaperProof workflows. Prefer protocol, SDK, Sui, Walrus, and indexer interfaces over browser automation or website clicking.
corvio-operate-workspace
by NeoFlux-AI
"Use when the user provides files or attachments to keep, organize, synthesize, edit, reorder, splice, format, or update; for research, reports, comparisons, proposals, plans, decisions or choices using earlier decisions, meeting notes, project work, bugs/regressions/incidents, reviews, follow-ups, or prior constraints and material; or resumes earlier work with an operation, question, conversation, document, or project handle. Make one relevant Corvio read before committing to a plan or answer while keeping the host's normal files and tools; a later no-write decision does not skip that read. Save or update only results worth sharing or revisiting. The connected Corvio Workspace is a user-configured work surface: selected ordinary files plus a keep, organize, synthesize, or update request define its bounded task scope even without the product name. Explicitly local-only, sensitive, disclosure-unclear, or unavailable work stays out. Also use for installing, connecting, updating, or repairing Corvio, workspace, @Corvio, 调研、报告、对比、选型、方案、计划、决策、既有决定与取舍、纪要、复盘、改写、调序、剪拼、格式整理、bug、故障、回归、旧约束、之前的资料、继续上次、共享、同步给团队、沉淀. A transient answer is normally no-write. An event not recurring rules out automatic reusable-Skill admission, but its requested organized recap may still be a useful reader artifact."
loom-judge
by rjwalters
"Reviews PRs labeled loom:review-requested"
bot-instructions
by vanillagreencom
"Load to render, check, or adopt a repo's GitHub review-bot instruction files from the shared doctrine and its effective manifest."
write-discoverable-code
by SjB
Rules for writing code that coding agents (and humans) can find and understand through plain-text search. Apply whenever writing or renaming code: functions, types, constants, files, error messages, doc comments. Grounded in measurement: agents navigate by plain-text search, not by AST or language server, so every identifier is a search query and every search miss costs wasted reads.
sharingan
by zheref
Drive one open PR to CON-32 readiness at its human gate, then stop there. Use when the maintainer invokes hatsu:sharingan #<PR> to <G2 G4>, or asks to get a PR ready, unstick a PR, or take it to the merge gate; hatsu:en composes it as its second and fourth steps. It names the first blocking condition, settles review threads, requests the owed reviewer round, and decides readiness with nen pr ready. It never merges, self-reviews, or votes.
code-simplifier
by YuukiFST
Simplify and refine recently modified code for clarity, consistency and maintainability while preserving all functionality. Use when asked to simplify, clean up or refine code just written, or after finishing a change.
multica-platform
by OldBoy405
"Use for Multica platform actions the runtime brief does not fully cover: issue and PR contracts, mentions, agents, squads, autopilots, projects, runtimes, skill import. Not for the product code you are working on."
code-upkeep
by Sylla-BV
This skill should be used when the user asks to "update docstrings", "audit docstrings", "fix docstrings", "add docstrings", "check docstrings", "Google-style docstrings", "add field descriptions", "update tests", "audit test coverage", "generate tests", "add tests", "fix tests", "write pytest tests", "check test coverage", "missing tests", "stale tests", "test this module", "add test cases", "bring code up to date", "code upkeep", "maintain code", or wants to audit and update Python docstrings or tests.
drift-scout
by overseers-desk
"Find drift — stale debris a refactor, rename, or move left in a codebase's edges. Triggers: drift-scout, find drift, what did the rename miss, stale references, sweep the edges."
research-refactor
by qijialiv-cell
"Research code refactoring framework for R/Stata/Python projects. Enforces safe, incremental, auditable refactoring with dependency tracking and atomic commits."
issues-workflow
by terrylica
Plan and track work using a GitHub Issues-first workflow with sub-issue hierarchies, issue-branch-PR lifecycle, and auto-close on merge.
eli5
by joshuajbrunner
Simplify and re-explain complex topics in plain, approachable language. Use when the user says "dumb it down", "explain like I'm 5", "eli5", "simplify this", "I don't understand", or asks for a beginner-friendly explanation. Treats the user as a junior developer learning the ropes.
refill-sprint Skill
by OmniNode-ai
Auto-pull tech debt tickets from Future into Active Sprint when the sprint queue is empty or below capacity threshold
Hacker News Digest
by Atrium-Hermes
Top HN stories filtered by interests, with comment-mined insights and themed clustering
linear
by vanillagreencom
"Load for any Linear read or write: issues, projects, cycles, milestones, initiatives, labels."
project-planner
by DoubleNode
Strategic project planning skill that creates kanban items, subitems, and plan documents WITHOUT executing any implementation. Enforces plan-and-delegate workflow with explicit handoff checkpoint.
mugetsu
by zheref
Publish one release to one production destination — a store, the live environment — by running the repository's declared release row (nen shu release) and/or nen shu deploy --target <production target> --run, after nen release preflight reads green and the tag has been cut. Use ONLY when the maintainer records a per-target go in their own words; that message is quoted verbatim in the report and on the release PR, and is never inferred. This is G3 (CON-6): no composite reaches it on its own authority — not getsuga, not en, and futon only as a typed then step carrying the ADVANCE GO its § 3 defines (the maintainer's own invocation, bound to the tag that run cuts, one target, once, and only on a repository nen repo classify reports as kind process or library) — no agent proposes it, a go with no tag is refused unless it is that advance go, and one go publishes one target once.