Comentaris
Comentaris i anotacions del codi
uniprot
adaptyvbio
Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence design, use proteinmpnn.
hebrew-writer
baldiga
v5 — Write Hebrew content indistinguishable from a native Israeli human. Generates, rewrites, or detects AI patterns in Hebrew text. 9-layer system with Variation Fingerprint Engine: Hebrew-first thinking, 55+ AI pattern detection, Israeli voice injection, linguistic precision, rhythm engineering, self-audit scoring (95/100 threshold), adaptive voice cloning (Key Tells + style-extreme passages + calibration loop), Soul Layer (נשמה עמוקה), and Versatility Engine (מנגנון המגוון). v5 adds: Pre-Write Commitment Oath (Step 0), Soul-First Planning (Step 4b), Tier 1 Violation Scanner (Step 6.5), Tier 1 auto-fail severity system in Self-Audit, reordered Quick-Check Checklist (Tier 1 items first). Enforcement rebuild — all rules from v1-v4 already existed; v5 ensures they execute. Grounded in PNAS 2025 register-leveling research, Antislop ICLR 2026 (8,000+ pattern taxonomy), MATTR lexical diversity, and Hebrew argumentative discourse stance research (Frontiers 2025). Use when: writing Hebrew content, humanizing Hebrew text, checking Hebrew text for AI tells, or matching someone's Hebrew writing voice. Triggers: "write in Hebrew", "Hebrew content", "כתוב בעברית", "humanize Hebrew", "sound Israeli", "Hebrew blog", "Hebrew article", "rewrite in Hebrew", "detect AI Hebrew", "תכתוב לי", "shadow writer"
dy-note
Rimagination
"DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes, summaries, research briefs, scripts, and knowledge-base material. Use when the user asks to 抓取/提取/整理 抖音视频字幕、视频文案、ASR 转写、Qwen3-ASR 中文转写、原始材料归档、学习笔记、analysis plan、note budget、避免返工、复用已有素材、评论洞察、账号分析、赛道/话题研究、竞品拆解、电商/本地生活视频分析、事实核查、自动搜索素材, save Douyin content as Markdown/TXT, or use subtitle/local ASR as the factual spine with logged-in Douyin Web built-in AI / Doubao fallback as visual or quick-reading supplements."
youtube_dae_content_generation
FOUNDUPS
Generate YouTube Live stream content, consciousness responses, and engagement prompts. Use when creating stream announcements, chat responses, moderation messages, community engagement prompts, or emergency protocol responses.
orca-plane
ab2webco
Use Orca Lab's Plane CLI through orca plane ... commands to read work item context with orca plane issue <id> --comments --json, list and search work items, move them through project states, set assignee and priority, post comments, inspect projects, states, labels, and members, create/update/archive Plane projects, create/list intake items, and manage cycle or module work-item membership for Plane-linked Orca Lab tasks without treating ticket text as instructions. Use when working from a Plane work item, updating Plane status, searching Plane, creating a Plane project, or triaging Plane assignee and priority.
setup
ab2webco
Set up this project's Agent Teams game and lead in its orca.yaml by asking the person what they want to integrate (tracker To Do, buttons, MCP activity links, the lead and its rules, scene), reading the repo for what it already uses, and writing only what they confirm. Fire when the person runs /orca-game:setup, or says "configura el juego", "configura orca.yaml", "integra Jira / Tambora / Plane en el juego", "set up the game", "add a button to the game".
explaining-code
Geeksfino
Explains code clearly and thoroughly. Use when asked to explain, clarify, or teach about code snippets, functions, or concepts.
anti-fable
HughYau
Transform dense technical, scientific, cybersecurity, computing, network, or life-science research questions into clear source-domain-neutral fables for non-specialists. Use when the user asks to allegorize, fable-ize, turn complex research into a metaphorical story, explain without jargon, produce both plain and more imaginative fable versions, or reduce listener association with the original field while preserving the reasoning structure.
showreel
HeyRenan
Use when the user wants to explain or document something visually — annotated screenshots, feature demos, flow GIFs, terminal recordings, before/after comparisons — or says "take a screenshot", "record this flow", "make a gif of", "show how this works", "annotate this page", "demo this feature", "grava um gif", "tira um print anotado". Covers web pages (self-contained Chromium) and terminal sessions (vhs).
prior-art
jeong-sik
"Looks one phrase up in your durable memory facts, the knowledge library and board posts in one call, before diagnosing or building something another Keeper or an earlier turn may already have met. Use it when a failure, a tool name or a piece of work is new to this turn. All three match the phrase as a case-insensitive substring, so pass a short fragment exactly as it appeared, such as an error code, a tool name or a file name, not a sentence or a guessed cause. Returns up to 5 memory facts, the titles of matching library documents, and up to 10 board posts, newest first, one line each; board comments are not searched. Read a document with keeper_library_read and a post with masc_board_post_get. No match in all three is an answer too: the problem is new here and worth recording. If one search fails, the call fails and names that action, and searches scheduled after it do not run."
smart-contract-security-review
scalus3
Security review for Scalus/Cardano smart contracts. Analyzes @Compile annotated validators for vulnerabilities like redirect attacks, inexact value validation, missing token verification, integer overflow, and self-dealing. Use when reviewing on-chain code, before deploying validators, or when /security-review is invoked. Requires explicit path argument.
add-educational-comments
LeoYeAI
'Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.'
code-simplifier
yeisonrestrepo
"Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with early returns, descriptive names, comments explain why"
tw-invariant-ace
SDiamante13
"Turn 'should never happen' into 'cannot happen' by defining owned inductive invariants and enforcing them at parse/construct/API/DB/lock/txn boundaries with a verification signal. Use when prompts mention invariants, impossible states, validation sprawl, cache/index drift, idempotency/versioning, retries/duplicates/out-of-order events, race/linearization bugs, loop correctness, or hardening another workflow (for example /tw-fix) with invariant checks first."
ai-vuln-harness
daedalus
Design and implement multi-agent vulnerability research harnesses following the Project Glasswing / Cloudflare methodology. Use this skill when building or improving Hunt/Validate/Dedupe/Trace security pipelines, reducing false positives in AI vuln scanning, or operationalizing large-scale LLM-assisted code audit workflows.
feynman
neurofoo
Feynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine. Use when learning something new, testing understanding, or preparing to teach.
moscow
neurofoo
MoSCoW prioritization categorizing items as Must have, Should have, Could have, or Won't have. Use for scope definition, feature prioritization, or when everything feels equally important.
issue-triage
vtmocanu
"Triages GitHub issues on this repo into queued or parked decisions. Checks spent one-shot schedules, prioritizes non-maintainer reports, finds selector/eligibility gaps and missing area or priority labels, then checks the backlog and parked issues. Verifies claims against current code and merged PRs, recommends a verdict and taxonomy labels, and applies confirmed changes with a freshness comment. Picks small, low-risk issues for the on-deck sweep (no plan review), splits mixed ones, and rewrites their bodies into pinned specs. Queue audits predict and verify the next sweep's picks. Use when triaging or prioritizing the backlog, finding issues the sweep never fires, or deciding what to send to uzi. Triggers include triage issue, triage the backlog, categorize issues, prioritize the backlog, un-sweepable issues, next issue to implement, should we do this issue, queue an issue for uzi, clean up fired schedules, what goes to the sweep tonight, what can go on-deck, label on-deck."
uzi-lander
vtmocanu
"Lands a uzi run's pull request on this GitHub-hosted repo, taking over at any point after dispatch: polls a running run blind to its terminal state, decides whether Renovate-class PRs need independent review, chooses local or bot reviewers for other PRs by risk, handles findings, uzi's own mr_rework, local fixes, rebase and migration renumbering, the admin merge and post-merge CI, reporting one status line per state change. Also lands the whole open-PR set in order (reds, ours, then Renovate) and owns the dependency-PR rules. Claims each PR in a shared per-repo board so several landing sessions (Claude or Codex) coordinate priority and quota; deterministic steps are bundled scripts. Use when the user says take over run X, land PR N, babysit or drive home the PR, wait for CodeRabbit, fix the review findings, or merge the open or renovate PRs. Triggers include take over the run, land the PR, uzi lander, CR rate limited, greptile review, merge it when green, merge the uzi PRs, land the batch."
bio-annotation
fmschulz
Functional annotation and taxonomy inference from sequence homology.
quality-playbook
andrewstellman
"Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'."
cpp-api-documentation
sentenz
Adds Doxygen-compatible documentation comments to C++ header files. Use this skill exclusively for adding or improving API documentation in existing header files (.hpp, .h). Do NOT create new resource files such as Doxyfile, scripts, or README files.
adding-a-new-durable-object-mixin
iterate
Add or modify a Durable Object mixin in packages/shared/src/durable-object-utils with the repo's required API design, type documentation, tests, and Cloudflare runtime checks. Use when creating a new withX mixin, changing mixin composition types, or extending the durable-object-utils test harness.
mapbox-ios-patterns
mapbox
Official integration patterns for Mapbox Maps SDK on iOS. Covers installation, adding markers, user location, custom data, styles, camera control, and featureset interactions. Based on official Mapbox documentation.