Comments
Code comments and annotations
language-maturity
by radra23
Per-language OTel signal maturity matrix (Stable / Beta / Development) and feature-gating rules. Use before generating OTel SDK code to gate signals by maturity and the --experimental flag.
how
by mmdmcy
"Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation."
review-paper
by pedrohcgs
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via --peer --stress; reviewer-disposition variance reporting via --peer --variance N. Auto-invokes /review-r + /audit-reproducibility on referenced scripts unless --no-cross-artifact.
Xiaohongshu (小红书)
by imoonkey
```
reference-educational-template
by djankies
[REPLACE] Teach concepts and demonstrate patterns with examples. Use when [REPLACE with specific triggers].
butler-qa-pr-review
by Tzeusy
Use when working a GitHub PR for a Butler QA investigation or reviewer follow-up: unresolved review threads must be answered inline, PR text must contain no personal information or secrets, and the branch is not done until required GitHub checks are green.
addressing-pr-review-comments
by streamlit
Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review comments and general PR (issue) comments. Use when a PR has reviewer feedback to address, including code changes, style fixes, and documentation updates.
fizz
by visionik
Fizzy.do Kanban CLI for managing boards, cards, comments, tags, and more.
review-pr
by warpdotdev
Review a pull request diff and write structured feedback to review.json for the workflow to publish. Use when reviewing a checked-out PR from local artifacts like pr_diff.txt and pr_description.txt and producing machine-readable review output instead of posting directly to GitHub.
by imoonkey
Write-op coverage (2026-04-19): all 12 write ops verified PASS end-to-end (likePost, unlikePost, savePost, unsavePost, followUser, unfollowUser, muteUser, unmuteUser, blockUser, unblockUser, createComment, deleteComment). createComment/deleteComment chain via ${prev.createComment.id} against a low-traffic target post — high-profile accounts (e.g. @instagram) trigger spam-filter shadow-deletes that 404 the immediate delete.
cognitive-task-analysis
by curiositech
Methodology for eliciting expert knowledge about cognitive processes, decisions, and mental models in complex tasks
generar-post
by josevictorgarcia
Crear un post (carrusel) de Instagram o TikTok de N slides a partir de una plantilla propia de Canva, cambiando solo los textos (y, si la plantilla lo pide, una imagen libre de derechos). Úsala cuando el usuario pida un post, una publicación, un carrusel o contenido nuevo sobre un tema concreto, o mencione una de sus plantillas. También cuando pida "otro igual pero de X".
Scholar Evaluation
by unerue
Abstract: ScholarEval is a retrieval augmented evaluation framework that assesses research ideas based on two fundamental criteria: soundness (the empirical validity of proposed methods based on existing literature) and contribution (the degree of advancement made by the idea across different dimensions relative to prior research). The framework achieves significantly higher coverage of expert-annotated evaluation points and is consistently preferred over baseline systems in terms of evaluat
by imoonkey
source_url should match the page where the action would naturally happen — Pinterest sometimes rejects writes when source_url is just /. Use the board/pin URL the action targets (e.g. /<username>/<board-slug>/).
build
by TakaGoto
"Build a RAG component hands-on with guided steps"
github-code-review
by darkmatter
"Review PRs: diffs, inline comments via gh or REST."
todo-manager
by Nakadie
Manage the weekly todo note. Use this skill whenever the user asks to add a ticket to their todos, move a ticket between days, mark a todo as done, or create a Jira subtask from a PR review comment. Handles Jira title lookup, PR/status checks, and subtask creation automatically.
tech-radar-blip
by bcook797
Guide for writing high-quality blip submissions for the ThoughtWorks Tech Radar. This skill should be used when someone asks for help submitting a blip to the Tech Radar, writing a radar submission, or preparing a technology recommendation for the ThoughtWorks radar.
code-review
by dotnet
Deep code review of PR or materialized candidate-patch changes for correctness, safety, and MAUI conventions. Uses independence-first assessment (code before narrative) and delegates to the maui-expert-reviewer agent for per-dimension sub-agent evaluation. Triggers on: "review code for PR", "code review PR", "review candidate patch", "analyze code changes", "check PR code quality". Do NOT use for: summarizing PRs, describing what changed, general PR questions, running tests, or fixing code.
analyze-github-flake
by flutter
Expertise in analyzing flake github issues in the flutter/flutter repository. Use when a user wants to analyze the flakiness of a specific link to a flutter github issue.
explain-code
by dakotahp
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
line-chart-generator
by zxhfighter
Generate line charts and time-series visualizations using matplotlib. Use when users need to create line charts for price trends, stock data, performance metrics, or any time-series data. Supports annotations, reference lines, and customization of chart dimensions.
dogfood
by vercel-labs
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
content-daily
by nabilakhannn
Primary LinkedIn content creation skill. Invoke for "give me today's content", "write me a LinkedIn post", "today's post", "content for this week", "generate my weekly posts", "post idea for me", "help me write a post", "I need content for [topic]", "batch this week's content". Runs a rigid 5-phase pipeline — Research → Topic Selection → POV Questions → Writing → Log. Cannot skip phases. Uses your voice card, the 7-layer Writing SOP, hook library, posts-log memory, and your positioning. Enforces anti-AI red-flag scan before output.