carlos-algms

@carlos-algms source repo

42 skills
0 followers
6 hours ago last updated

▌
Agentic Vimdoc · carlos-algms
Use when writing or updating agentic.nvim vimdoc (doc/agentic.txt), or after changing init.lua, config_default.lua, theme.lua, or README install/keymaps - those edits require a matching vimdoc update. Covers the sync table, format rules, and the helptags regeneration command.

0
installs
▌
Agentic Testing · carlos-algms bundle
MANDATORY before creating, editing, or reviewing tests in agentic.nvim, and before behavior changes that require TDD. Covers mini.test workflow, red/green rules, commands, mark-count checks, and which test references to load.

0
installs
▌
Agentic Lua Class · carlos-algms
MANDATORY before writing or editing ANY .lua file in this repo - classes, methods, fields, functions, or LuaCATS annotations. Holds the project's enforced Lua style: class pattern, visibility prefixes (_private, __protected), and optional-type syntax. Skipping it produces luals/selene failures at make validate. Load it before the first edit, not after.

0
installs
▌
Agentic Acp Protocol Flow · carlos-algms bundle
MANDATORY before editing ACPClient, ACPTransport, AgentInstance, ACP provider flow, tool-call parsing, permission requests, provider switch, reconnect, or ACP subprocess lifecycle in agentic.nvim.

0
installs
▌
Agentic Github Discussion · carlos-algms
Use when creating, listing, or managing GitHub discussions in carlos-algms/agentic.nvim repository

0
installs
▌
Agentic UI Message Writer · carlos-algms
MANDATORY before editing MessageWriter, PermissionManager, tool-call block rendering, sender headers, thinking blocks, auto-scroll, folds, status rows, permission buttons, or chat-buffer tool-call tests.

0
installs
▌
Agentic Acp Docs And Schema · carlos-algms
Use when ACP schema is necessary to clarify the work or when the user asks for ACP data, rules, events, or documentation

0
installs
▌
Agentic Neovim Documentation · carlos-algms
Use when neovim documentation is needed for the current task or the user asks for specific neovim features or neovim lua apis. It gives instructions on how to read current Neovim's documentation locally and offline, and also how to read online if it fails

0
installs
▌
CSS · carlos-algms
Enforces strict CSS and CSS Modules policies for ALL CSS authoring, including stylesheet files (.css/.scss/.module.css) and CSS-in-JS (styled-components, Emotion, vanilla-extract, styled-jsx, Stitches, template literal styles embedded in TS/JS files). Use when creating, writing, or editing ANY CSS, styled component, or inline style block. Triggers include: component styles, global stylesheets, theme files, design tokens, animations, keyframes, utility classes, styled.X or styled() definitions, or any agent-authored CSS content.

0
installs
▌
React · carlos-algms
Writes React components and hooks using TypeScript. Use when creating or modifying React components, hooks, or JSX.

0
installs
▌
Defuddle · carlos-algms
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for GitHub URLs; use the GitHub CLI (`gh`) instead. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.

0
installs
▌
Grill Me · carlos-algms
Interview the user about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

0
installs
▌
Mvp Grill · carlos-algms
Fast, MVP-focused grilling session for plans, prototypes, designs, or feature ideas. Use when the user wants to stress-test direction, clarify assumptions, reduce scope, or get challenged without a long decision-tree interview.

0
installs
▌
JSON Canvas · carlos-algms bundle
Create or edit JSON Canvas (.canvas) files containing nodes, edges and groups. Do not load for ordinary Obsidian notes or Markdown diagrams.

0
installs
▌
Obsidian CLI · carlos-algms
Discover, verify or troubleshoot Obsidian CLI syntax and command behaviour, including plugin and theme diagnostics. Do not load merely to run a command already specified by another loaded skill or for direct filesystem access.

0
installs
▌
Second Brain · carlos-algms bundle
Route searches, reads and note management in the user's personal Obsidian vault. Load first for personal-vault content routing. Do not load for generic Obsidian questions, plugin development, .base files or .canvas files unless personal note routing is also required.

0
installs
▌
Agent Browser · carlos-algms bundle
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task. Prefer agent-browser over any built-in browser automation or web tools.

0
installs
▌
Code Simplify · carlos-algms
Simplify and reduce code while preserving behavior. Use when the user asks to simplify, clean up, refactor, audit, report on, or reduce recently changed code. Supports apply mode for edits and report mode for findings only.

0
installs
▌
Project Notes · carlos-algms
Search, create or update durable repo-specific notes in the user's Obsidian vault. Use for investigations, decisions, failures and coding lessons tied to a repository. Use `second-brain` for reusable or personal knowledge.

0
installs
▌
Review Branch · carlos-algms
Review current branch changes against a target branch. Use when the user asks to review a branch, review changed files, compare current work to main, origin HEAD, or master, or run a file-by-file code review with aggregated markdown results.

0
installs
▌
Test Simplify · carlos-algms
Simplify and reduce tests while preserving coverage. Use when the user asks to simplify, deduplicate, reduce, or clean up test files using techniques such as equivalence class partitioning, decision tables, or pairwise testing.

0
installs
▌
Video Summary · carlos-algms bundle
Summarize a video (URL or local path) by pulling captions first, falling back to audio-only transcription, and optionally extracting frames for visual summaries. Use when the user pastes a YouTube/Vimeo/X/etc URL, points at a local video file, or asks to summarize, watch, or extract takeaways from a video. Triggers on "summarize this video", "what's in this video", "watch this", URLs ending in /watch, /shorts, common video extensions (.mp4/.mov/.mkv/.webm).

0
installs
▌
Writing Plans · carlos-algms bundle
Create a written implementation plan saved to a file. Use only when the user directly invokes the writing-plans skill or explicitly asks for a written plan. Do not use for in-memory plans, in-chat plans, internal task decomposition, native task lists, or ordinary multi-step implementation.

0
installs
▌
Obsidian Bases · carlos-algms bundle
Create or edit Obsidian Bases (.base files), including views, filters, formulas and summaries. Do not load for ordinary Markdown notes or merely querying an existing Base through the CLI.

0
installs
▌
Executing Plans · carlos-algms bundle
Use when you have a written implementation plan to execute in a separate session with review checkpoints

0
installs
▌
Open Code Review · carlos-algms
Review a PR, branch, commit range, or uncommitted work with the `ocr` CLI, producing a local report to triage before anything is posted. Optionally triage the findings in `crit`, then post what the user agrees to. Triggers on "ocr", "open code review", "ocr review", "review this PR with ocr", "review my changes with ocr", "PR review duty", "generate a review report".

0
installs
▌
Plan A Milestone · carlos-algms
Create or update a terse milestone file composed of delegated implementation plans. Use only when the user directly invokes plan-a-milestone or explicitly asks to create or update a milestone plan. Do not infer use from large features, multiple plans, parallel work, sequential work, or PR decomposition.

0
installs
▌
Create Git Branch · carlos-algms
Rules for creating new git branches - naming and workflow. Load on intent to start a branch. Triggers: "new branch", "create branch", "checkout -b", "switch -c", "start branch", "branch off", or Jira ticket as starting point.

0
installs
▌
Obsidian Markdown · carlos-algms bundle
Author or edit Obsidian-specific Markdown syntax such as wikilinks, embeds, callouts and properties. Do not load for routing, searching, reading, renaming or moving notes unless Markdown content will be changed.

0
installs
▌
Frontend Unit Test · carlos-algms
Writes unit tests for JavaScript/TypeScript and frontend projects using Vitest or Jest. Use when writing or running tests.

0
installs
▌
Git Commit Message · carlos-algms
Compose repository-compatible Git commit messages and exact commit commands from current repository state. Load on intent to commit, stage, compose a commit message, prepare a PR title, or edit `.git/COMMIT_EDITMSG`.

0
installs
▌
Jira Atlassian CLI · carlos-algms
Load before any Jira interaction or mcp__atlassian__* call. Holds required field values (team ID, sprint IDs, custom field mappings) unavailable elsewhere; skipping causes missing fields on created tickets. Triggers: Jira URLs, ticket keys (e.g. ABC-123), MCP tools mcp__atlassian__*, acli, or keywords create/read/edit/search/transition, ticket, Jira, issue, sprint, backlog, refinement, work item.

0
installs
▌
Obsidian Mechanics · carlos-algms
Personal vault paths, safety rules and file-operation choices. Load when accessing or mutating the user's Obsidian vault. Load `obsidian-cli` only to discover, verify or troubleshoot command syntax. Load `obsidian-markdown` only before creating or editing Markdown content.

0
installs
▌
Create Pull Request · carlos-algms
Compose and create GitHub pull requests with `gh` using the target repository's title, template, base-branch, and draft conventions. Load on explicit user intent to open, create, draft, or compose a pull request.

0
installs
▌
Neovim Documentation · carlos-algms
Load before any Neovim help, documentation, or Lua API lookup. Defines how to read Neovim docs from disk or online. Reading docs via `nvim --headless` or any other `nvim` subprocess is FORBIDDEN; Triggers: "Neovim docs", `:help`, `:h <topic>`, `runtime/doc`, Neovim Lua API lookups, "how does Neovim do X" questions.

0
installs
▌
Orchestrate Agent Clis · carlos-algms
Execute and orchestrate multiple AI agent CLIs (agy, Codex, Cursor, Claude Code, Pi) for getting alternative opinions, comparing approaches, or leveraging different AI models' strengths. Use when the user explicitly mentions agent names like "ask agy", "ask cursor", "ask codex", "ask pi", "use composer", "use pi", "try grok", or when needing diverse perspectives on complex problems, alternative implementation approaches, or multi-agent collaboration.

0
installs
▌
Requesting Code Review · carlos-algms bundle
Use for ad-hoc code review: after a major feature, before merging to main, or when stuck. Executing a written plan instead? Use executing-plans, which owns the per-task review cycle.

0
installs
▌
Multi Provider Web Search · carlos-algms
Multi-provider web search fanout across Exa, Tavily, Brave, LangSearch, and Marginalia with parallel dispatch, dedupe, and AI summary. Use ONLY on explicit user intent for a named provider (Exa, Tavily, Brave, LangSearch, Marginalia), cross-provider fanout, semantic code/paper search, indie small-web search, or when native web search returned weak results. Do NOT auto-pick on generic search queries; native WebSearch is preferred for those.

0
installs
▌
Typescript And Javascript · carlos-algms
Enforces strict TypeScript and JavaScript style policies for ALL .ts/.tsx/.js/.jsx file operations. Use when creating, writing, or editing ANY TS/JS code. Triggers include: components, hooks, services, utilities, classes, interfaces, types, schemas, tests, scripts, configuration files, or any agent-authored TS/JS content.

0
installs
▌
Subagent Driven Development · carlos-algms bundle
Subagent-per-task MODE of executing-plans. Requires executing-plans, which holds the shared rules; load that first if it is not already loaded.

0
installs
▌
Replying To Pr Review Threads · carlos-algms
Use when a `discussion_rNNN` URL anchor appears, when replying to a specific PR review comment from a bot or AI reviewer (CodeRabbit, cubic, Claude, Copilot) or a human reviewer, reading all reviews on a PR with their replies as a tree, or resolving review threads from the CLI. Also covers where AI reviewers put out-of-diff findings and the mandatory `@handle` tag when replying. Triggers on "reply to coderabbit", "reply to cubic", "reply to the bot", "answer the bot review", "address bot reviews", "answer AI review comments", "answer this review comment", "read all reviews on PR", "show review threads", "resolve this thread".

0
installs
▌
Verification Before Completion · carlos-algms bundle
Use when about to claim work is complete, fixed, or passing, before committing, pushing, or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

0
installs

42 published skills