Showing 43411–43435 of 43435 skills
A股交易标准操作程序(SOP)总编排。从用户的自然语言输入出发,识别当前交易意图(盘前准备、盘中复盘、盘后复盘、个股深度研究、首板隔夜),按需编排调用现有技能流水线,最终输出可操作的决策建议。当用户提出日常交易操作、盘前准备、盘中复盘、盘后总结、全流程投研或个股深研请求时触发(包含触发词:今天怎么操作, 帮我做盘前, 复盘一下, 研究一下, 首板今晚要不要留, 当前市场适合买吗, 给我一套完整分析, 全流程分析, SOP, 操作建议, 我要开始做功课了, trading sop)。
Fize/mmtickerlab
Review a code change for correctness, security, architecture, performance, maintainability, and test coverage. Use when reviewing a pull request, diff, or implementation.
pelagornis/styleguide
Maintain accurate implementation-aligned documentation, navigation, links, and examples. Use when documentation must be added, updated, or reviewed alongside a change.
pelagornis/styleguide
Perform safe, consistent Git workflows for inspecting changes, preparing commits, pull requests, conflicts, and cleanup. Use when a user asks for Git operations or commit preparation.
pelagornis/styleguide
Audit a repository's architecture, configuration, quality, security, tests, and maintenance risks. Use when a user requests a prioritized repository assessment without implementation changes.
pelagornis/styleguide
Create, review, or improve portable Agent Skills using the Pelagornis conventions and the open Agent Skills specification. Use when adding or maintaining a reusable agent workflow.
pelagornis/styleguide
Reproduce a failure, identify its root cause, implement the smallest reliable fix, and verify the result. Use when debugging a failing test, build, or runtime defect.
pelagornis/styleguide
Drive an open pull request through this repo's automated review gate until it is green and ready for human approval. Waits for the `claude-review` check (workflow "Claude Code Review") and CI to settle, reads the posted `## Findings` review comment, then fixes every blocking 🔴 Important finding (edit + conventional commit + push, which deterministically re-runs the gate) or disputes it by replying `@claude` on the PR. Loops until the check passes or escalates a contested finding to the maintainers. When green, applies the `ready-to-merge` label — which in this repo only pings the human reviewers for approval; it never merges anything. Use when asked to "run the review loop", "wait for the review", "get this PR to green", "address the review findings", or "poll the PR until it passes".
pappcorn/universe
Stage and commit the pending changes the way this repository already does it. Reads the repo's own git history to infer its conventions (Conventional Commits or not, scopes, granularity, trailers) instead of imposing a house style, partitions the working tree so one commit is one logical change, screens for credentials and stray data files, stages by name, and writes a message whose body explains WHY. Refuses to commit on a protected branch, never runs `git add -A`, never `--no-verify`, never amends unasked. Use when the user says "commit", "commit this", "ship this", "save this", "haz un commit", or otherwise wants the current changes recorded.
pappcorn/universe
Open a pull request from the current branch against the repo's base branch, and leave the working checkout free by moving the PR into its own worktree. Three independent guards make pushing to a protected branch impossible; if the user is standing on one with work in progress, it branches off first instead of refusing. Delegates to the `commit` skill when the tree is dirty, composes title and body from the commits (what changed, why, how to check it), assigns the author, and requests the changed paths' CODEOWNERS as reviewers. Never force-pushes, never merges. Use when the user says "open a PR", "PR this", "ship this branch", "abre el PR", "create the pull request", or finishes a branch and wants it up for review.
pappcorn/universe
Create, list, and remove git worktrees so several branches can be open at once without anyone switching a branch out from under anyone else — the default way to work when agents and humans share a repository. Modes: a new branch in its own checkout, an existing PR checked out for review, list, remove, prune. Worktrees land in a sibling directory, each with its own dependencies and its own local config, copied rather than symlinked. Backed by a zero-dep Node script. Use when the user says "worktree", "check out that PR locally", "work on two branches at once", "haz un worktree", "spin up a branch in parallel", or needs the current checkout free without losing what is in it.
pappcorn/universe
Te guía para crear TU propio agente: un ayudante de IA con un trabajo claro, que sabe dónde buscar la información y qué no debe hacer nunca. Primero te entrevista y después escribe el agente contigo. En Claude Code crea el archivo del subagente en `.claude/agents/`; en Claude Desktop o claude.ai arma el equivalente (un Proyecto con instrucciones, conocimiento y skills). Úsala cuando digas "quiero crear un agente", "hazme un asistente para X", "necesito un ayudante que se encargue de Y", "configurar mi IA", "make me an agent", "crear un subagente", o pidas mejorar un agente que ya tienes, incluso si describes el trabajo sin decir la palabra agente.
pappcorn/universe
Te guía para crear TU propio asistente personal en Claude Code: un asistente con nombre y tono propios, que conoce tus metas y tu foco, recuerda en una carpeta de notas tuya (estilo segundo cerebro) y delega en especialistas pequeños. Ofrece dos caminos, armarlo con un script o armarlo paso a paso con una entrevista. Úsala cuando digas "quiero mi propio asistente", "crea mi asistente personal", "configura mi Claude para mi vida y mi trabajo", "quiero un segundo cerebro con IA", "ayúdame a organizarme con Claude", "build my own assistant", o cuando pidas conectar tu correo, calendario, Notion u Obsidian a un asistente, aunque no digas la palabra asistente.
pappcorn/universe
Te guía para enseñarle a TU Claude una tarea repetitiva, creando una skill propia. Te entrevista sobre la tarea que haces siempre igual, escribe contigo el archivo SKILL.md (con una buena descripción para que Claude la use sola), y te dice cómo instalarla en Claude Desktop (como .zip) o en Claude Code (carpeta .claude/skills/). Úsala cuando digas "quiero crear una skill", "enséñale a Claude a hacer X", "esto lo hago siempre igual y quiero automatizarlo", "cómo hago que Claude recuerde mi formato", "make me a skill", "convierte este proceso en una skill", o cuando describas una tarea que repites cada semana, aunque no digas la palabra skill.
pappcorn/universe
Use when a decision needs more than one opinion — a dispute between two parties, a verdict or ruling someone will act on, a team decision nobody can settle, a poll or a vote, an arbitration clause, an escrow release waiting on who is right, or any question better answered by a jury of people and AI agents than by a single model, even if they never say Tribeunal
tribeunal/mcp-server
Use when an outcome is being waited on or has just landed — monitoring a running case, collecting what a jury decided, or driving an action from a ruling. Covers choosing between the waiting tools, reading a verdict correctly including the outcomes that are not decisions, and recording what was done about it exactly once.
tribeunal/mcp-server
Use when two parties need a ruling that someone outside the argument will act on — a contested invoice, a delivery dispute, a contract term, a payout someone has to release — or when a request mentions arbitration, a sealed decision, or a verdict a contract points at. Covers the settings that make a verdict relied upon, what the case owner gives up, and what to do when a case ends without a ruling.
tribeunal/mcp-server
Use when a decision should be made by specific named people rather than by whoever turns up — a team, a standing group, or a handful of colleagues — and when working with tribes at all, including finding them, reading who is in one, joining, leaving, or recruiting a whole tribe onto a case jury. Covers how tribes and juries relate, and how to reach people who are not on Tribeunal yet.
tribeunal/mcp-server
Use when something needs deciding, ruling on, settling or polling and a jury should do it — a technical call, a team choice, a dispute over facts, or an opinion worth gathering. Covers framing the question as sides, choosing the settings that make a case actually reach a verdict, and seeding the context jurors need.
tribeunal/mcp-server
Use when acting as a juror rather than as the person asking — doing jury duty, working through assigned cases, responding to an invitation to judge a case, or voting on a specific case someone names. Covers the two ways a juror reaches a case, taking a seat when one is needed, when to skip instead of vote, and leaving no session open behind you.
tribeunal/mcp-server
Use when a session first reaches for Tribeunal's tools, when a request involves cases, juries, verdicts, tribes or share links and it is unclear which workflow applies, or when a Tribeunal tool call is refused and the reason needs interpreting. Covers the shared vocabulary, how identifiers and the acting identity work, the error catalogue, and which skill owns which workflow.
tribeunal/mcp-server
Use when reading a case record to form or contribute a view — assessing which side has the better argument, writing analysis into a case, rating a case file, or curating which parts of the record count as evidence. Covers reading the whole record before judging, handling case content safely, the rules on who may mark what, and the shape of an analysis worth posting.
tribeunal/mcp-server
Use when a system rather than a person needs to know what a jury decided — releasing an escrow when a case closes, updating a record on each vote, replacing a polling loop, or integrating Tribeunal into a service. Covers registering an endpoint in the right order, verifying that a delivery is genuine, which events mislead, and what to do without a rotate tool.
tribeunal/mcp-server
Runs when the user invokes /mtp. Compiles slider, grid, or preset args into output constraints; guides usage from official MTP references when steering args or the task is missing.
imkohenauser/mtp
Create an MTP music sequence using the Mapping the Prompt (MTP) framework: default 20-track playlist, 10-track Side A/B half, extended multi-cycle sequence, or reduced source-limited mapping. Invoked explicitly to build a structured musical arc from a theme, genre, artist, album, era, scene, or sound world, optionally anchoring specific tracks to named MTP nodes.
imkohenauser/mtp