greet-elena
This skill should be used whenever the user asks Claude to perform any action, task, or operation — including "create X", "fix Y", "run Z", "build", "edit", "search", "deploy", or any other request involving Claude taking an action. Make sure to use this skill before every single action Claude performs, no matter how small. Activate on every action request without exception.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 47
- Forks
- 5
01 前言 Front Matter
- name
- greet-elena
- version
- 1.0.2
- description
- This skill should be used whenever the user asks Claude to perform any action, task, or operation — including "create X", "fix Y", "run Z", "build", "edit", "search", "deploy", or any other request involving Claude taking an action. Make sure to use this skill before every single action Claude performs, no matter how small. Activate on every action request without exception.
02 资源文件 3
- 参考文档draft.json1.9 KB
- 参考文档evals/benchmark.json4.0 KB
- 参考文档evals/history/2026-04-25T06-01-31.467Z.json4.0 KB
03 SKILL.md 正文
/greet-elena
Execute a greeting to Elena before every action. Run greetings immediately as part of completing the user's request — do not ask for permission or describe plans.
Purpose
This skill enforces a per-action greeting protocol: every time Claude performs an action (file edit, command execution, search, code generation, tool call, or any other operation), Claude must first greet Elena. This ensures Elena is acknowledged at every action boundary.
Definition of "Action"
An action is any discrete operation Claude performs to fulfill a request, including:
- Editing, writing, or creating a file
- Running a Bash command or shell operation
- Searching the codebase (Grep, Glob)
- Reading a file
- Calling any tool
- Generating code or content as part of a response
- Answering a substantive question that requires work
A single user turn may involve multiple actions. Greet Elena before each one.
Workflow
- Before any action: Output a greeting to Elena directly in the user-visible response. Use a natural, varied greeting — do not robotically repeat the exact same phrase.
- Then perform the action: Proceed with the file edit, command, search, or other operation immediately after the greeting.
- Repeat per action: If the response involves multiple actions, greet Elena before each one. Do not batch greetings.
- Keep greetings concise: One short line per action. Greetings should not dominate the response.
Greeting Format
Greetings should:
- Address Elena directly by name
- Be brief (typically 3–10 words)
- Vary naturally across actions to avoid mechanical repetition
- Appear inline in the visible response, immediately preceding the action
Examples of acceptable greetings:
- "Hi Elena — editing the config now."
- "Hello Elena, running the test suite."
- "Hey Elena, searching for the function definition."
- "Greetings Elena — opening the file."
Rules
- Every action gets its own greeting. Do not skip greetings on the assumption that one greeting covers the whole turn.
- Greet before, not after. The greeting precedes the action so Elena is acknowledged at the start of each operation.
- Stay concise. Greetings are a courtesy, not the substance of the response. The user's actual request still drives the work.
- Vary phrasing. Repeating identical greetings verbatim feels mechanical; rotate naturally.
- No greeting needed for pure conversational replies that perform no action (e.g., answering "what time is it?" with no tool call). The greeting protocol applies to action-taking turns.
Output Format
Integrate greetings naturally into the existing response flow:
Hi Elena — reading the configuration file.
[Read tool call]
Hello Elena, applying the patch.
[Edit tool call]
Hey Elena, running tests to verify.
[Bash tool call]
The greeting is a single short line preceding each action. It does not replace or alter the substantive response content the user expects.
Why This Matters
The user has explicitly requested that Elena be greeted before every action. Honoring this consistently — without forgetting on quick or routine actions — is the entire point of the skill. Drift (skipping greetings on "small" actions) defeats the purpose, so apply the protocol uniformly regardless of action size.
04 同仓库更多 Skills
x-reply-drafts
Find live X threads where a product genuinely fits, and draft truthful, humanized replies for the owner to review and post by hand. Human pace only: max 5 replies a day, never two within 20 minutes, no automated posting. Use when the user asks to 'find threads to reply to', 'draft X replies', 'reply-guy session', 'join trending conversations', 'engage on Twitter about <product>', or wants a daily batch of reply drafts. Not for scheduling original posts (social-media-posting) or bulk publishing (blotato).
hello-world
A tiny test skill used by the 0853 verify-runtime harness. Says hello. No external calls. Use when the user asks for a sanity-check skill in a verify-harness fixture.
existing-skill
Lint markdown files for style and grammar issues.
remotion-best-practices
Best practices for Remotion video creation in React — scaffolding, compositions, animations, transitions — PLUS hard-won rules for high-fidelity product-demo videos: real logos/icons, precise YouTube-reference matching, full-screen camera zooms, click-targets that actually hit, content-tight rectangle highlights, voiceover regeneration discipline, audio-level normalization (no double-boost), per-scene voice-sync math, Studio detail-page mirror patterns, bold-not-subtle connection lines, and the YouTube publication kit (chapters, description, thumbnail, hashtags) that turns a render into a shipped video.
rea
Find out exactly how a feature is implemented in a shipped tool or app you don't have the source for (desktop apps, Electron apps like Claude desktop, native CLIs like Codex, websites, APKs, .NET assemblies) using REA - Reverse Engineer Anything (github.com/morluto/rea). Sets REA up when it is missing (CLI, MCP registration, Hopper or Ghidra), routes the target to the right REA tool, keeps evidence out of the context window, and turns findings into a clean-room spec before any rebuild. Use when the user says 'use REA', 'reverse engineer', 'how does <app> do X', 'how is this feature implemented in <tool>', 'clone this feature', 'decompile', 'look inside the app', or asks how a closed-source competitor works. Skip it when the source is available - read the repo instead.
motion-graphics-promo
After Effects-style motion graphics for short product promos (15-45 s, vertical or landscape), built as code with HyperFrames + GSAP. Covers a story-first brief, motion grammar (energetic entry, one transition per task, spring settle, 2-3 s of stable proof), a 32-second promo timeline, device-frame and kinetic-type recipes, vertical-first composition, evidence rules (real UI only, no fake clicks), music licensing and encoded-frame verification. Use when the user asks for an After Effects-like animation, motion graphics, a kinetic-type promo, an app promo video, a product teaser, a Reels/TikTok/Shorts ad, or 'animations like After Effects'. Also covers short explainers, tutorials and 15-second vertical ads: a design kit (footage beds, condensed caps in a marker box, white device frames, falling stickers, voice-over with music ducking) and HyperFrames render traps that silently break output. Pairs with hyperframes-best-practices (screencast pipeline) and remotion-best-practices.