greet-elena
Skill48 starsChanged 6 months agoMITView on GitHub
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.
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Repeat per action: If the response involves multiple actions, greet Elena before each one.
- Distinctive: line 51
Every action gets its own greeting: Do not skip greetings on the assumption that one greeting covers the whole turn.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/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.
In this repository30 other files it gives its agents.
- obsidian-brainSkill
- animejsSkill
- css-animationsSkill
- greet-anton-abyzovSkill
- gsapSkill
- higgsfield-seedanceSkill
- hyperframes-cliSkill
- hyperframes-mediaSkill
- hyperframes-registrySkill
- hyperframesSkill
- lottieSkill
- obsidian-brainSkill
- private-skillSkill
- remotion-to-hyperframesSkill
- scoutSkill
- slack-messagingSkill
- stub-skill-76f6713eSkill
- tailwindSkill
- threeSkill
- waapiSkill
- website-to-hyperframesSkill
- excalidraw-mcpSkill
- greet-anton-abyzovSkill
- handoffSkill
- hi-atlantisSkill
- html-reportSkill
- hyperframes-best-practicesSkill
- motion-graphics-promoSkill
- reaSkill
- remotion-best-practicesSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

