agentsclimarketplace

Skill

Skill noodlebindev/claude-skills-monorepo/templates/skill

Use when the user asks to <REPLACE WITH TRIGGER>. Phrases like "<REPLACE>", "<REPLACE>". Do not use for <REPLACE WITH ANTI-TRIGGER>.From its SKILL.md

Install
npx -y skills add noodlebindev/claude-skills-monorepo --skill skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, 411 tokens by cl100k_base, as published. Nobody here has run it

{{SKILL_NAME}}

<One-sentence statement of what this skill does. Loaded at activation time, so keep the whole body tight.>

When to use this skill

<Specific trigger conditions. The agent reads this to decide whether the activation was correct.>
  • When the user says "<example phrase>"
  • When the user is working in <context> and asks for <thing>
  • When <specific condition>

When NOT to use this skill

<Anti-triggers — situations where this skill should hand off to another, or do nothing.>

  • When the user wants <adjacent-but-different thing> — use <other skill> instead
  • When <condition that looks similar but isn't>

What this skill does

<Step-by-step procedure. Numbered. Imperative voice ("Read the file", not "The agent reads the file").>

  1. <Step one>
  2. <Step two>
  3. <Step three>

Inputs

<What the agent needs to gather from the user or environment before running the procedure.>
  • <Input 1> — <where it comes from>
  • <Input 2> — <validation rules>

Outputs

<What the agent produces. Be precise — formats, file locations, follow-up actions.>

  • <Output 1>
  • <Output 2>

Example

User says:

<Realistic user prompt>

Agent does:

  1. <Action>
  2. <Action>
  3. <Action>

Result:

<Expected output>

References

For deeper material, see:

  • references/<topic>.md — <what's in it>

Constraints

  • <Hard limit, e.g., max file size, max API calls>
  • <Behavioural limit, e.g., never overwrites without confirmation>

Failure modes

If <condition>, the skill should: <what to do>.

If <condition>, the skill should refuse and say: "<exact message>".

What ships with it: 6 files

2.9 KB alongside SKILL.md

examples/

scripts/

tests/

Keep looking

Skills are one crate of 326,367. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.