agentsclimarketplace

Template

Skill sordi-ai/skill-everything/skills/_template

Git-versioned agent memory: agents that never make the same mistake twice. Anthropic-Skill folder standard, multi-runtime (Claude Code, Cursor, Gemini CLI, OpenCode).

Install
npx -y skills add sordi-ai/skill-everything --skill _template

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

  • 17 stars17 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 author says it does

Copied from the file, not written here

<one-sentence trigger condition — when should this skill be loaded? Start with "Apply when ..." for consistency.>

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

1.6 KB, as published. Nobody here has run it

Sub-Skill: [Name]

<!-- target: tokens_target above. Run `python tools/render_readme_table.py` to update README. -->

Purpose: [1-2 sentences. What this sub-skill does and why it exists.]


Rules

[Category 1]

  1. [Rule name]. [Action directive — must start with Always, Never, Before, After, Prefer, Avoid, Use, Do, or Ensure.]
  2. [Rule name]. [Action directive.] Reference: ERR-YYYY-NNN
  3. [Rule name]. [Action directive.]

[Category 2]

  1. [Rule name]. [Action directive.]
  2. [Rule name]. [Action directive.]

See also

  • skills/code-quality/SKILL.md (when this skill specialises a generic rule, link to it)
  • skills/error-log/SKILL.md (errors that motivated rules in this skill)

Notes

  • Frontmatter is mandatory. The CI validator (tools/validate_rules.py) will fail any sub-skill without a valid frontmatter against schemas/skill-manifest.json.
  • Action directives, not descriptions. "SQL injection is dangerous" is a description; "Never concatenate user input directly into SQL queries; always use prepared statements" is an action directive.
  • Reference: ERR-YYYY-NNN on every rule born out of a real observed mistake.
  • Token budget under 3000. When exceeded, split into thematic sub-skills with loads_after chains.

Keep looking

Skills are one crate of 328,083. 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.