agentleFS
InjectiveLabsInjectiveLabs/agent-skills/skills/injective-docs-style/SKILL.md

injective-docs-style

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Audit and report adherence to Injective's documentation standards

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When writing developer documentation for Injective

    line 21
  2. Distinctive:

    When writing developer documentation adhering to Injective's developer documentation standards

    line 22
  3. Distinctive:

    Always run: "Check documentation style"

    line 26
  4. Distinctive:

    Only run if explicitly requested: "Verify technical correctness"

    line 27
  5. Distinctive:

    Use this to validate technical correctness of all pages that were checked in the previous step "Check documentation style".

    line 37
  6. Distinctive:

    Start with the report file output in the "Check documentation style" step

    line 62
  7. Distinctive:

    Write file to disk with the same filename

    line 65
  8. Very specific:

    Use the injective-mcp-servers skill to connect to the Injective Documentation MCP.

    line 72
  9. Distinctive:

    Use this to check for correctness of any technical terminology that is Injective-specific.

    line 75
  10. Distinctive:

    If these skills are not available, selectively run the following commands to install them:

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Injective Documentation Style, Skill Guide

Injective provides extensive developer documentation that is available on https://docs.injective.network (for humans) and https://docs.injective.network/llms.txt (for robots). This skill is to assist authors working on Injective's developer documentation.

When to apply

  • When writing developer documentation for Injective
  • When writing developer documentation adhering to Injective's developer documentation standards

Activities

  • Always run: "Check documentation style"
  • Only run if explicitly requested: "Verify technical correctness"

1 - Check documentation style

Invoke the "devrel-docs-style" skill, and specify use of American English.

2 - Verify technical correctness

Invoke the "injective-mcp-servers" skill, and connect to the Injective Documentation MCP server.

Use this to validate technical correctness of all pages that were checked in the previous step "Check documentation style". Do so by:

  • Make a list of claims, based on the contents of the files
    • Identify any new claims made
    • Identify any existing claims modified or removed
  • For each claim, based on the Injective Documentation MCP server.
    • Find supporting evidence
    • Find contradicting evidence

Based on this, create a list of all the claims, for each claim:

  • short description: 6 to 12 words
  • quote: text of each claim made, verbatim, as found in file
  • location: file path relative to project dir, and a single line number or range of line numbers, e.g. ./foo/bar.md:123-125
  • likelihood of correctness:
    • at least 80% sure claim is correct -> "Likely correct"
    • less than 80% sure claim is correct -> "Maybe correct"
    • less than 80% sure claim is wrong -> "Maybe wrong"
    • at least 80% sure claim is wrong -> "Likely wrong"
  • rationale: reason for chosen likelihood of correctness

Use format: ./assets/claims-template.md

3 - Assemble report

  • Start with the report file output in the "Check documentation style" step
  • Append the result from the "Verify technical correctness" step
    • The "## Claims" section should be inserted right above the "## Reproducing this report" section
  • Write file to disk with the same filename

Related skills

  • devrel-docs-style
  • injective-mcp-servers

Use the injective-mcp-servers skill to connect to the Injective Documentation MCP.

Through this you may search/ consult existing Injective developer documentation. Use this to check for correctness of any technical terminology that is Injective-specific.

If these skills are not available, selectively run the following commands to install them:

npx skills add bguiz/devrel-agent-skills --skill devrel-docs-style
npx skills add InjectiveLabs/agent-skills --skill injective-mcp-servers

Prerequisites

  • Injective MCP server must be running
  • User prompts should be issued from an AI tool that is configured to talk to the Injective MCP server

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.