agentleFS
Sign inStart free
Cogni-AI-OUCogni-AI-OU/cogni-ai-agent-skills/rfc2119/SKILL.md

rfc2119

Skill4 starsChanged 6 months agoMITView on GitHub

Enforce correct usage of RFC 2119 requirement level keywords (MUST, SHOULD, MAY, etc.) in documentation and specifications. You MUST load this skill when writing or reviewing standards, specifications, or when applying RFC 2119 terminology.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Absolute Requirements: Use MUST, REQUIRED, or SHALL only for absolute requirements of the specification.

    line 15
  2. Very specific:

    Absolute Prohibitions: Use MUST NOT or SHALL NOT only for absolute prohibitions.

    line 16
  3. Very specific:

    Strong Recommendations: Use SHOULD or RECOMMENDED when valid reasons exist to ignore an item, but the full implications must be understood …

    line 17
  4. Very specific:

    Weak Prohibitions: Use SHOULD NOT or NOT RECOMMENDED when a behavior is acceptable or useful in specific circumstances, but implications …

    line 18
  5. Very specific:

    Optional Features: Use MAY or OPTIONAL for truly optional items.

    line 19
  6. Distinctive:

    Capitalization: ALWAYS capitalize these keywords when used in their RFC 2119 context.

    line 20
  7. Distinctive:

    Sparseness: Use imperatives sparingly.

    line 21
  8. Distinctive:

    Capitalize: Ensure the chosen keyword is fully capitalized.

    line 27

≈ “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

Skill: rfc2119

<!-- markdownlint-disable MD013 MD023 MD031 MD032 -->

Enforce the standardized meaning of requirement level keywords as defined in BCP 14 (RFC 2119).

Core Principles

  • Absolute Requirements: Use MUST, REQUIRED, or SHALL only for absolute requirements of the specification.
  • Absolute Prohibitions: Use MUST NOT or SHALL NOT only for absolute prohibitions.
  • Strong Recommendations: Use SHOULD or RECOMMENDED when valid reasons exist to ignore an item, but the full implications must be understood and weighed.
  • Weak Prohibitions: Use SHOULD NOT or NOT RECOMMENDED when a behavior is acceptable or useful in specific circumstances, but implications must be weighed before implementation.
  • Optional Features: Use MAY or OPTIONAL for truly optional items. Implementations must interoperate regardless of feature presence.
  • Capitalization: ALWAYS capitalize these keywords when used in their RFC 2119 context.
  • Sparseness: Use imperatives sparingly. Limit usage to requirements necessary for interoperation or to prevent harm.

Core Process

  1. Identify Imperatives: Scan the text for requirement-level intent.
  2. Select Keyword: Map the intent to the exact RFC 2119 keyword.
  3. Capitalize: Ensure the chosen keyword is fully capitalized.
  4. Verify Necessity: Confirm the requirement is essential for interoperability or safety; if not, rephrase without RFC 2119 keywords.
  5. Security Context: Elaborate on the security implications of ignoring MUST, MUST NOT, SHOULD, or SHOULD NOT directives.

Limitations

  • These keywords apply strictly to technical specifications and standards; do not use them for general narrative or conversational text where their formal weight is unnecessary.

References

Related Skills

  • docs-writer: You MUST load this skill when generating new documentation that incorporates these specifications.

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.

Check your setup, free