agentleFS
intent-driven-devintent-driven-dev/intent-driven-template/.agents/skills/glossary/SKILL.md

glossary

Skill185 starsChanged 32 days agoMITView on GitHub

Use when authoring or reviewing specs, requirements, design docs, ADRs, tasks, glossary entries, domain terms, technical terms, or wording consistency across artifacts

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use recap and review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • genomewalkerSkill

    recap

    Rebuild working context from transcripts and chitta memories in approximately 1500 tokens. Use when starting a new session to continue previous work.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 11 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use existing repository terms before creating new ones.

    line 8
  2. Very specific:

    Read glossary/business.md and/or glossary/technical.md when present.

    line 13
  3. Distinctive:

    If existing terms look close, ask the user whether to reuse one or define a new term.

    line 16
  4. Distinctive:

    Use the chosen term consistently in the artifact.

    line 17
  5. Distinctive:

    Add new terms to the appropriate glossary file.

    line 18
  6. Distinctive:

    Do not add generic dictionary words or one-off implementation details.

    line 21
  7. Distinctive:

    If a needed glossary file is missing, create it with this table:

    line 28
  8. Distinctive:

    Ask before creating a new term when existing terms may fit:

    line 39
  9. Distinctive:

    Do not proceed with a new term until the user answers, unless no plausible existing term exists.

    line 50
  10. Distinctive:

    Every authored or edited non-glossary artifact gets a companion file in the same directory.

    line 60
  11. Very specific:

    Do not create companion glossary reference files for glossary source files themselves, such as glossary/business.md or …

    line 62
  12. Distinctive:

    If no glossary terms are used, write:

    line 80
  13. Distinctive:

    Do not copy definitions into companion files.

    line 88

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “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

Glossary

Use existing repository terms before creating new ones.

Workflow

  1. Identify the artifact being authored or reviewed.
  2. Read glossary/business.md and/or glossary/technical.md when present.
  3. Extract project-specific, technical, overloaded, ambiguous, or repeated concepts.
  4. Compare extracted concepts with existing glossary terms.
  5. If existing terms look close, ask the user whether to reuse one or define a new term.
  6. Use the chosen term consistently in the artifact.
  7. Add new terms to the appropriate glossary file.
  8. For non-glossary artifacts, create or update the artifact's companion glossary reference document.

Do not add generic dictionary words or one-off implementation details.

Glossary Files

  • glossary/business.md: domain, product, workflow, and business terms.
  • glossary/technical.md: architecture, implementation, platform, and protocol terms.

If a needed glossary file is missing, create it with this table:

| Term | Definition | Use When | Avoid |
| --- | --- | --- | --- |

New entries use the same table format. Keep definitions to one concise sentence.

Close-Term Question

Ask before creating a new term when existing terms may fit:

These glossary terms look close to "<concept>":

- `<existing-term>`: <why it may fit>
- `<another-term>`: <why it may fit>

Do you want to use one of these existing terms, or define a new term?

Do not proceed with a new term until the user answers, unless no plausible existing term exists.

Marking Terms in Artifacts

In non-glossary artifacts, such as proposals, designs, specs, ADRs, and tasks, bold glossary terms that appear in the artifact's companion glossary reference.

Apply bolding in prose only. Do not bold terms in code blocks, frontmatter, links, or places where markdown formatting would make the artifact harder to read.

Companion Reference

Every authored or edited non-glossary artifact gets a companion file in the same directory.

Do not create companion glossary reference files for glossary source files themselves, such as glossary/business.md or glossary/technical.md.

Name: remove .md, then append -glossary-reference.md.

Examples: proposal-glossary-reference.md, design-glossary-reference.md, spec-glossary-reference.md, adr-glossary-reference.md, tasks-glossary-reference.md.

Format:

# Glossary Reference

| Term | Source Glossary | Context |
| --- | --- | --- |
| <Term> | `glossary/business.md` | <Short context for how the artifact uses this glossary term.> |

Source Glossary is the glossary file the term came from or was added to, such as glossary/business.md or glossary/technical.md.

If no glossary terms are used, write:

# Glossary Reference

No glossary terms referenced.

Do not copy definitions into companion files.

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.