agentleFS
D-SheyD-Shey/autoharness/.agents/skills/mode-classification/SKILL.md

mode-classification

Skill10 starsChanged todayMITView on GitHub

Attribute catalog capability triggers between task prompt and user message in CLI mode raising

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when explaining why a task mode was raised from light to full, identifying trigger keywords, or attributing matched capability terms to …

    line 10
  2. Distinctive:

    Check if the word is in the task text (case-insensitive substring or token match).

    line 16
  3. Distinctive:

    Check if the word is in the user message (case-insensitive substring or token match).

    line 17
  4. Distinctive:

    If the user message is empty or the word does not appear in the user message, do not attribute it to "the user's message".

    line 18
  5. Distinctive:

    Run unit tests verifying that keywords in task text are credited to "the task text", keywords in user message are credited to "the user's …

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Mode classification and word attribution

When to use

Use when explaining why a task mode was raised from light to full, identifying trigger keywords, or attributing matched capability terms to either the task prompt or the user's conversation prompt.

Steps

  1. Classify the combined task prompt and user message together (catalog.classify(about)).
  2. For each capability and its matched trigger words, check where each word appears:
    • Check if the word is in the task text (case-insensitive substring or token match).
    • Check if the word is in the user message (case-insensitive substring or token match).
  3. If the user message is empty or the word does not appear in the user message, do not attribute it to "the user's message".
  4. Group words by their actual source: "the task text" or "the user's message". If a word appears in both, default to "the task text".
  5. Format the diagnostic explanation clearly with capability names and source tags.

How to verify

Run unit tests verifying that keywords in task text are credited to "the task text", keywords in user message are credited to "the user's message", and absent user message never receives attributed words.

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.