Files
openprose__prose/packages/std/roles/classifier.md
irl-dan 63c8ce4b23 Migrate std and co into packages/ monorepo layout
Move the standard library (previously `github.com/openprose/std`) and
the company-as-prose library (previously local dir
`/Users/sl/code/openprose/company-as-prose`) into this repository
under `packages/std/` and `packages/co/` respectively.

Motivation: concentrate attention on one repository so stars,
discussions, and issues aggregate. `openprose/std` was a genuinely
useful asset nobody could find because ~50 stars on its own repo
told a much worse story than 1,106 stars on `openprose/prose`
would have. Same logic applies to co.

Layout choice: `packages/{std,co}/` rather than `std/` + `co/` at
the repo root. Root siblings accumulate over time, and a flat
top-level made future libraries (hub, kit, dev, etc.) compete with
spec infrastructure. `packages/` is bounded — new libraries land
there without cluttering root. Matches pnpm/Deno/monorepo tooling
conventions.

Changes:

- New: `packages/std/` (copied from openprose/std, `.git` excluded)
- New: `packages/co/` (copied from company-as-prose, README updated
  for new name and location)
- `packages/std/README.md`: updated shorthand expansion reference
- `packages/co/README.md`: renamed "company-as-prose" to "co" in
  self-references, added std-vs-co split heuristic, updated
  `prose run` examples to use `co/` shorthand
- `skills/open-prose/deps.md`:
  - `std/` shorthand now expands to
    `github.com/openprose/prose/packages/std/`
  - `co/` shorthand added, expands to
    `github.com/openprose/prose/packages/co/`
  - Both shorthands resolve into the same clone of
    `openprose/prose` under `.deps/github.com/openprose/prose/`;
    `packages/std/` and `packages/co/` are sibling subdirectories
  - `prose.lock` format row updated to `host/owner/repo sha`
    (matches the explicit-host resolution that landed in #35)
  - `.deps/` directory structure example redrawn to show the
    `{host}/{owner}/{repo}/packages/{std,co}/...` shape
  - Error message and Interaction tables refreshed accordingly
  - Resolution Algorithm step 1 now documents both shorthands
- `skills/open-prose/forme.md`: Step 2 resolution list updated to
  include co/ shorthand and the host-keyed `.deps/` layout
- `skills/open-prose/help.md`: Q&A "How do dependencies work?"
  rewritten to name both shorthands and the new explicit-host model
- `skills/open-prose/state/filesystem.md`: `.deps/` directory
  tree re-drawn to include the `{host}/` layer with std/co as
  sibling packages inside the clone
- `skills/open-prose/guidance/patterns.md`,
  `skills/open-prose/guidance/antipatterns.md`: examples now use
  the `std/` shorthand or explicit `github.com/...` rather than
  the deprecated bare `openprose/std/` form
- `skills/open-prose/examples/registry-import/index.md`: sample
  service reference switched to `std/evals/inspector`
- `README.md`: Stdlib badge replaced with internal `packages/std/`
  link plus new `packages/co/` link; "Standard Library" section
  rewritten as "Libraries" with both packages described

Out of scope for this PR (deliberately):
- Tooling changes to `prose install` and Forme's `.deps/` writer
  to adopt the `{host}/{owner}/{repo}/` layout in practice — this
  PR is spec-only. Existing tooling continues to work against
  whatever layout it currently implements; the spec now describes
  the target.
- Retiring the `openprose/std` GitHub repo. Delete that repo
  separately after this merges.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-21 14:14:31 -07:00

2.1 KiB

name, kind
name kind
classifier service

Classifier

Assign a structured category label to an input item given a set of categories with descriptions. Use classifier when the task is labeling or categorization against a known taxonomy. Distinct from router (which selects a handler to delegate to) -- classifier produces a label, not a delegation decision.

Description

Assign a category label to an input given a defined category set.

Metadata

  • version: 0.1.0

Requires

  • item: the thing to classify
  • categories: the category set, each with a description of what belongs in it
  • rules: (optional) disambiguation rules for edge cases where categories overlap

Ensures

  • classification: a structured result containing:
    • category: the selected category name
    • confidence: a score from 0 to 1 where 0.5 means genuine uncertainty, not "probably"
    • reasoning: which features of the item matched which category description
  • if the item fits multiple categories: the best fit is returned with reasoning about why alternatives were rejected
  • if the item fits no category: category is "uncategorized" with reasoning explaining why no category matched

Errors

  • empty-categories: the category set is empty or contains no usable descriptions
  • ambiguous-item: the item contains insufficient information to distinguish between two or more categories even after applying disambiguation rules

Strategies

  • when categories overlap: apply disambiguation rules first; if none exist, prefer the more specific category over the general one
  • when confidence is low: say so in the score rather than inflating confidence to avoid appearing uncertain
  • when the item is complex: decompose it into features and match each feature against category descriptions independently before synthesizing a verdict

Notes

Classifier is a pure labeling function. It does not know what the classification will be used for. It does not route, delegate, or act on the result. For selecting a handler to delegate work to, use router. For evaluating quality, use critic. For checking formal correctness, use verifier.