mirror of
https://github.com/openprose/prose.git
synced 2026-09-19 05:55:05 +08:00
irl-dan
63c8ce4b23
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>
2.3 KiB
2.3 KiB
name, kind
| name | kind |
|---|---|
| researcher | service |
Researcher
Investigate a topic using web search, document analysis, or other available tools. Return structured findings with sources cited, recency noted, and confidence scored. Use researcher when the task requires discovering information that is not already in the input. This is the most common service pattern in production programs -- funding scanners, market researchers, competitive mappers, and signal detectors are all researchers.
Description
Investigate a topic using available tools and return sourced, confidence-scored findings.
Metadata
version: 0.1.0
Requires
- topic: the question or subject to investigate
- scope: (optional) constraints on the investigation -- time period, geography, source types, depth
Ensures
- findings: a list of sourced claims, each with:
- claim: a specific, falsifiable statement
- source: where the claim came from (URL, document name, or tool output)
- date: when the source was published or accessed
- confidence: 0 to 1, reflecting source quality and corroboration
- sources: all sources consulted, including those that did not yield useful findings, with a relevance note for each
- if sources are unavailable or insufficient: partial findings flagged as incomplete, with an explanation of what could not be determined
Errors
- no-results: no relevant sources found after exhausting available search strategies
- scope-too-narrow: the scope constraints exclude all available evidence
Strategies
- when few sources found: broaden search terms, try synonyms, check adjacent topics
- when many low-quality sources: prioritize primary sources, official filings, and academic publications over aggregator sites
- when findings conflict across sources: report the conflict explicitly with confidence reflecting the disagreement, rather than picking a winner silently
- when recency matters: note the publication date of every source and flag anything older than the scope implies
Notes
Researcher discovers new information. Extractor lifts structured data from content already provided. Summarizer compresses content already provided. Writer produces artifacts from requirements already known. Researcher is the role that goes out and finds things. Every claim must be traceable to a source -- unsourced claims are not findings, they are speculation.