rlaope/oh-my-hermes / .claude/agent-skills/omh-source-finder
omh-source-finder
Verified[omh] Gathering candidate papers, datasets, or repos.
Source Finder
This is an OMH source-finder workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
source-finder exists so Hermes can turn vague source discovery requests into typed candidates, acquisition status, and downstream workflow choice without pretending OMH searched, downloaded, or verified the material.
First Steps
- Discover the current search/read tools and authorized scope, then follow
references/search-method.md: plan -> actual host search/read -> merge -> assess -> bounded retry. Useomh_searchonly when available; otherwise report the skill-only fallback. Keep direct file lookups direct.
Do Not Use When
- The requested output is factual findings, comparison, or a summary rather than a typed candidate inventory and acquisition status; use
ulw-research. - The user needs a business decision brief with evidence-versus-inference treatment; use
omh-research-brief. - The user asks for a cited answer to a current-facts question; use
omh-web-research, and for a reference-implementation study with a depth budget useulw-research. - The user supplies a paper/PDF/arXiv/DOI/excerpt and wants explanation; use
omh-paper-learning. - The user asks for recurring monitoring, source inbox, or Scout/Analyst/Briefer operations.
- The user asks to export, convert, render, package, or attach a file; use
omh-materials-packageoromh-deliverable-package. - The user asks for an image card or visual summary; use
omh-image-cards.
Examples
Good example:
- Prompt: source-finder find papers, datasets, and GitHub repos for evaluating browser agent benchmarks.
- Expected behavior: Prepare source_finder_plan/v1 with typed candidates, acquisition states, missing observed evidence, and downstream choices.
- Why: The user needs source candidates before deciding whether to learn, research, package, or implement.
Bad example:
- Prompt: source-finder find current citations and summarize what the sources say.
- Expected behavior: Route to
ulw-researchbecause the user asks for current evidence and synthesis, not candidate acquisition status. - Why: Source-finder prepares acquisition lifecycle metadata; research owns current evidence synthesis.
Completion Checklist
- Source kinds, source boundaries, and downstream intent are named.
- Each candidate has a source_candidate/v1 shape and acquisition state.
- Observed states include provenance before being treated as evidence.
- The next downstream workflow is recommended without claiming it ran.
- Search, download, clone, extraction, hash, license, verification, and downstream processing gaps are explicit.
Recovery Notes
- If the user asks for facts or citations, route to
ulw-research. - If a candidate lacks a link or file reference, keep it candidate_prepared and ask for the next observable source step.
- If the user wants to process a selected source, route to the downstream workflow instead of continuing source acquisition.
When to Use
Use when the requested output is a typed source candidate inventory and acquisition status across papers, web links, datasets, GitHub repositories, public presentations, docs/specs, or unknown source material before choosing omh-paper-learning, ulw-research, omh-research-brief, omh-materials-package, or ulw-work for a delivery cycle.
Strong routing signals: `source-finder`, `source finder`, `source acquisition`, `source intake`, `find papers and datasets`, `find datasets and repos`, `find papers`, `find arxiv link`, `find arxiv paper`, `find datasets`, `find github repos`, `find oss repos`, `find presentations`, `find public slides`, `find docs and specs`, `find source candidates`, `download candidate`, `source candidate`, `acquisition status`, `자료 후보`, `출처 후보`, `arxiv 링크`, `arxiv 링크 찾아`, `논문 데이터셋 찾아`, `깃허브 저장소 찾아`, `공개 발표자료 찾아`, `문서 스펙 찾아`
Catalog Metadata
Category: research
Phase: source-acquisition
Quality tier: source-acquisition-gated
Reasoning demand: standard
Quality bar:
- Name source kinds from: paper, web_link, dataset, github_repo, presentation, docs_spec, unknown.
- Record acquisition state from: candidate_prepared, link_observed, download_link_prepared, download_observed, file_hash_recorded, text_extraction_observed, license_checked, verification_observed, downstream_selected.
- Separate candidate preparation, observed link, observed download, file hash, text extraction, license check, verification, and downstream selection.
- Attach observation provenance before treating any acquisition state as evidence.
- For
papercandidates, when Hermes' bundledarxivskill is available, search through it - by topic, author, category, or paper id - and record each entry it returns aslink_observedwithhermes_toolprovenance. A search result is an observed link and nothing more: download, text extraction, and verification stay unclaimed until their own run is observed. Without the skill, a paper candidate stayscandidate_prepareduntil a link is observed another way. - When the candidates are scholarly papers, load
references/literature-retrieval.md: pick arXiv, OpenAlex, bioRxiv or PubMed by topic, scale follow-up rounds to a stated difficulty within the plan's cap, dedupe by id, DOI, then title, and keep only papers a host result returned. - Vary search angles across official docs, academic work, implementations, datasets, and criticism within the plan's budget (3 queries, 10 external attempts and one follow-up for an explore search), and name the source kinds still without candidates when the budget ends.
- Recommend the next downstream workflow without pretending that downstream work already ran.
Required inputs:
- source target or topic
- desired source kinds
- source boundaries or exclusion criteria
- downstream intent when known
Expected outputs:
- source_finder_plan/v1
- source_candidate/v1
- source_candidate_set/v1
- source_acquisition_status/v1
- downstream workflow recommendation
- not-evidence boundary
Artifact expectations:
- source_finder_plan/v1 under .omh/source-finder when a wrapper or CLI records it
Safety rules:
- Do not claim web search, download, repository clone, file extraction, file hash verification, license verification, or source correctness from a prepared candidate.
- Do not define a source inbox; source-finder owns source_candidate_set/v1 and source_acquisition_status/v1 only.
- Route current citations and source-backed synthesis to
ulw-research, supplied-paper explanation toomh-paper-learning, file export toomh-materials-package, and image cards toomh-image-cards.
Runtime Evidence
Use the current host's own tools and subagent/task mechanism when available;
otherwise run the same lanes sequentially or name the unavailable capability.
A prepared plan, handoff, checklist, or skill installation is not execution,
review, CI, merge-readiness, or merge evidence. Record actual tool results, or
not_observed / not_available, in the record; never invent dispatch or host
accounting.
Treat supplied context as advisory, not proof of hidden memory reads or writes.
State scope, constraints, verification, and the stop condition before work.
Reply in the user's own words and the host's own voice: the host's persona owns
reply language, tone, speech level, and sentence endings, progress updates
included (where it sets no language, use the one the user wrote in), and OMH
shapes structure and content only; OMH's record terms
(surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in
records and tool calls, never in the sentence the user reads unless they ask
about one; and when a real unresolved user decision or a useful briefing discussion
remains, offer one specific, content-linked question. Completed work needs no question;
omit unrelated non-action footers and generic offers to continue.
Supporting paths are relative to this skill directory; sibling skill paths are
relative to its parent. Resolve them from the host-provided skill base directory
({baseDir} on hosts that provide it), never a hardcoded install location.
A named workflow not installed here is unavailable, not permission to emulate
its host-specific capabilities. Verify through the real surface before done.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |