Skip to content

hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-research

hyper-research

Verified

[Hyper] Use this skill when the user asks for multi-source, cited research - fact-finding, comparisons, market or trend analysis, or evidence-backed recommendations across live web, official docs, GitHub, and local repo sources - saved as a markdown report. Do not use for one-source lookups, rewriting, or implementation.

references/report-template.md

View on GitHub
# Report Template

Use this reference when drafting the saved research report.

## Contents

- File path
- Template
- Quick variant
- Writing rules

## File Path

Save to `.hyper/research/[NN].slug.md`, with the journal in `.hyper/research/[NN].slug/` for default, deep, and parallel runs.

Example: `.hyper/research/03.websocket-vs-sse.md` and `.hyper/research/03.websocket-vs-sse/`.

## Template

```markdown
# [Topic] Research Report

> As of: YYYY-MM-DD or version | Depth: quick/default/deep (+parallel) | Run state: converged/exhausted/blocked
> Sources reviewed: N | Sources cited: M | Domains: D | Waves: W | Excursions: X | Execution checks: V

## Executive Summary
[Answer the core question first in 2-4 sentences. Only verified claims appear here.]

## Scope And Fidelity
- Core question:
- Axes:
- Time window and as-of anchor:
- Source floor and derived-number policy:
- Evidence channels used:

## Key Findings
### 1. [Finding]
- Claim: [statement] [S1][S4] (C1)
- Numbers: [value] MEASURED [S1] | [value] DERIVED = [formula over inputs]
- Why it matters:

## Comparison
| Criteria | Option A | Option B | Sources |
|------|------|------|------|

## Expected Truths
| Expected truth | Result | Evidence |
|---|---|---|
| E1 | true / violated / unknown | |

## Verified Claims
| Claim | Kind | Verdict | Evidence |
|---|---|---|---|
| C3 | code | CONFIRMED | `[NN].slug/verify-<slug>.md` |
| C1 | non-code | supported (2 domains, primary S1, counter-search Q7) | [S1][S4] |

## Contradictions
- [Source A vs source B: resolution and evidence, or why it stays open]

## Debate record
| Claim | Verdict | Change to the claim |
|---|---|---|
| C1 | holds | |
| C5 | unverified (one debate attack) | moved to Unresolved |

- The full debate rows live in the journal file `debate.md`; this annex lists each high-risk claim with its verdict.

## Unresolved And Refuted
- Unresolved: [claim - what is missing]
- Refuted: [claim - the counter-evidence]

## Risks And Caveats
- [Limitation, weak-source caveat, assumption with its sensitivity line]

## Known Gaps
- [What the run could not answer; for an exhausted run, the open leads and what an extension would investigate]

## Recommendation
- [Decision or next action, drawn only from verified claims]

## Source Ledger
| # | Source | URL/path | Publisher | Published/updated | Accessed | Channel | Grade | Role | Used? |
|---:|---|---|---|---|---|---|---|---|---|

## Query Log
- [Distinct query, channel, and why it was used; for journaled runs, a pointer to `queries.md`]

## Expansion Trace
- Wave 1: [searches or lanes] -> [leads gained]; Wave 2: ...; stop reason: [rule]

## Validation Notes
- Gates: structure, citation, claim gate, lineage, recency, read-back - pass or residual defect
- Source floor: [met or shortfall, reviewed vs cited]
- Dedupe: [queries and duplicate sources handled]

## Report gates
| Gate | Status (pass / fail / not_run) | Open-defect severity (blocker / major / minor) | Reason |
|---|---|---|---|
| structure | | | |
| citation | | | |
| claim gate | | | |
| number lineage | | | |
| recency | | | |
| read-back | | | |

## References
- [S1] [Title](https://example.com/source), accessed YYYY-MM-DD
```

## Quick Variant

A `--quick` report keeps the header, Executive Summary, Scope And Fidelity, Key Findings, Risks And Caveats, Source Ledger, Query Log, Validation Notes, and References. It drops the sections a single pass cannot fill, and its claim-source matrix sits inside Key Findings.

## Writing Rules

- Put the answer before the backstory.
- Cite every non-obvious claim with `[S<n>]` ids that resolve to the ledger.
- Assert high-risk statements only from `verified-claims`; annex items appear only under Unresolved And Refuted.
- The `## Debate record` annex lists each high-risk claim with its verdict; the full debate rows live in the journal file `debate.md`.
- Label every number `MEASURED`, `ASSUMED`, or `DERIVED`.
- Use exact dates when recency matters, and state the as-of anchor in the header.
- Count a duplicate source once, even when several lanes found it.
- Quote sources verbatim in their original language, under 20 words, with a translation beside the quote when the report language differs.

## Sources

> Checked 2026-11-09.

| Claim | Source |
|---|---|
| The effort header, verified-claims and contradictions sections, the unresolved and refuted annex, the expansion trace, and short attributed quotes, adapted from the `ulw-research` synthesis layout | <https://github.com/code-yeongyu/oh-my-openagent/tree/0d80470e4201925727e88afbafcdf24d7801a588> |
| The source ledger columns and the reviewed-versus-cited split | `instructions/sourcing/references/source-ledger.md` |
| The `## Debate record` annex that lists high-risk claims with their verdicts | `dbc-hbin/omp-ulw` at commit `74df40f` (2026-11-09); the source repository has no license, so the mechanism was re-authored in this package's own words and no text or code was copied |

### Evidence grade

`LOCAL` - this file carries this package's own template. The `https://example.com/source` destination is a placeholder host, not a source.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall