Install
$ agentstack add skill-mmthebest-research-architect-research-architect-citation ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
First Paper Citation Support
Use this branch after literature mapping and before first-draft writing.
Purpose
Build a citation support bank. This is separate from exemplar learning.
- Exemplar learning teaches structure.
- Citation support justifies specific literature statements.
Inputs
Read:
paper_output/project_config.json
paper_output/concept_dossier.md
paper_output/sota_gap_map.md
paper_output/confirmed_research_spine.md
paper_output/claim_register.md when available
paper_output/reference_materials/source_index.md
Required output
Create:
paper_output/citation_support_bank.md
Use:
| Citation ID | Full Reference or Stable Identifier | Year | Source Type | Supports Section | Support Claim Sentence | Why It Fits | Verification Status | Notes | |---|---|---|---|---|---|---|---|---|
Candidate count
Default target: 30 high-quality candidate sources. If the project is narrow or the user provides fewer sources, produce fewer and explicitly mark coverage gaps.
Verification statuses
verified: metadata and claim support checked;partial: likely relevant but claim support requires checking;needs_user_file: source inaccessible without user-provided file;reject: not suitable for citation.
Rules
- Never invent bibliography entries.
- Never cite a paper for a claim it does not support.
- Prefer sources with clear claim relevance over superficially similar titles.
- Use a coherent subset in the draft; do not dump all candidates.
- Mark uncertainty rather than hiding it.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mmTheBest
- Source: mmTheBest/Research-Architect
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.