Install
$ agentstack add skill-adeerkhan-vitruvius-gap-analysis ✓ 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
Gap Analysis
Run a systematic literature gap analysis for an engineering sub-topic. This skill wraps scholarly-research for source discovery and adds the gap-validation methodology on top.
Workflow
flowchart LR
Input["Discipline + Sub-topic"] --> Search["Narrow-Query Search"]
Search --> Triangulate["Triangulate Sources"]
Triangulate --> Validate["Validate Gap Signal"]
Validate --> Dossier["Gap Dossier + Provenance"]
Invocation
/gap-analysis [--deep | --quick]
- discipline: one of
civil,mechanical,electrical,software,architectural - sub-topic: narrow focus within the discipline (e.g.,
FRP-bonding,hydrogen-embrittlement). Required — if the user doesn't provide one, ask. --deep: Force parallel verification lanes for all gap validation claims.--quick: Skip parallel verification, use single-source checks only.- No flag: Auto-scale based on gap criticality (safety-related gaps get parallel verification).
Methodology (Execute This)
Phase 1 — Narrow-Query Search (wrap scholarly-research)
For the target sub-topic, construct a narrow search query and run it through OpenAlex using title_and_abstract.search:
GET https://api.openalex.org/works?filter=title_and_abstract.search:&per-page=20&select=id,display_name,publication_year,cited_by_count,doi,open_access,best_oa_location,authorships
Then run the same query on arXiv:
GET https://export.arxiv.org/api/query?search_query=all:&max_results=20
Gap signal: If the narrow query returns 0–5 hits, and the top hits are off-topic, low-citation ( methodology > citation authority > reproducibility > recency.
Output
Inline Summary (chat response)
- Gap statement (1-2 sentences)
- Confidence: High | Medium | Low (based on triangulation completeness)
- Validation counts: OpenAlex hits, arXiv hits, web "open problem" signals
- Top 3 edge papers: [first author, year] — covers X, misses Y [Tier N]
- 3-5 concrete, answerable research questions
- Path to full dossier on disk
Full Dossier (saved to disk)
Match the structure of existing gap-analysis//-.md files in this repository. Required sections:
- What's Missing — specific knowledge gap description
- Why It Matters — safety, economic, societal stakes
- Suggested Research Questions — 3-5 concrete, answerable
- Key Papers (Touching the Edges) — 4-7 papers with Authors, Year, DOI/URL, Covers, Misses, Tier
- Validation — OpenAlex query + hits + date, arXiv query + hits + date, web sources, open problem signals
- Confidence — High | Medium | Low with justification
Write the dossier to outputs/gap-analysis/.md and a provenance sidecar to outputs/gap-analysis/.provenance.md.
Quality Gate (mandatory before returning)
Self-check the output. If any check fails, retry once with feedback:
- Gap count — at least 3 distinct gaps identified. If < 3, re-search with broader terms.
- Source count — at least 4 key papers referenced. If < 4, expand search to additional databases.
- Triangulation — at least 2 source tiers represented (e.g., OpenAlex + arXiv). If only 1, search missing tier.
- Research questions — at least 3 concrete, answerable questions. If < 3, refine gap analysis.
- Confidence justification — Confidence level has explicit justification. If missing, add reasoning.
Retry logic: If quality gate fails, re-run the search phase once with the specific failure as feedback. If it fails again, return the best output with a PARTIAL confidence and list the unresolved issues in provenance.
Scope and Boundaries
- This skill identifies gaps — it does not fill them. For filling gaps,
dispatch to engineering-research.
- Output is research-only, not design or implementation guidance.
- Fail-closed: if triangulation cannot be completed, mark the gap
unverified
rather than claiming it exists.
- Never fabricate a gap. If the literature adequately covers the topic, say so.
- When a source is paywalled or unreachable, cite from metadata and mark
blocked.
See references/blocked-access-policy.md for the full rules.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: adeerkhan
- Source: adeerkhan/vitruvius
- 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.