# Manifest Generation And Documentation

> Use when you need to audit a bioinformatics repository (such as MIBiG) to determine which sequence files are maintained locally but lack public accessions in NCBI GenBank/RefSeq. Use this to support curation workflows, data provenance tracking, or to identify candidate sequences for public release.

- Skill: `holobiomicslab/manifest-generation-and-documentation` (Agent Skill)
- Install (CLI): `npx skillmds@latest add holobiomicslab/manifest-generation-and-documentation`
- Raw SKILL.md: https://api.skillmd.com/api/skills/holobiomicslab/manifest-generation-and-documentation/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- License: CC-BY-4.0
- Author: HolobiomicsLab (https://skillmd.com/u/holobiomicslab)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/holobiomicslab/manifest-generation-and-documentation

---


# Reconstruct the non-NCBI sequence inventory from the genbanks directory

> **License: restricted** — no clear open-source license detected for the underlying tool; verify licensing before commercial use or redistribution. <!-- asb-license-banner -->
## Summary

Generate a structured inventory manifest of sequence files held in a repository's local `genbanks` directory that are not available from NCBI's GenBank/RefSeq databases. This skill reconciles local file metadata with public sequence databases to identify and document sequences unique to the repository.

## When to use

Apply this skill when you need to audit a bioinformatics repository (such as MIBiG) to determine which sequence files are maintained locally but lack public accessions in NCBI GenBank/RefSeq. Use this to support curation workflows, data provenance tracking, or to identify candidate sequences for public release.

## When NOT to use

- Input sequence files are already linked to public NCBI accessions and no audit of local-only sequences is needed.
- The genbanks directory does not exist or is empty in the target repository.
- NCBI E-utilities or BLAST access is unavailable and cross-referencing cannot be performed.

## Inputs

- MIBiG repository cloned from github.com/mibig-secmet/mibig-json
- genbanks directory containing sequence files
- NCBI GenBank/RefSeq database (via E-utilities or BLAST)

## Outputs

- Structured manifest (CSV or JSON) with columns: file path, sequence identifier, GenBank accession, availability status (local-only or public)

## How to apply

Clone or access the target repository and enumerate all files in the `genbanks` directory, extracting sequence identifiers and any embedded NCBI accession numbers. For each file, cross-reference the accession against NCBI GenBank/RefSeq using NCBI E-utilities or local BLAST searches to establish availability status. Files with valid public accessions are marked as publicly available; files with no matching accession or accession lookup failures are flagged as local-only. Compile the results into a structured manifest (CSV or JSON) recording filename, entry identifier, accession (if present), and a local-only status flag. This reconciliation approach ensures completeness and helps distinguish curated or proprietary sequences from those already in the public domain.

## Related tools

- **NCBI E-utilities** (Query NCBI GenBank/RefSeq databases to verify accession availability and retrieve sequence metadata for cross-referencing)
- **BLAST** (Perform local sequence similarity searches to determine whether sequences are present in NCBI GenBank/RefSeq or are unique to the local genbanks directory)

## Evaluation signals

- Manifest file is generated and contains all expected columns: file path, sequence identifier, GenBank accession, and availability flag.
- All files in the genbanks directory are represented in the manifest with no missing entries.
- Accession lookups return consistent results when spot-checked against NCBI's online interfaces or local BLAST databases.
- Local-only sequences have blank or 'N/A' accession fields, while public sequences carry valid NCBI accessions and availability = 'public'.
- Manifest can be parsed as valid CSV/JSON and round-trips without data loss.

## Limitations

- Some sequence files in the genbanks directory may lack embedded accession identifiers, requiring sequence-level similarity searches (BLAST) which may be computationally expensive or ambiguous for highly similar or fragmented sequences.
- NCBI E-utilities queries may timeout or rate-limit if the number of accessions is very large; batch queries or delays may be necessary.
- Sequences that are novel or significantly divergent from public databases may not be detected as local-only without full de novo assembly or annotation.
- No changelog is available in the repository documentation to track historical changes to the genbanks directory, limiting provenance tracking.

## Evidence

- [readme] The `genbanks` directory contains a handful of sequence files that are not available from NCBI's GenBank/RefSeq databases.: "The `genbanks` directory contains a handful of sequence files that are not available from NCBI's GenBank/RefSeq databases"
- [other] Cross-reference each file against NCBI GenBank/RefSeq accession identifiers (using NCBI E-utilities or local BLAST) to determine availability status.: "Cross-reference each file against NCBI GenBank/RefSeq accession identifiers (using NCBI E-utilities or local BLAST) to determine availability status"
- [other] Compile results into a structured manifest recording filename, entry identifier, accession (if present), and local-only status flag.: "Compile results into a structured manifest recording filename, entry identifier, accession (if present), and local-only status flag"
- [other] Output the manifest as a CSV or JSON file with columns for file path, sequence identifier, GenBank accession, and availability (local-only or public).: "Output the manifest as a CSV or JSON file with columns for file path, sequence identifier, GenBank accession, and availability (local-only or public)"