AGENT SKILL

filetree-simple

Generate or lint a compact top-level FILETREE.md navigation map. Use when repository structure changes or FILETREE.md needs creation, regeneration, or validation.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 3
Forks
0

01 前言 Front Matter

name
filetree-simple
license
MIT
description
Generate or lint a compact top-level FILETREE.md navigation map. Use when repository structure changes or FILETREE.md needs creation, regeneration, or validation.

02 资源文件 2

03 SKILL.md 正文

Filetree

Generate FILETREE.md as a deterministic cold-start map: core repository files plus public top-level areas. Each area owns its meaning in index.md; the map links to that entrypoint and stops there.

Run commands from the target repository root, or pass --repo before the subcommand. The helper is scripts/filetree.py.

Generate

  1. Run:

    python scripts/filetree.py generate
    
  2. If validation fails, fix every reported entrypoint and rerun generate.

  3. Run lint after generation.

Completion criterion: FILETREE.md contains the complete two-section map and lint exits 0.

Lint

Run:

python scripts/filetree.py lint

lint builds the expected map in memory and compares it with FILETREE.md. It never writes files. Exit 0 means current; exit 1 means invalid inputs or drift that generate must resolve.

Contract

  • Output is English Markdown with Core Files and Main Areas sections.
  • Core files use the script's stable ordered descriptions and appear when present as regular files.
  • A public area is a non-hidden direct child directory outside the conventional temporary-directory exclusions in the script.
  • A public area uses index.md. Only a skill directory may fall back to SKILL.md.
  • An index.md entrypoint starts with an English H1 followed by one plain English sentence of at most 20 words. That sentence becomes the map summary.
  • A SKILL.md entrypoint supplies single-line name and description frontmatter; description follows the same summary rules.
  • Top-level directory symlinks are rejected. The generator does not traverse nested directories.
  • Generation validates the complete map before atomically replacing FILETREE.md; a failed run leaves the existing file unchanged.

Scope, Inputs, Outputs, and Limitations

  • Scope: compact top-level navigation, not an exhaustive file inventory or content-integrity manifest.
  • Inputs: the target root, conventional core files, and top-level index.md or skill SKILL.md entrypoints.
  • Output: one generated FILETREE.md; no sidecar manifest or hashes.
  • Runtime: Python 3.9+ standard library; Git and third-party packages are not required.
  • Limitations: full OKF conformance, nested bundle navigation, file history, and content integrity remain separate concerns.

Run the standard-library test suite after changing the skill:

python -m unittest discover -s tests -v

Credits

Inspired by nekocode/filetree-skill, an MIT-licensed Claude Code plugin.

04 同仓库更多 Skills

pengqianhan
pengqianhan/AI-Human-Research-OS

workflow-skill-creator

Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

uv

Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

uniprot-database

Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

unibind-database

Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED/FASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

ucsc-conservation-and-tfbs

Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

string-database

Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.

★ 3