dev-ingest-named
100 / 100 · Low risk
Fine to try.
Playbook for landing one evidence-approved single-skill intake whose L4 topology is a NEW fusion generic plus one named implementation: create the generic and its prerequisites, create the named skill, ingest each verified evidence row, and appraise Trust Magnitude — then stop at the calibration gate. Use when: an intake issue carries intake:topology-approved and intake:evidence-approved, the promotion PR review/meta/intake-<N> is open, and a reviewed evidence manifest exists. Triggers: "ingest…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'dev-ingest-named' ] || [ -L ~/.agents/skills/'dev-ingest-named' ]; then echo 'A skill folder named dev-ingest-named already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/gaia-research/gaia-skill-tree' "$d" && git -C "$d" checkout --quiet '9b4d9b98043140188f00b14d0ac8fa6bc02491b7' -- '.agents/skills/dev-ingest-named' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/dev-ingest-named' ~/.agents/skills/'dev-ingest-named' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'dev-ingest-named' ~/.claude/skills/'dev-ingest-named' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/gaia-research/gaia-skill-tree/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-14 | 9b4d9b9 | 100 |
Also found in
- gaia-research/gaia-skill-tree/.claude/skills/dev-ingest-named