skill-index

name	skill-index
description	Query Claudex's own skill catalog by category, tag, or capability. Use when asked "what skills exist for X", "do we have a skill for Y", "list all backend skills", or when planning multi-step work that might benefit from a skill you didn't load.
category	meta
tags	["skill-catalog","jq","discovery","self-tooling","frontmatter"]
maturity	beta
external_deps	[]

Skill Index

Claudex ships with 160+ skills. Auto-loading by description matching works well for the common case, but sometimes you need to explicitly enumerate what's available — for planning multi-step work, for answering "do we have anything for X", or for spotting gaps.

This skill teaches you how to query the skill catalog without scanning every SKILL.md by hand.

Quick reference

# Where the catalog lives (generated by scripts/skill-index.sh)
INDEX=$HOME/.claude-agent/data/skill-index.json
SKILLS_DIR=$HOME/.claude-agent/.claude/skills

Common queries

# All skills in a category
jq -r '.[] | select(.category == "security") | "\(.name) — \(.description)"' "$INDEX"

# All skills with a specific tag
jq -r '.[] | select(.tags // [] | index("docker")) | .name' "$INDEX"

# Only stable skills (skip experimental/beta when reliability matters)
jq -r '.[] | select(.maturity == "stable") | .name' "$INDEX"

# Skills with external dependencies (need INSTALL.md)
jq -r '.[] | select((.external_deps // []) | length > 0) | "\(.name): \(.external_deps | join(", "))"' "$INDEX"

# Count by category
jq -r '[.[] | .category] | group_by(.) | map({category: .[0], count: length}) | .[] | "\(.count)\t\(.category)"' "$INDEX" | sort -rn

# Search descriptions for a keyword (fallback when category/tag don't match)
jq -r --arg q "$KEYWORD" '.[] | select(.description | test($q; "i")) | "\(.name) — \(.description)"' "$INDEX"

When to use

• Planning a complex task — list relevant skills upfront so you don't reinvent
• Answering "what can Claudex do for X" — give the user a real list, not a hand-wave
• Spotting gaps — if a category has only 1 skill, that's a tell
• Audit/maintenance — find all experimental skills to harden, or deprecated ones to remove

Fallback when the index isn't built

If $INDEX doesn't exist yet (skill-index.sh hasn't run), grep frontmatter directly:

# All skills with a given category
grep -l "^category: security" "$SKILLS_DIR"/*/SKILL.md | xargs -n1 dirname | xargs -n1 basename

# All skill names + descriptions (raw)
for f in "$SKILLS_DIR"/*/SKILL.md; do
    awk '/^name:/ {name=$2} /^description:/ {sub(/^description: */, ""); print name " — " $0; exit}' "$f"
done

Categories (the 14)

development · frontend · backend · security · research · data · system · comms · writing · productivity · media · trading-finance · home-iot · meta

Rules

• Don't enumerate when you already know. If the user asked a specific question and you know the right skill, just use it — don't list 12 alternatives first.
• Use the index for breadth, descriptions for depth. The index tells you what exists; reading individual SKILL.md tells you how to use it.
• Flag uncategorized skills. If jq -r '.[] | select(.category == null) | .name' "$INDEX" returns anything, those skills need their frontmatter completed.