Skip to content

lasp/adamant-skills / adamant-skill-selector

adamant-skill-selector

Verified

Route Adamant framework tasks to the correct skill(s). Load this FIRST for any Adamant work -- it tells you which specific skills to read.

FileKindSize
SKILL.mdskill md20.9 KB
scripts/generate_selector.shexecutablescript1.6 KB

scripts/generate_selector.sh

View on GitHub
#!/bin/bash
# Generate skill selector routing summary from skill frontmatter
# Usage: ./generate_selector.sh [skills_dir]
# Outputs markdown table of all Adamant skills with descriptions

SKILLS_DIR="${1:-$(dirname "$0")/../../}"
echo "# Auto-Generated Skill Index"
echo ""
echo "Generated: $(date -u +%Y-%m-%dT%H:%M:%SZ)"
echo ""
echo "| Skill | Description | Lines | Refs |"
echo "|-------|-------------|-------|------|"

for skill_dir in "$SKILLS_DIR"/adamant-*/; do
    [ -d "$skill_dir" ] || continue
    skill_name=$(basename "$skill_dir")
    skill_md="$skill_dir/SKILL.md"
    [ -f "$skill_md" ] || continue

    # Extract description from frontmatter
    desc=$(sed -n '/^---$/,/^---$/{ /^description:/{ s/^description: *//; p; q; } }' "$skill_md")
    lines=$(wc -l < "$skill_md" | tr -d ' ')

    # Count reference lines
    ref_lines=0
    if [ -d "$skill_dir/references" ]; then
        ref_lines=$(find "$skill_dir/references" -name '*.md' -o -name '*.yaml' | xargs wc -l 2>/dev/null | tail -1 | awk '{print $1}')
        [ -z "$ref_lines" ] && ref_lines=0
    fi

    echo "| \`$skill_name\` | $desc | $lines | $ref_lines |"
done

echo ""
echo "## Non-Adamant Skills"
echo ""
for skill_dir in "$SKILLS_DIR"/*/; do
    [ -d "$skill_dir" ] || continue
    skill_name=$(basename "$skill_dir")
    [[ "$skill_name" == adamant-* ]] && continue
    [ "$skill_name" = "scripts" ] && continue
    skill_md="$skill_dir/SKILL.md"
    [ -f "$skill_md" ] || continue
    desc=$(sed -n '/^---$/,/^---$/{ /^description:/{ s/^description: *//; p; q; } }' "$skill_md")
    echo "- **$skill_name**: $desc"
done
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall