Skip to content

monte-carlo-data/mc-agent-toolkit / .claude/skills/toolkit-skill-author

toolkit-skill-author

Verified

Authors or extends a skill in mc-agent-toolkit. Gates for forbidden buckets and name collisions, applies CONTRIBUTING's extend-or-split rules, then edits a peer skill or hands off to Anthropic's skill-creator and walks the registration checklist.

scripts/tests/find-peers.bats

View on GitHub
#!/usr/bin/env bats

setup() {
  SCRIPT="$BATS_TEST_DIRNAME/../find-peers.sh"
}

@test "dumps frontmatter for every skill under the dir" {
  TMP=$(mktemp -d)
  mkdir -p "$TMP/alpha" "$TMP/beta"
  cat > "$TMP/alpha/SKILL.md" <<'EOF'
---
name: alpha
description: Alpha does X.
when_to_use: |
  When the user asks about X.
---

Body content here.
EOF
  cat > "$TMP/beta/SKILL.md" <<'EOF'
---
name: beta
description: Beta does Y.
---
EOF
  run "$SCRIPT" "$TMP"
  [ "$status" -eq 0 ]
  [[ "$output" == *"=== alpha ==="* ]]
  [[ "$output" == *"=== beta ==="* ]]
  [[ "$output" == *"description: Alpha does X."* ]]
  [[ "$output" == *"description: Beta does Y."* ]]
  [[ "$output" == *"When the user asks about X."* ]]
  [[ "$output" != *"Body content here."* ]]
}

@test "exits 2 when skills dir is missing" {
  run "$SCRIPT" /nonexistent-path-$$
  [ "$status" -eq 2 ]
}

@test "exits 2 when skills dir has no SKILL.md files" {
  TMP=$(mktemp -d)
  run "$SCRIPT" "$TMP"
  [ "$status" -eq 2 ]
}

@test "defaults to ./skills when no arg given" {
  TMP=$(mktemp -d)
  mkdir -p "$TMP/skills/gamma"
  cat > "$TMP/skills/gamma/SKILL.md" <<'EOF'
---
name: gamma
description: Gamma.
---
EOF
  cd "$TMP"
  run "$SCRIPT"
  [ "$status" -eq 0 ]
  [[ "$output" == *"=== gamma ==="* ]]
}
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: 471kUpdated 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