GentBajko/capstone / skills/core
core
VerifiedInternal to the capstone suite - carries the shared rules (references/) and scripts every capstone subcommand reads; it exists so npx-skills installs ship them alongside the command skills. Not meant to be invoked directly; when invoked anyway, run references/../scripts/help.sh and output its stdout verbatim.
scripts/help-hook.sh
View on GitHub#!/usr/bin/env bash
# UserPromptExpansion hook: answers /capstone:help without invoking the model.
# hooks.json's matcher targets command_name "capstone:help"; the stdin check
# below is a second guard so a broad matcher can never hijack other commands.
# Verified payload fields: hook_event_name, expansion_type, command_name,
# command_args, command_source, prompt.
# JSON encoding below covers any text: backslashes and quotes are
# escaped, tabs become \t, newlines \n, and CR and the other control
# characters (which help.sh never prints) are dropped.
# Terminal CLI only: blocked-prompt reasons render in the terminal but are
# swallowed by GUI surfaces (VS Code extension et al.; claude-code#15344),
# where blocking would eat the command and print nothing. Allowlist the one
# surface known to render the reason; everywhere else stay silent so the
# prompt passes through and the help skill answers via the model instead.
if [ "${CLAUDE_CODE_ENTRYPOINT:-}" != "cli" ]; then exit 0; fi
INPUT="$(cat)"
if printf '%s' "$INPUT" | grep -q '"command_name":"capstone:help"'; then
HELP="$(bash "$(dirname "$0")/help.sh" | sed 's/\\/\\\\/g; s/"/\\"/g' \
| tr -d '\000-\010\013-\037' | awk '{ gsub(/\t/, "\\t"); printf "%s\\n", $0 }')"
# Fenced so markdown-rendering surfaces (VS Code extension chat) keep the
# column alignment; terminals just show the fence lines. Empty HELP means
# help.sh broke; pass through so the model path answers instead.
if [ -n "$HELP" ]; then
printf '{"decision": "block", "reason": "```\\n%s```"}' "$HELP"
fi
fi
exit 0
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 470k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |