Skip to content

sno-ai/sno-station-skills / plugins/sno-station-standalone/skills/agentic-walkthrough

agentic-walkthrough

Verified

Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect, capture one observable per hop, and report a result a no-op could not produce.

FileKindSize
SKILL.mdskill md6.6 KB
scripts/selftest/run-selftest.shexecutablescript1.2 KB

scripts/selftest/run-selftest.sh

View on GitHub
#!/usr/bin/env bash
# Text contract for this skill only. Reads nothing outside this payload.
set -Eeuo pipefail

selftest_dir="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
skill="$(cd -- "$selftest_dir/../.." && pwd)/SKILL.md"

python3 - "$skill" <<'PY'
import pathlib
import sys

text = " ".join(pathlib.Path(sys.argv[1]).read_text(encoding="utf-8").split())
rules = {
    "take the program seat": "BE the executor, then make the executor prove itself.",
    "check the consumer side of the last hop": "Check the reader's path, not the writer's",
    "report a number a no-op could not produce": "Finish with a number a no-op could not have produced, plus the line where each action happens.",
    "zero is a broken path, not a result": "Zero is a failure of the walk, not a result.",
    "an unnamed line is not proof": "If you cannot name the line, that action is not proven to run.",
    "prove the instrument can answer otherwise": "Prove your check could have produced the other answer",
}
missing = [name for name, phrase in rules.items() if phrase not in text]
if missing:
    raise SystemExit(f"agentic-walkthrough: missing load-bearing rules: {', '.join(missing)}")
PY

printf 'agentic-walkthrough text contract passed\n'
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