xonika9/agent-skills / skills/x9-agent-instructions
x9-agent-instructions
VerifiedWrite or review prompts, task briefs, and agent-instruction files — «напиши промпт», «проверь инструкции», "review this agent prompt". Do not use as the primary workflow for repository onboarding files, skill authoring, ordinary prose, or executing or delegating the described task.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.2 KB |
| references/onboarding.json | config | 305 B |
| scripts/check_globals.py | script | 1.1 KB |
| scripts/test_check_globals.py | script | 3.0 KB |
scripts/test_check_globals.py
View on GitHub#!/usr/bin/env python3
"""Regression tests for byte-exact shared-core extraction."""
from pathlib import Path
from tempfile import TemporaryDirectory
import unittest
from check_globals import extract
START = b"<!-- BEGIN SHARED PERSONAL CORE -->"
END = b"<!-- END SHARED PERSONAL CORE -->"
SKILL_FILE = Path(__file__).resolve().parent.parent / "SKILL.md"
class ExtractTests(unittest.TestCase):
def write(self, directory: str, name: str, data: bytes) -> Path:
path = Path(directory) / name
path.write_bytes(data)
return path
def test_preserves_line_endings(self):
with TemporaryDirectory() as directory:
lf = self.write(directory, "lf.md", START + b"\nrule\n" + END)
crlf = self.write(directory, "crlf.md", START + b"\r\nrule\r\n" + END)
self.assertNotEqual(extract(lf), extract(crlf))
def test_rejects_duplicate_marker_pairs(self):
with TemporaryDirectory() as directory:
path = self.write(directory, "duplicate.md", START + END + START + END)
with self.assertRaises(ValueError):
extract(path)
class SkillContractTests(unittest.TestCase):
@classmethod
def setUpClass(cls):
cls.skill = SKILL_FILE.read_text(encoding="utf-8")
def test_review_is_report_first_and_approval_continues(self):
self.assertIn("For an inspection-only request, the first pass is report-only", self.skill)
self.assertIn("An explicit request to fix or update the prompt authorizes", self.skill)
self.assertIn("without asking for the same permission again", self.skill)
self.assertIn("After the user explicitly approves", self.skill)
self.assertIn("without requesting another approval", self.skill)
def test_review_explains_changes_before_complete_diff(self):
self.assertIn("Why these changes help", self.skill)
self.assertIn("lead with the practical improvement", self.skill)
self.assertIn("smallest complete proposed diff", self.skill)
self.assertIn("actual diff, changed-file summary", self.skill)
def test_skill_creator_can_load_subordinate_rubric(self):
self.assertIn("primary workflow for", self.skill)
self.assertIn("subordinate instruction-quality rubric", self.skill)
def test_installed_skills_use_names_not_machine_paths(self):
self.assertIn("Name an installed skill by its discoverable name", self.skill)
self.assertIn("never by a machine-specific `SKILL.md` path", self.skill)
self.assertIn("use a project-relative path and say why", self.skill)
self.assertIn("when the target runtime loads it automatically", self.skill)
def test_global_contract_includes_all_three_harnesses(self):
self.assertIn("`~/.config/opencode/AGENTS.md`", self.skill)
self.assertIn("`~/.claude/CLAUDE.md`", self.skill)
self.assertIn("`~/.codex/AGENTS.md`", self.skill)
self.assertIn("byte-identical in all three", self.skill)
if __name__ == "__main__":
unittest.main()
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: 471k | Updated | Claude CodeCodex | Verified | 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 |