lihaozheCharlie/the-way-here / knowledge-engine/skills/common/reasoning-lenses
common-reasoning-lenses
Verified为个人 Wiki 的查询、回信和解释性构建提供可动态发现的人物推理视角。它只改变怎样理解证据,不构成新证据,也不决定是否写入。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.9 KB |
| references/calibration-material.md | markdown | 1.8 KB |
| references/evidence-and-lens-guardrails.md | markdown | 1.5 KB |
| references/examples/benjamin-franklin-letter.md | markdown | 4.0 KB |
| references/examples/steve-jobs-letter.md | markdown | 4.1 KB |
| references/figures/albert-einstein.md | markdown | 5.7 KB |
| references/figures/benjamin-franklin.md | markdown | 5.8 KB |
| references/figures/charlie-munger.md | markdown | 5.7 KB |
| references/figures/elon-musk.md | markdown | 5.5 KB |
| references/figures/richard-feynman.md | markdown | 5.5 KB |
| references/figures/steve-jobs.md | markdown | 5.6 KB |
| references/figures/warren-buffett.md | markdown | 5.6 KB |
| references/figures/yanni.md | markdown | 6.4 KB |
| scripts/list_lenses.py | script | 5.5 KB |
| tests/cross-domain-regression.md | markdown | 5.5 KB |
| tests/test_dynamic_discovery.py | script | 3.3 KB |
tests/test_dynamic_discovery.py
View on GitHub#!/usr/bin/env python3
from __future__ import annotations
import importlib.util
import json
import subprocess
import sys
import tempfile
from pathlib import Path
SCRIPT = Path(__file__).resolve().parents[1] / "scripts/list_lenses.py"
SPEC = importlib.util.spec_from_file_location("list_lenses", SCRIPT)
if SPEC is None or SPEC.loader is None:
raise RuntimeError(f"无法加载 {SCRIPT}")
MODULE = importlib.util.module_from_spec(SPEC)
SPEC.loader.exec_module(MODULE)
def lens_text(lens_id: str, display_name: str) -> str:
headings = "\n\n".join(
f"{heading}\n\n测试内容。" for heading in MODULE.REQUIRED_HEADINGS
)
return f'''---
lens_id: "{lens_id}"
display_name: "{display_name}"
attention: "测试注意力"
signals: "测试信号"
helper_use: "测试辅助边界"
---
# {display_name}
{headings}
'''
def main() -> int:
with tempfile.TemporaryDirectory(prefix="reasoning-lenses-") as tmp:
root = Path(tmp)
(root / "first-lens.md").write_text(
lens_text("first-lens", "第一视角"), encoding="utf-8"
)
lenses, errors = MODULE.load_lenses(root)
assert not errors, errors
assert [lens["lens_id"] for lens in lenses] == ["first-lens"]
# 模拟后续只新增人物文件;发现器和下游协议均不修改。
(root / "future-lens.md").write_text(
lens_text("future-lens", "未来视角"), encoding="utf-8"
)
lenses, errors = MODULE.load_lenses(root)
assert not errors, errors
assert [lens["lens_id"] for lens in lenses] == [
"first-lens",
"future-lens",
]
cli = subprocess.run(
[sys.executable, str(SCRIPT), "--root", str(root), "--json"],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
check=False,
)
assert cli.returncode == 0, cli.stderr
discovered = json.loads(cli.stdout)
assert [lens["lens_id"] for lens in discovered] == [
"first-lens",
"future-lens",
]
# 已有路由与推理章节仍不能替代新增的成文校准契约。
for heading in ("## 特色视角与辨别", "## 成文校准案例"):
candidate = root / "uncalibrated-lens.md"
candidate.write_text(
lens_text("uncalibrated-lens", "缺少校准的视角").replace(
f"{heading}\n\n测试内容。", ""
), encoding="utf-8"
)
_, errors = MODULE.load_lenses(root)
assert any(heading in error for error in errors), errors
candidate.unlink()
(root / "broken-lens.md").write_text(
'---\nlens_id: "broken-lens"\n---\n# 不完整视角\n',
encoding="utf-8",
)
_, errors = MODULE.load_lenses(root)
assert errors, "不完整人物文件必须校验失败"
cli = subprocess.run(
[sys.executable, str(SCRIPT), "--root", str(root), "--check"],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
check=False,
)
assert cli.returncode != 0, "命令行校验必须拒绝不完整人物文件"
print("dynamic-discovery=ok")
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |