charlieviettq/awesome-agent-skill / .claude/skills/autoskill
autoskill
VerifiedObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.1 KB |
| config.yaml | config | 2.0 KB |
| references/https-proxy.md | markdown | 1.5 KB |
| references/screenpipe-config.yaml | config | 1.5 KB |
| scripts/autoskill.py | script | 1.1 KB |
| scripts/backends.py | script | 2.3 KB |
| scripts/cluster.py | script | 1.7 KB |
| scripts/doctor.py | script | 3.4 KB |
| scripts/fetch_window.py | script | 1.1 KB |
| scripts/match_skills.py | script | 1.3 KB |
| scripts/promote.py | script | 1.5 KB |
| scripts/redact.py | script | 1.6 KB |
| scripts/run.py | script | 7.2 KB |
| scripts/synthesize.py | script | 2.3 KB |
| tests/conftest.py | script | 113 B |
| tests/smoke_lmstudio.py | script | 2.0 KB |
| tests/test_backends.py | script | 4.2 KB |
| tests/test_cli.py | script | 1.5 KB |
| tests/test_cluster.py | script | 2.7 KB |
| tests/test_doctor.py | script | 3.0 KB |
| tests/test_e2e.py | script | 11.9 KB |
| tests/test_fetch_window.py | script | 3.7 KB |
| tests/test_match_skills.py | script | 2.5 KB |
| tests/test_promote.py | script | 3.5 KB |
| tests/test_redact.py | script | 4.5 KB |
| tests/test_run.py | script | 8.0 KB |
| tests/test_synthesize.py | script | 3.1 KB |
tests/test_fetch_window.py
View on GitHubimport httpx
import pytest
from fetch_window import fetch_window
def _make_client(handler):
transport = httpx.MockTransport(handler)
return httpx.Client(transport=transport, base_url="http://localhost:3030")
def _ocr_event(ts: str, app: str, title: str, text: str) -> dict:
return {
"type": "OCR",
"content": {"timestamp": ts, "app_name": app, "window_name": title, "text": text},
}
def test_fetch_calls_search_endpoint_with_time_window_params():
calls = []
def handler(request: httpx.Request) -> httpx.Response:
calls.append(request)
return httpx.Response(200, json={"data": [], "pagination": {"limit": 50, "offset": 0, "total": 0}})
client = _make_client(handler)
fetch_window(client, start_time="2026-04-17T00:00:00Z", end_time="2026-04-17T04:00:00Z")
assert calls, "expected at least one HTTP call"
assert calls[0].url.path == "/search"
params = dict(calls[0].url.params)
assert params["start_time"] == "2026-04-17T00:00:00Z"
assert params["end_time"] == "2026-04-17T04:00:00Z"
def test_fetch_normalizes_ocr_events_into_unified_schema():
def handler(request: httpx.Request) -> httpx.Response:
return httpx.Response(200, json={
"data": [_ocr_event("2026-04-17T10:00:00Z", "VSCode", "paper.tex", "hello")],
"pagination": {"limit": 50, "offset": 0, "total": 1},
})
events = fetch_window(_make_client(handler), "2026-04-17T00:00:00Z", "2026-04-17T23:59:59Z")
assert len(events) == 1
e = events[0]
assert e["app"] == "VSCode"
assert e["window_title"] == "paper.tex"
assert e["text"] == "hello"
assert e["content_type"] == "ocr"
assert e["ts"] == "2026-04-17T10:00:00Z"
def test_fetch_paginates_until_all_results_collected():
pages = [
{"data": [_ocr_event("2026-04-17T10:00:00Z", "App", "t1", "a")] * 2,
"pagination": {"limit": 2, "offset": 0, "total": 3}},
{"data": [_ocr_event("2026-04-17T10:05:00Z", "App", "t2", "b")],
"pagination": {"limit": 2, "offset": 2, "total": 3}},
]
call_count = {"n": 0}
def handler(request: httpx.Request) -> httpx.Response:
page = pages[call_count["n"]]
call_count["n"] += 1
return httpx.Response(200, json=page)
events = fetch_window(_make_client(handler), "2026-04-17T00:00:00Z", "2026-04-17T23:59:59Z", page_size=2)
assert call_count["n"] == 2
assert len(events) == 3
def test_fetch_returns_empty_list_when_no_results():
def handler(request):
return httpx.Response(200, json={"data": [], "pagination": {"limit": 50, "offset": 0, "total": 0}})
events = fetch_window(_make_client(handler), "2026-04-17T00:00:00Z", "2026-04-17T23:59:59Z")
assert events == []
def test_fetch_sends_bearer_token_when_provided():
seen = []
def handler(request):
seen.append(request)
return httpx.Response(200, json={"data": [], "pagination": {"limit": 50, "offset": 0, "total": 0}})
fetch_window(_make_client(handler), "a", "b", token="secret-123")
assert seen[0].headers.get("authorization") == "Bearer secret-123"
def test_fetch_omits_auth_header_when_no_token():
seen = []
def handler(request):
seen.append(request)
return httpx.Response(200, json={"data": [], "pagination": {"limit": 50, "offset": 0, "total": 0}})
fetch_window(_make_client(handler), "a", "b")
assert "authorization" not in {k.lower() for k in seen[0].headers.keys()}
def test_fetch_raises_on_http_error():
def handler(request):
return httpx.Response(500, text="server down")
with pytest.raises(httpx.HTTPStatusError):
fetch_window(_make_client(handler), "2026-04-17T00:00:00Z", "2026-04-17T23:59:59Z")
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: 472k | 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 |