LeoYeAI/agent-master-skills / skills/autoskill
autoskill
VerifiedAnalyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts or composition recipes for review. Requires a reachable Screenpipe HTTP API, normally on localhost:3030. Detection and embedding inference run locally; the selected LLM receives redacted app/title cluster summaries and matched skill descriptions. Use only when the user explicitly asks to analyze their recent work and propose skills.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 34 B |
| SKILL.md | skill md | 16.5 KB |
| config.yaml | config | 2.1 KB |
| references/api-contracts.md | markdown | 7.4 KB |
| references/https-proxy.md | markdown | 2.2 KB |
| references/screenpipe-config.yaml | config | 1.4 KB |
| scripts/autoskill.py | script | 1.1 KB |
| scripts/backends.py | script | 5.1 KB |
| scripts/cluster.py | script | 1.7 KB |
| scripts/doctor.py | script | 4.5 KB |
| scripts/fetch_window.py | script | 2.8 KB |
| scripts/match_skills.py | script | 1.2 KB |
| scripts/promote.py | script | 1.5 KB |
| scripts/redact.py | script | 1.6 KB |
| scripts/run.py | script | 7.4 KB |
| scripts/synthesize.py | script | 2.7 KB |
scripts/fetch_window.py
View on GitHubimport warnings
_MAX_PAGES = 10_000 # bounded exit: hard ceiling so the loop cannot spin forever
def fetch_window(client, start_time, end_time, page_size=50, token=None):
"""Fetch local timeline rows; memories/parsed records are not activity events."""
if isinstance(page_size, bool) or not isinstance(page_size, int) or page_size < 1:
raise ValueError("page_size must be a positive integer")
events = []
skipped_types = set()
offset = 0
headers = {"Authorization": f"Bearer {token}"} if token else {}
for _page in range(_MAX_PAGES):
response = client.get("/search", params={
"start_time": start_time,
"end_time": end_time,
"limit": page_size,
"offset": offset,
"content_type": "all",
"include_frames": "false",
"include_cloud": "false",
# Upstream filter_pii can use a remote enclave. Redact locally instead.
"filter_pii": "false",
}, headers=headers)
response.raise_for_status()
payload = response.json()
data = payload.get("data")
pagination = payload.get("pagination", {})
total = pagination.get("total")
if (not isinstance(data, list) or isinstance(total, bool)
or not isinstance(total, int) or total < 0):
raise ValueError("Screenpipe /search must return data[] and pagination.total")
if pagination.get("offset", offset) != offset:
raise ValueError("Screenpipe /search returned an unexpected pagination offset")
for item in data:
content = item.get("content", {})
kind = item.get("type", "").lower()
if kind not in {"ocr", "ui", "accessibility", "input", "audio"}:
skipped_types.add(kind or "unknown")
continue
if not content.get("timestamp"):
raise ValueError(f"Screenpipe {kind} row has no timestamp")
events.append({
"ts": content.get("timestamp"),
"app": content.get("app_name") or "",
"window_title": content.get("window_name") or content.get("window_title") or "",
"text": content.get("text") or content.get("transcription") or content.get("text_content") or "",
"content_type": kind,
})
offset += len(data)
if offset >= total:
break
if not data:
raise RuntimeError("Screenpipe search ended before pagination.total; rerun a fixed time window")
else:
raise RuntimeError("Screenpipe search exceeded the page limit; request a smaller time window")
if skipped_types:
warnings.warn("Skipped non-timeline Screenpipe types: " + ", ".join(sorted(skipped_types)),
stacklevel=2)
return events
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 |