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/cluster.py
View on GitHubfrom collections import defaultdict
def segment_sessions(events, idle_gap_seconds, min_session_seconds):
if not events:
return []
events = sorted(events, key=lambda e: e["ts"])
groups = [[events[0]]]
for prev, curr in zip(events, events[1:]):
if curr["ts"] - prev["ts"] > idle_gap_seconds:
groups.append([curr])
else:
groups[-1].append(curr)
sessions = []
for group in groups:
duration = group[-1]["ts"] - group[0]["ts"]
if duration < min_session_seconds:
continue
apps, seen = [], set()
for evt in group:
if evt["app"] not in seen:
seen.add(evt["app"])
apps.append(evt["app"])
sessions.append({
"start_ts": group[0]["ts"],
"end_ts": group[-1]["ts"],
"duration_seconds": duration,
"apps": apps,
"window_titles": [e["window_title"] for e in group if e.get("window_title")],
})
return sessions
def cluster_sessions(sessions, min_cluster_size):
buckets = defaultdict(list)
for s in sessions:
buckets[tuple(s["apps"])].append(s)
clusters = []
for apps, members in buckets.items():
if len(members) < min_cluster_size:
continue
example_titles = []
for m in members:
if m["window_titles"]:
example_titles.append(m["window_titles"][0])
clusters.append({
"apps": list(apps),
"session_count": len(members),
"total_duration_seconds": sum(m["duration_seconds"] for m in members),
"example_titles": example_titles,
})
return clusters
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 |