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_synthesize.py
View on GitHubimport json
import pytest
from synthesize import synthesize, SynthesisError
class StubBackend:
def __init__(self, response: str):
self.response = response
self.last_prompt = None
def __call__(self, prompt: str) -> str:
self.last_prompt = prompt
return self.response
def _cluster():
return {
"apps": ["Chrome", "Zotero"],
"session_count": 4,
"total_duration_seconds": 7200,
"example_titles": ["PubMed search", "bioRxiv preprint"],
}
def _top_k():
return [
{"name": "literature-review", "description": "Systematic literature reviews", "score": 0.82},
{"name": "citation-management", "description": "Find and format citations", "score": 0.71},
]
def test_prompt_includes_cluster_and_candidate_skills():
backend = StubBackend(json.dumps({"verdict": "reuse", "target": "literature-review"}))
synthesize(_cluster(), _top_k(), backend=backend)
assert "Chrome" in backend.last_prompt
assert "Zotero" in backend.last_prompt
assert "literature-review" in backend.last_prompt
assert "citation-management" in backend.last_prompt
def test_parses_reuse_verdict():
backend = StubBackend(json.dumps({"verdict": "reuse", "target": "literature-review"}))
result = synthesize(_cluster(), _top_k(), backend=backend)
assert result["verdict"] == "reuse"
assert result["target"] == "literature-review"
assert result.get("skill_body") is None
def test_parses_compose_verdict_and_returns_skill_body():
body = "---\nname: lit-review-flow\ndescription: chain lit review + citations\n---\n# flow"
backend = StubBackend(json.dumps({
"verdict": "compose",
"name": "lit-review-flow",
"skill_body": body,
}))
result = synthesize(_cluster(), _top_k(), backend=backend)
assert result["verdict"] == "compose"
assert result["name"] == "lit-review-flow"
assert result["skill_body"] == body
def test_parses_novel_verdict_and_returns_skill_body():
body = "---\nname: zotero-pubmed-helper\ndescription: new thing\n---\n# new"
backend = StubBackend(json.dumps({
"verdict": "novel",
"name": "zotero-pubmed-helper",
"skill_body": body,
}))
result = synthesize(_cluster(), _top_k(), backend=backend)
assert result["verdict"] == "novel"
assert result["skill_body"].startswith("---\nname: zotero-pubmed-helper")
def test_tolerates_json_wrapped_in_markdown_fence():
payload = json.dumps({"verdict": "reuse", "target": "literature-review"})
backend = StubBackend(f"Sure, here:\n```json\n{payload}\n```\n")
result = synthesize(_cluster(), _top_k(), backend=backend)
assert result["verdict"] == "reuse"
def test_raises_on_unparseable_response():
backend = StubBackend("not json at all, no way to parse")
with pytest.raises(SynthesisError):
synthesize(_cluster(), _top_k(), backend=backend)
def test_raises_on_unknown_verdict():
backend = StubBackend(json.dumps({"verdict": "weird"}))
with pytest.raises(SynthesisError):
synthesize(_cluster(), _top_k(), backend=backend)
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 |