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_match_skills.py
View on GitHubfrom pathlib import Path
from match_skills import load_skill_descriptions, top_k_matches
SKILL_TEMPLATE = """---
name: {name}
description: {description}
---
# {name}
"""
def _write_skill(root: Path, name: str, description: str) -> None:
d = root / name
d.mkdir(parents=True, exist_ok=True)
(d / "SKILL.md").write_text(SKILL_TEMPLATE.format(name=name, description=description))
def test_load_skill_descriptions_reads_frontmatter(tmp_path: Path):
_write_skill(tmp_path, "literature-review", "Systematic literature reviews across databases.")
_write_skill(tmp_path, "latex-posters", "Create conference posters in LaTeX.")
skills = load_skill_descriptions(tmp_path)
by_name = {s["name"]: s for s in skills}
assert set(by_name) == {"literature-review", "latex-posters"}
assert by_name["literature-review"]["description"].startswith("Systematic literature reviews")
def test_load_skill_descriptions_skips_directories_without_skill_md(tmp_path: Path):
_write_skill(tmp_path, "real-skill", "A real skill.")
(tmp_path / "empty-dir").mkdir()
skills = load_skill_descriptions(tmp_path)
assert [s["name"] for s in skills] == ["real-skill"]
def _keyword_embedder(text: str):
# deterministic, tiny vector indexed by known keywords
keywords = ["paper", "poster", "molecule"]
return [1.0 if k in text.lower() else 0.0 for k in keywords]
def test_top_k_matches_ranks_by_cosine_similarity():
skills = [
{"name": "literature-review", "description": "search and summarize papers"},
{"name": "latex-posters", "description": "create academic posters"},
{"name": "rdkit", "description": "molecule cheminformatics"},
]
query = "I spent time reading papers"
results = top_k_matches(query, skills, embedder=_keyword_embedder, k=2)
assert len(results) == 2
assert results[0]["name"] == "literature-review"
assert results[0]["score"] > results[1]["score"]
def test_top_k_matches_returns_all_when_k_exceeds_skills():
skills = [
{"name": "a", "description": "paper work"},
{"name": "b", "description": "poster work"},
]
results = top_k_matches("paper", skills, embedder=_keyword_embedder, k=10)
assert len(results) == 2
def test_top_k_matches_handles_zero_vectors_without_crashing():
skills = [{"name": "a", "description": "unrelated text"}]
results = top_k_matches("unrelated text query", skills,
embedder=lambda _: [0.0, 0.0, 0.0], k=1)
assert len(results) == 1
assert results[0]["score"] == 0.0
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 |