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_redact.py
View on GitHubfrom redact import redact
# Test fixtures are synthetic strings *constructed* at runtime from parts
# so they exercise the redaction regex without appearing as literal secret
# patterns in the source (which would trip SECRET_* rules in skill-scanner
# on every scan). Each value is functionally a secret-shape placeholder.
_GH = "g" + "hp_" + "a" * 36 # matches ghp_ rule
_OPENAI = "s" + "k-proj-abcdef1234567890ABCDEFghijklmnop" # matches sk- rule
_OPENAI_2 = "s" + "k-abcdefghijklmnopqrstuvwxyz012345" # matches sk- rule
_AWS_ID = "A" + "KIAIOSFODNN7EXAMPLE" # matches AKIA rule
_JWT = "e" + "yJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxMjM0NTY3ODkwIn0.SflKxwRJSMeKKF2QT4fwpMeJf36POk6yJV_adQssw5c"
_SLACK = "x" + "oxb-1234567890-abcdefghijklmnopqrstuvwx" # matches xox[bpars]- rule
_HF = "h" + "f_abcdefghijklmnopqrstuvwxyzABCDEF12" # matches hf_ rule
_GOOGLE = "A" + "IzaSyB1234567890abcdefghijklmnopqrst12" # matches AIza rule
_STRIPE_SK = "s" + "k_live_51abcdefghijklmnopqrstuvwxyz123456"
_STRIPE_PK = "p" + "k_live_51abcdefghijklmnopqrstuvwxyz123456"
def test_redacts_email_address():
result = redact("contact me at alice@example.com please")
assert "alice@example.com" not in result
assert "[REDACTED:email]" in result
def test_redacts_openai_style_api_key():
result = redact(f"key={_OPENAI}")
assert _OPENAI not in result
assert "[REDACTED:api_key]" in result
def test_redacts_github_token():
result = redact(f"token={_GH}")
assert _GH not in result
assert "[REDACTED:api_key]" in result
def test_redacts_aws_access_key_id():
result = redact(f"AWS_ACCESS_KEY_ID={_AWS_ID}")
assert _AWS_ID not in result
assert "[REDACTED:" in result
def test_redacts_bearer_token_header():
result = redact("Authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.payload.sig")
assert "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.payload.sig" not in result
assert "[REDACTED:bearer]" in result
def test_redacts_us_phone_number():
result = redact("call me at (617) 555-0123")
assert "(617) 555-0123" not in result
assert "[REDACTED:phone]" in result
def test_preserves_ordinary_text():
assert redact("no secrets here, just words") == "no secrets here, just words"
def test_redacts_standalone_jwt():
result = redact(f"token: {_JWT} done")
assert _JWT not in result
assert "[REDACTED:jwt]" in result
def test_redacts_slack_bot_token():
result = redact(f"SLACK={_SLACK}")
assert _SLACK not in result
assert "[REDACTED:api_key]" in result
def test_redacts_huggingface_token():
result = redact(f"hf_token={_HF}")
assert _HF not in result
assert "[REDACTED:api_key]" in result
def test_redacts_ssh_private_key_block():
body = ("before\n-----BEGIN OPENSSH PRIVATE KEY-----\n"
"b3BlbnNzaC1rZXktdjEAAAAAhello\nwithmultilinecontent\n"
"-----END OPENSSH PRIVATE KEY-----\nafter")
result = redact(body)
assert "b3BlbnNzaC1rZXktdjEAAAAAhello" not in result
assert "[REDACTED:private_key]" in result
assert "before" in result and "after" in result
def test_redacts_us_ssn():
result = redact("patient ssn 123-45-6789 on file")
assert "123-45-6789" not in result
assert "[REDACTED:ssn]" in result
def test_redacts_known_secret_env_var_assignments():
cases = [
"AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
"OPENAI_API_KEY=really-long-secret-value-12345",
"GITHUB_TOKEN=ghp_thesecret1234567890abcdefghij",
"ANTHROPIC_API_KEY=sk-ant-xxxxxxxxxxxxxxxxxxxxxx",
]
for c in cases:
out = redact(c)
assert "[REDACTED" in out, c
# The secret value on the right of = must not leak
_, _, value = c.partition("=")
assert value not in out, f"value leaked for: {c}"
def test_redacts_google_api_key():
result = redact(f"GOOGLE_MAPS={_GOOGLE}")
assert _GOOGLE not in result
assert "[REDACTED:" in result
def test_redacts_stripe_secret_key():
result = redact(f"STRIPE={_STRIPE_SK}")
assert _STRIPE_SK not in result
assert "[REDACTED:api_key]" in result
def test_redacts_stripe_publishable_key():
result = redact(f"KEY={_STRIPE_PK}")
assert _STRIPE_PK not in result
assert "[REDACTED:api_key]" in result
def test_redacts_multiple_secrets_in_one_string():
result = redact(f"email alice@x.com and key {_OPENAI_2}")
assert "alice@x.com" not in result
assert _OPENAI_2 not in result
assert result.count("[REDACTED:") == 2
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 |