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 |
config.yaml
View on GitHub# autoskill configuration
#
# LLM backend for skill synthesis. Detection/clustering always runs locally;
# only redacted cluster summaries are sent to the LLM.
#
# Local is the default; summaries stay local when the endpoint is loopback.
# Cloud backends (claude, foundry) are available for users who explicitly
# opt in; see the backend sections below.
backend: local # local | claude | foundry
# Per-backend settings. Only the selected backend's block is used.
local:
# LM Studio exposes an OpenAI-compatible server. Start it from the
# "Developer" tab; the default port is 1234.
endpoint: http://localhost:1234/v1
# Load your installed model with --identifier autoskill-local, or use its
# exact /v1/models ID. Set LM_API_TOKEN if server auth is enabled.
model: autoskill-local
claude:
model: claude-opus-4-7
# api_key read from ANTHROPIC_API_KEY env var
foundry:
endpoint: https://your-resource.services.ai.azure.com/anthropic
model: claude-opus-4-7
# model must be your deployment name; API-key authentication only.
# api_key read from FOUNDRY_API_KEY env var
# Screenpipe HTTP endpoint. For TLS, point this at your local Caddy proxy
# (see references/https-proxy.md).
screenpipe:
url: http://localhost:3030
# Screenpipe requires a bearer token for its local API. Either set `token`
# here, or export SCREENPIPE_TOKEN in your environment (preferred — keeps
# the token out of version control). Retrieve with: `screenpipe auth token`.
# token: your-token-here
# Embedding model for matching against existing scientific skills.
# Inference is local; initial installation can download from Hugging Face.
embeddings:
model: sentence-transformers/all-MiniLM-L6-v2
local_files_only: false # true requires a pre-existing local model/cache
# Clustering thresholds.
cluster:
min_session_minutes: 5 # skip sessions shorter than this
idle_gap_minutes: 10 # new session after this much inactivity
min_cluster_size: 2 # need this many similar sessions before proposing
# Local redaction is always applied to event text, app names, and titles.
# It is defense-in-depth, not complete anonymization.
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 |