autoskill
Auto-detects repeated research tasks on your screen and creates new agent skills to automate them.
Install
mkdir -p .claude/skills/autoskill && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11831" && unzip -o skill.zip -d .claude/skills/autoskill && rm skill.zipInstalls to .claude/skills/autoskill
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Observe 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.Key capabilities
- →Observe user screen activity via screenpipe daemon
- →Detect repeated research workflows from screenpipe data
- →Match detected patterns against existing scientific-agent-skills
- →Draft new skills for uncovered workflow patterns
- →Draft composition recipes that chain existing skills
- →Cluster repeated workflow patterns from screenpipe's local HTTP API
How it works
This skill queries a local screenpipe daemon to analyze user workflow history, clusters repeated patterns, and then drafts new skills or composition recipes based on these patterns.
Inputs & outputs
When to use autoskill
- →Automating repetitive research tasks
- →Identifying workflow patterns
- →Creating new agent automation skills
About this skill
autoskill
Requires a running screenpipe daemon. This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default
http://localhost:3030). If the daemon isn't running,run()raisesScreenpipeUnreachablewith install instructions.
Network access & environment variables. This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of
http://localhost:1234/v1(LM Studio, default),https://api.anthropic.com(opt-in Claude), or a user-supplied BYOK Foundry gateway. The adapters readSCREENPIPE_TOKEN,LM_API_TOKEN,ANTHROPIC_API_KEY, andFOUNDRY_API_KEYfor the corresponding configured service. HTTPX also honors its standard proxy and CA environment settings; sentence-transformers uses Hugging Face cache/download settings. Opt-in cloud backends receive redacted cluster summaries and matched skill descriptions. Embedding-model installation may also download public model files; local inference does not imply zero network access.
Overview
Turn the user's own workflow history — captured passively by the local screenpipe daemon — into new skills. This skill is on-demand: the user invokes it with a time window, it queries screenpipe's local HTTP API, clusters repeated workflow patterns, compares each pattern against the existing skills in this repo, and produces a staged folder of proposals the user can review, edit, and promote.
When to Use This Skill
Invoke this skill when the user asks to:
- "Analyze my last 4 hours / day / week and propose new skills."
- "Look at what I've been doing and tell me what's not covered yet."
- "Draft a skill from my recent workflow."
- "Find composition recipes for workflows I repeat."
Do not invoke it for one-off questions about screenpipe itself, for real-time screen queries, or without an explicit user request — the skill analyzes sensitive local content and must stay explicitly user-triggered.
Privacy Posture
- Configure capture filtering in Screenpipe before collecting history.
references/screenpipe-config.yamlis a checklist of literal, case-insensitive app/title substrings, not a Screenpipe-importable YAML file. Apply them in Screenpipe settings or as repeated--ignored-windowsarguments;*is not a glob. Check exclusions with synthetic windows. Filtering cannot remove sensitive material already captured or guarantee complete exclusion. - Raw OCR is not sent to the synthesis backend by this pipeline.
scripts/fetch_window.pypulls data over localhost HTTP.scripts/cluster.pyreduces the timeline to app/duration/title summaries.scripts/redact.pyscrubs recognizable emails, API keys, bearer tokens, and selected phone formats as defense-in-depth before any cluster summary reaches the LLM. - LLM backend defaults to
local. Use an already installed chat model served by LM Studio; its exact server model ID belongs inlocal.model. Summaries stay on the machine only while this endpoint is loopback. A remote HTTPS endpoint also sends summaries off-host. Cloud backends (claude,foundry) remain opt-in. Detection and embedding inference run locally regardless of backend choice. - Dry-run mode (
--dry-run) skips skill matching and LLM synthesis and writes a clusteredplan.md. Review the retained app names and window titles before selecting a cloud backend; the regex scrubber does not guarantee anonymization or removal of unpublished research details. - TLS for localhost (optional, for corporate policy): see
references/https-proxy.mdfor the Caddy pattern.
Prerequisites
1. Screenpipe daemon
Either install the official release or build from source. Either way the daemon binds HTTP on localhost:3030 by default.
From source (recommended if you want the CLI daemon without the desktop GUI):
git clone --depth 1 https://github.com/screenpipe/screenpipe.git
cd screenpipe
cargo build -p screenpipe-engine --release
# System deps (macOS): cmake + full Xcode.app (not just Command Line Tools).
# brew install cmake
# # if xcodebuild plug-ins error: sudo xcodebuild -runFirstLaunch
./target/release/screenpipe doctor # confirm permissions + ffmpeg
./target/release/screenpipe record --disable-audio --use-pii-removal \
--ignored-windows "1Password" --ignored-windows "Bitwarden" \
--ignored-windows "Private Browsing" --ignored-windows "Incognito"
This source-build example is illustrative and was not compiled in the API review. Check the installed screenpipe record --help; permissions and system dependencies vary by platform/release. On macOS, grant the requested Screen Recording/Accessibility permissions and relaunch. Review the full deny-list before real capture.
2. Screenpipe API token
Current Screenpipe enables API auth by default; protected routes such as /search require a bearer token even on loopback. /health is exempt, so a successful health check does not validate search authorization. For an authenticated instance, retrieve its local API token:
export SCREENPIPE_TOKEN="$(screenpipe auth token)"
(Or set screenpipe.token directly in config.yaml — env var is preferred since it keeps secrets out of version control.)
Screenpipe connections permit HTTP only on loopback; remote endpoints require HTTPS. Generated draft names must be valid skill names, so model output cannot write outside the proposal directory.
3. Python environment
Create a separate environment; do not add scientific dependencies to the repository environment:
uv venv .venv-autoskill --python 3.12
uv pip install --python .venv-autoskill/bin/python httpx==0.28.1 pyyaml==6.0.3 sentence-transformers==6.1.0
source .venv-autoskill/bin/activate
The public sentence-transformers/all-MiniLM-L6-v2 model downloads on first use. For an existing cache, set embeddings.local_files_only: true to prevent download attempts. Its 384-dimensional embeddings truncate inputs beyond 256 word pieces; long summaries may lose detail. Similarity is a retrieval heuristic, not proof of workflow equivalence.
4. Local LLM (default path) — LM Studio
- Install LM Studio.
- Choose a chat model already installed on your machine (
lms ls). Match the context length to its supported limits and available memory; no particular GPU fit is assumed. - Load it with a stable identifier and start the API server explicitly:
lms load <installed-model-key> --identifier autoskill-local
lms server start --port 1234
lms server status
This setup is illustrative; no model was downloaded or inferred during this review. lms load does not itself start the HTTP server. If LM Studio's Require Authentication option is enabled (0.4.0+), set LM_API_TOKEN to a token created in its server settings. doctor checks the configured ID against /v1/models; the list can include JIT-loadable models and does not prove inference succeeds.
5. Cloud LLM backends (optional, opt-in)
Only if you explicitly opt out of local:
claude: setANTHROPIC_API_KEY, flipbackend: claudeinconfig.yaml.foundry: setFOUNDRY_API_KEY, flipbackend: foundry, and setfoundry.endpointtohttps://<resource>.services.ai.azure.com/anthropic(or a gateway with that same Messages contract). Setfoundry.modelto the deployment name. This adapter supports API-key auth, not Entra token acquisition; Entra-only deployments need a different client.
Architecture
screenpipe daemon (user-installed)
│ HTTP on localhost:3030
▼
scripts/fetch_window.py → normalized timeline events
scripts/redact.py → regex scrub (defense-in-depth)
scripts/cluster.py → sessions + clusters (local only)
scripts/match_skills.py → top-k vs discovered skills (local embeddings)
scripts/synthesize.py → LLM judge: reuse / compose / novel
│
▼
~/.autoskill/proposed/<timestamp>/ (default; override with --out)
├── report.md
├── composition-recipes/<name>/SKILL.md
└── new-skills/<name>/SKILL.md
scripts/promote.py → user-approved proposal → skills/<name>/
Workflow
The skill ships a unified CLI at scripts/autoskill.py with three subcommands:
python skills/autoskill/scripts/autoskill.py doctor --config skills/autoskill/config.yaml --skills-dir skills
python skills/autoskill/scripts/autoskill.py run --start <ISO-start> --end <ISO-end> --config skills/autoskill/config.yaml
python skills/autoskill/scripts/autoskill.py promote --proposed <proposal-dir> --skills-dir skills --name <skill>
0. Preflight with doctor
Before a full run, check connectivity and backend configuration:
python skills/autoskill/scripts/autoskill.py doctor \
--config skills/autoskill/config.yaml \
--skills-dir skills
The report covers config (backend choice valid), skills_dir (exists), screenpipe (public health endpoint reachable), and llm (LM Studio lists the configured model, or a cloud API key is present). It does not fetch history, verify Screenpipe search auth, test cloud credentials, run inference, or load embedding weights. Non-zero exit on any failure, with the offending line marked error.
1. Run the pipeline
export SCREENPIPE_TOKEN="$(screenpipe auth token)"
python skills/autoskill/scripts/autoskill.py run \
--start "2026-04-17T00:00:00Z" \
--end "2026-04-17T23:59:59Z" \
--config skills/autoskill/config.yaml \
--skills-dir skills
Proposals land in ~/.autoskill/proposed/<timestamp>/ by default, keeping experimental output out of the skills repo. Pass --out PATH to override.
Internally:
- Fetch —
fetch_windowuses/searchwith a fixed time window and limit/offset pagination, explicitly disables cloud results, frame images,
Content truncated.
When not to use it
- →For one-off questions about screenpipe itself
- →For real-time screen queries
- →Without an explicit user request to analyze workflow or propose skills
Prerequisites
Limitations
- →Requires a running screenpipe daemon locally on port 3030
- →Has no other data source than the local screenpipe HTTP API
- →Only redacted cluster summaries reach the LLM
How it compares
This skill automatically generates new automation skills or recipes by observing actual user screen activity, unlike manual skill creation or predefined templates.
Compared to similar skills
autoskill side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| autoskill (this skill) | 0 | 5mo | Review | Intermediate |
| session-logs | 8 | 6mo | Review | Intermediate |
| context-management-context-restore | 10 | 7mo | Review | Advanced |
| conversation-memory | 8 | 9mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by bg-szy
View all by bg-szy →You might also like
session-logs
openclaw
Search and analyze your own session logs (older/parent conversations) using jq.
context-management-context-restore
sickn33
Use when working with context management context restore
conversation-memory
davila7
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
zlibrary-to-notebooklm
zstmfhy
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。
workiq-copilot
github
Guides the Copilot CLI on how to use the WorkIQ CLI/MCP server to query Microsoft 365 Copilot data (emails, meetings, docs, Teams, people) for live context, summaries, and recommendations.
compound-learnings
parcadei
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".