Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

autoskill · k-dense-ai | DecimalAI

agent toolingby k-dense-ai

autoskill

k-dense-ai/autoskill

Source k-dense-ai/scientific-agent-skills ↗License MIT

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.

SkillScore86Maintained

Automatic

AI Engineer pack

Last verified 9/8/2026

What it changes

Passed 16 of 19 test cases with the skill, and 4 of 19 without it.

Without skill23%

With skill86%

Checks it passed that the model alone missed

Sets backend to claude in config.yaml.
Specifies Gemma-4-31B-it as the default model.
Uses an idle gap duration threshold of 10 minutes.

and 16 more in the full report

14 fixed5 passed either way3 still failing0 broke

Pass-rate lift: +64 pp
Tokens: +134%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 9/8/2026v2 · latest is v319 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/k-dense-ai-autoskill/SKILL.md https://app.decimal.ai/s/k-dense-ai-autoskill/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add k-dense-ai-autoskill, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/k-dense-ai-autoskill/ and pins it in .decimal/skills.lock

decimalai skills add k-dense-ai-autoskill

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/k-dense-ai-autoskill/SKILL.md https://app.decimal.ai/s/k-dense-ai-autoskill/SKILL.md

Raw file: /s/k-dense-ai-autoskill/SKILL.md ↗ · machine-readable summary at /s/k-dense-ai-autoskill.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

In the session segmentation step, user activity stream events are split into separate sessions whenever an inactivity pause occurs. What is the default idle gap duration threshold in minutes?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses an idle gap duration threshold of 10 minutes.	Missed	Passed

case-10 · gemini-3.6-flash · 9/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md240 lines14 filesincludes scripts

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() raises ScreenpipeUnreachable with 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 read SCREENPIPE_TOKEN, LM_API_TOKEN, ANTHROPIC_API_KEY, and FOUNDRY_API_KEY for 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.yaml is a checklist of literal, case-insensitive app/title substrings, not a Screenpipe-importable YAML file. Apply them in Screenpipe settings or as repeated --ignored-windows arguments; * 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.py pulls data over localhost HTTP. scripts/cluster.py reduces the timeline to app/duration/title summaries. scripts/redact.py scrubs 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 in local.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 clustered plan.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.md for 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

Track record

Benchmark

16 / 19

test cases passed, vs 4 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/8/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

k-dense-ai / scientific-agent-skills

skills/autoskill/SKILL.md

View on GitHub ↗

License MIT licenseImported 10/8/2026Version v3Bundled 13 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

lingxling/autoskillObserve 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 ruNear-identical description+65 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

autoskill

Overview

When to Use This Skill

Privacy Posture

Prerequisites

1. Screenpipe daemon

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills