CtrlK
BlogDocsLog inGet started
Tessl Logo

jbaruch/auto-skill-discovery

Automated pipeline that takes a company name and produces a custom Tessl skill plus an eval report showing per-scenario lift (baseline agent vs with-skill agent). A1 MVP cell of the produce/consume × personalization 2x2.

88

1.45x
Quality

86%

Does it follow best practices?

Impact

89%

1.45x

Average score across 13 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-9/

Initial Discovery Intake: Siemens

Problem/Feature Description

Your team received a request to run discovery on "Siemens" — a name that appeared on the attendee list for an industrial IoT conference. Before investing time in full source research and skill-target analysis, the pipeline runs a preliminary intake step to check whether the input is well-formed enough to proceed.

Run the discovery intake for Siemens. Start by resolving the company identity: check for any rebrands, acquisitions, or "doing business as" registrations that might affect which GitHub org or docs portal to key searches against. Then assess whether "Siemens" as a bare name is a coherent target for a single discovery run, or whether it represents a structure that would require further scoping before the full pipeline can produce a meaningful result.

Persist whatever output is appropriate for this stage to a file named discovery.json in your working directory.

Output Specification

Produce a file named discovery.json that reflects the outcome of the intake step.

Also produce a file named intake-notes.md with a brief explanation of your findings and the reasoning behind the output — this will be reviewed by the team before they decide how to re-invoke the pipeline.

evals

discovery-output-contract.md

README.md

tile.json