CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

service-factory/gds-assessment-plugin

Granular 4-phase, 4-role GDS Service Standard assurance skills, panel orchestrator, and synthesis engine.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

README.mdskills/gds-assessment-how-to/evidence-kit/

Evidence kit

Fill the folder for the phase the service is in. Do not fill a later phase early. A production design in Discovery, or a production environment treated as the beta platform in Alpha, fails that phase.

FolderCopy it when
discovery/You are defining the problem and can still stop or join another service
alpha/You are testing risky ideas with throwaway prototypes and spikes
beta/Real users are on a private beta, and you are preparing the full 14-point panel
live/The service is running, and you can show operation, research, and published performance since the last assessment

Where a template asks for something you do not have, write Not held and the owner. An empty heading is missing evidence.

panel/dialogue.md stores the full chat after each question is closed. The panel asks in the conversation, one question at a time. Later assessments read the file with the other evidence.

coverage.md lists the files in each phase and the red lines those files are there to catch. The scoring rules are in the plugin at rules/phase-expectations.md.

skills

gds-assessment-how-to

build_past_assessment_catalogue.py

create-evidence-kit.py

create-example.py

library_paths.py

reports_mcp_server.py

scrape_gds_reports.py

SKILL.md

.mcp.json

README.md

tile.json