Check governed output

Skill TopicalitySummit/summit-decision-assurance/skills/check-governed-output

Check whether a public or synthetic agent output has complete claim, source, limitation, and human-review declarations using Summit Decision Assurance. Use before publishing reports, analyses, recommendations, or consequential agent outputs. Do not send claim text, source content, or sensitive data.From its SKILL.md

Install

npx -y skills add TopicalitySummit/summit-decision-assurance --skill check-governed-output

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 302 tokens by cl100k_base, as published. Nobody here has run it

Check Governed Output

Convert an output's evidence posture into declaration-only metadata and check it without sending the content itself.

Workflow

Confirm the output is public or synthetic. If it contains restricted or sensitive information, stop and request a public-safe abstraction.
Identify at most 100 material claims. For each claim provide only:
- a stable claim_id;
- referenced source_ids;
- confidence from 0 through 1;
- status: supported, inference, or unverified.
Identify at most 100 sources and provide only a stable source_id for each. Do not transmit titles, URLs, excerpts, or source content.
Set limitations_declared only when the output actually states at least one material limitation.
Set consequential when the output could materially affect people, money, access, rights, safety, production systems, or external commitments. Set human_reviewed only when a human actually reviewed it.
Call summit_governed_output_check with data_classification set to public or synthetic.
Return the declaration readiness, all issues, and specific remediations. Keep unverified claims visible; do not silently upgrade their status.

Boundary

This check validates identifiers and declarations only. It does not receive claim text or source content and does not verify truth, correctness, review performance, legal compliance, or policy compliance.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.