Check assumptions
Skill control-decks/reality-check/plugins/reality-check/skills/check-assumptions
A verification deck for checking sources, assumptions, and concrete targets without replacing the result.
npx -y skills add control-decks/reality-check --skill check-assumptionsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 17 days oldThe repository was created 17 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.
- 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.
What its author says it does
Copied from the file, not written here
Expose and classify the explicit and material implicit assumptions in the current HACP Working Object, appending an assumptions-checked annotation without replacing the object. Use only when the user invokes CHECK ASSUMPTIONS or explicitly asks to inspect current assumptions.
SKILL.md
2.1 KB, 420 tokens by cl100k_base, as published. Nobody here has run it
๐ง Check Assumptions
ID: reality-check/check-assumptions
HACP: 0.4
Kind: operation
Mode: annotate
Traits: read-only, evidence-annotation, assumption-classification
Default Binding: Full available conversation
Accepts: hacp/content, hacp/result
Produces: hacp/result, preserving the input kind and content and adding
reality-check/assumptions-checked with traits evidence and
assumption-evidence
Duration: once
Effect: Classify the material assumptions bound to the current object and append a scoped evidence annotation without replacing that object.
Limits: Do not invent hidden motives, psychological premises, or exhaustive edge cases. Keep missing evidence classified rather than fabricating support.
Check
- Extract explicit assumptions and only implicit assumptions required for the object to hold.
- Classify each as
supported,unsupported,unknown, ornot-testable-here. - Identify which unsupported or unknown assumptions could change the decision.
- Append the classification with the Binding actually inspected, its traits, content, and source. Preserve the object's Binding, status, kind, content, and existing annotations.
When this card initializes a combo without an object, its default Binding makes the check conversation-wide. After another operation, the current Working Object takes precedence and the check is local to that object. The annotation keeps that resolved scope while it transits.
Format
Contribute โ ๐ **CHECK ASSUMPTIONS** to the one complete combo trace, or
begin with > ๐ฏ **<binding>** โ ๐ **CHECK ASSUMPTIONS** when used alone.
Then use Assumptions and list only assumptions that materially affect the
result. Never emit a second trace or deck-status line.
What ships with it: 2 files
18.9 KB alongside SKILL.md
agents/
- openai.yaml305 B
assets/
- icon.png18.6 KB