Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →spec-kitty/spec-kitty-glossary-context
Curate and apply canonical terminology across Spec Kitty missions. Triggers: "update the glossary", "use canonical terms", "check terminology", "add a term", "fix term drift", "glossary conflicts", "resolve ambiguity", "review terminology consistency", "shape a domain model's terms", "validate domain language against code". Does NOT handle: runtime loop advancement, setup or repair requests, agent configuration, or direct code implementation tasks.
Passed 18 of 20 test cases with the skill, and 6 of 20 without it.
and 21 more in the full report
14 fixed4 passed either way0 still failing2 broke3 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
A runtime conflict with ID 'conf_89a12' blocked our mission '012-docs'. What exact spec-kitty command should a developer run to interactively resolve this conflict for that specific mission?
| Checked | Without skill | With skill |
|---|---|---|
| Provides the command spec-kitty glossary resolve conf_89a12 --mission 012-docs. | Missed | Passed |
The instructions your model reads when the skill loads.
Maintain semantic integrity by curating the project glossary, detecting term drift, and ensuring that all mission artifacts use canonical terminology.
Use this skill when the user wants to inspect, update, or enforce glossary terms. Do not use it for purely operational tasks like advancing the runtime loop or repairing an installation.
The glossary is a semantic integrity runtime — a 5-layer middleware pipeline that intercepts mission step execution, extracts terms from inputs/outputs, checks them against stored definitions, and can block generation if terminology conflicts are unresolved.
Terms have a surface (normalized to lowercase), definition, scope,
confidence (0.0–1.0), and status (draft/active/deprecated).
Seed files (.kittify/glossaries/{scope}.yaml) provide initial definitions.
Event logs (.kittify/events/glossary/*.events.jsonl) record all runtime
mutations as append-only JSONL. State is reconstructed by replaying seed files
then events.
| Precedence | Scope | Use For |
|---|---|---|
| 0 (highest) | mission_local | Feature-specific jargon |
| 1 | team_domain | Team/org conventions |
| 2 | audience_domain | Industry/domain standards |
| 3 (lowest) | spec_kitty_core | Framework terms (lane, work package, mission) |
When a mission primitive executes (via @glossary_enabled decorator or
test cases passed, vs 6 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.