Install
npx skillscat add ashokraj2011/singularityflow/sflow-evidence Install via the SkillsCat registry.
SKILL.md
Show the evidence matrix
Output contract: Relay requested CLI fields or output faithfully; preserve warnings/errors and only the explanations required below. For suggested actions, pair Shell with the returned Copilot command; honor commandGuidance. If absent, say "Copilot: no verified equivalent"; never invent a slash command.
Boundary: no Story required; cwd=opened Git root or verified repositoryPath from singularity-flow workspace current --json; refuse if neither resolves; never search $HOME/parents.
- Use the Boundary repository. With an explicit Work ID, do not require or change the active Story. Without an ID, run
singularity-flow session current --jsonand require itsreadyStory; use its exactrepositoryPathas cwd. - Run
singularity-flow evidence matrix <WORK-ID> --json, or without the ID for the attached Story, adding only--row,--resultor--facetwhen the person asked for them. - From
data.matrix.evaluation, showcompletion.labelwith itsreasons,lifecycle.words, the counts insummary.results,summary.assuranceFloor, andsummary.scope.wordsandsummary.scopeRevision.wordswhen present. Then showpage.rowsas a table: row ID, result, assurance, and each obligation'sresponsibilityandstatus. - Use only the labels the CLI returned. Never say a Story is complete, all tests passed or all requirements are satisfied unless
completion.labelsays so; "module-observed" means a covering test command passed; only "exact-local-observed" means the criterion's own test was seen passing. - List
findingsthat need attention and each row'sactionscommands as next steps, without running them. - When the person asks which requirement statements the Story's sources hold, run
singularity-flow evidence scope <WORK-ID> --jsoninstead: show each item'sid,text,sourceIdanddisposition, the unreadable sources,structurallyCompleteandcompletenessReview. A review never means the scope is correct. - Do not change files or lifecycle state.