Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-buddy-ssot-knowledge
Single Source of Truth detection — where truth lives in an nWave repo and how to avoid contradicting it.
Passed 20 of 22 test cases with the skill, and 11 of 22 without it.
and 10 more in the full report
9 fixed11 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I remember from our earlier conversation that we were on branch feature/auth, but I need to verify our current repository branch and working directory state before proceeding. How should current git state be determined?
| Checked | Without skill | With skill |
|---|---|---|
| Requires executing actual git status or git branch commands prior to answering. | Missed | Passed |
| Prohibits relying on conversation memory for git state. | Passed | Passed |
The instructions your model reads when the skill loads.
Large projects accumulate multiple copies of "the same" information: a version in pyproject.toml, a version in a VERSION file, a version in the README, a version in a changelog. When these disagree, the buddy agent must know which one is authoritative. This skill is the SSOT map for nWave projects.
Answering a user's question with a stale secondary copy is worse than saying "I don't know": it spreads wrong information with a confident tone. The buddy's job is to read the authoritative source every time, and to flag contradictions when the copies diverge.
Each concept below has one authoritative file. Read that file first. Treat everything else as a cache that may be stale.
pyproject.toml [project] version = "..." (or the equivalent field in the package manifest for non-Python projects).VERSION file, README badges, docs footer, release notes.pyproject.toml. If asked about a cache that disagrees, report the discrepancy.BACKLOG.md at the repo root.BACKLOG.md is not planned. Don't invent items. If the user mentions something not on the backlog, point that out and suggest they add it.docs/architecture/architecture-design.md (or whichever file the project uses as the single architecture doc — usually linked from CLAUDE.md or README.md).docs/feature/ with wave subdirectories, ADRs in docs/adrs/, diagrams in docs/, comments in code.pyproject.toml, .pre-commit-config.yaml, ci.yml, whichever applies).test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.