{{ message }}
Repository navigation
feat(project-demo): Project to case study and demo video - #35
Merged
Merged
Conversation
ingest.ts clones a local repo or GitHub URL at depth 50 and writes a budgeted source brief with line-numbered code, run scripts, commits with bodies and GitHub PRs, issues and contributors. check-study.ts refuses a case study whose features don't cite a code line that exists, whose decisions have no source, or whose numbers have no citation on their line. fixtures/project is a fictional CLI with the same traps VetsAI has: a README-only feature, a vestigial config key and an advertised command with no handler. Part of #4.
Before and after on the fictional Trail Counter repo, the gate's refusal list, what the ingest reads, requirements, cost and privacy. The root README gains the skill row and fixtures/README the project fixture and its planted traps. Part of #4.
Rendered with brand-explainer, the default pack and Kokoro: seven frames, 167 words, 64.5 s, every gate green. Part of #4.
jeromehardaway
marked this pull request as ready for review
October 16, 2026 04:04
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A portfolio repo in (local path or GitHub URL); a gated case study, a hero image and audio overview through blog-media, and a 60-second demo video through brand-explainer out.
What's in it
scripts/ingest.ts: shallow clone at the recorded sha; a budgetedsource-brief.mdwith the README, manifests, run scripts and CI, line-numbered entry points and main source (with a definitions outline past the budget), tests, TODOs, roadmap and changelog, the last 20 human commits with bodies, and withghsigned in the merged PR bodies with authors, open issues and contributors with names. Noise, binaries, data dumps and bots are skipped.scripts/check-study.ts: refuses a case study unless the five sections are there in order, every feature cites apath:lineto code that exists in the clone, every decision and roadmap item names its source, and every number has a citation or source on its line.SKILL.md: the workflow, the case-study template, the three builder questions, the hand-off to blog-media and to brand-explainer at 55-65 s.fixtures/project: Trail Counter, a fictional CLI with VetsAI's three traps (README-only feature, vestigial config key, advertised command with no handler). The tests replay it as a repo with history.npm test.Run on two catalog repos
.envvs Streamlit-secrets drift.--dryon the VetsAI study: $0.19-$0.59. No Gemini key in this environment, so the hero image and audio were not generated.Closes #4