Integrate CV Builder MVP foundation and close PR cleanup pass#85
Merged
Conversation
Shared, validated contract for CV Builder surfaces: Resume, JobDescription, Archetype, Issue, Claim, and EvalResult (with required rubric/archetype versions). Closes #47
Scoring brain the prompts reference: rubric v1 (six weighted dimensions with 0-5 anchors), three role archetypes (Software Engineer, Product Manager, Data & ML Engineer), keyword-based detectArchetype, and the ATS and claim validator specs. Closes #63
The three Phase 1 prompts a power user's agent runs. Markdown templates are the source of truth; renderers inject the live rubric, archetype weights, and claim rules so each assembled prompt is self-contained and stays in sync with the intelligence package. Every prompt asks for JSON matching its schema. Closes #64
Clone the repo, open Claude Code, run /evaluate-cv: the cv-evaluation skill runs extract -> detect -> score -> validate-claims locally, reading the prompts and rubric straight from the repo (no build). A SessionStart hook greets the user with the available commands on open. Skill subfiles point at the package sources to avoid drift. Closes #65
Five fixtures across the three archetypes (including an ATS-hostile resume) guard the deterministic layer: for each, the detected archetype and ATS read must match expectations and the resume must parse against the schema. No LLM involved. Wired as a pnpm eval task and a CI step. Closes #66
README gets a 'Power User — run it with Claude Code' section (clone, open Claude Code, /evaluate-cv) linking apps/cli/README.md, and the architecture tree plus the CONTRIBUTING structure now list schemas, intelligence, prompts, eval, and apps/cli. Closes #67
Add path_instructions for core/cli/web packages and markdown docs, enable ESLint and markdownlint tools, ignore build/dependency output, disable the review poem, and turn on knowledge base learnings.
…to feature/intelligence-rubric-archetypes
- Remove 'Translate the README or docs' section from CONTRIBUTING.md - Renumber remaining 'no-code' sections 4-6 to 4-5 - Drop 'translations' reference from 'How to submit' section - Remove 4 README translation rows from ROADMAP.md (pt-BR, hi, ar, zh) Translation was the lowest-leverage of the open contributor asks. Project should focus on archetypes, rules, and PR reviews instead.
# Conflicts: # pnpm-lock.yaml
# Conflicts: # packages/core/src/evaluator/index.ts
# Conflicts: # packages/core/src/evaluator/index.ts
…hetype # Conflicts: # packages/core/src/__tests__/evaluator.test.ts
# Conflicts: # README.md # packages/core/src/__tests__/evaluator.test.ts # packages/core/src/archetypes/index.ts
|
Warning Review limit reached
Next review available in: 33 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 Walkthrough
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
SaharPak
pushed a commit
that referenced
this pull request
Jul 2, 2026
This was referenced Jul 2, 2026
SaharPak
added a commit
that referenced
this pull request
Jul 2, 2026
* docs: align repository documentation with MVP status Documentation-only audit. No code, evaluator, or rule changes; no new features; no Cloudflare work; no changes to PR #37 or #78. User-facing copy fixed: - README.md: replace misleading ASCII diagram (3 rewrites / Tailored CV) with the actual MVP outputs (Score, Issues, Strengths, ATS verdict, Archetype); clarify that /evaluate-cv ./my-resume.pdf works only because Claude Code reads PDFs natively (the local CLI/web UI parse .md and .txt only). - apps/web-ui layout.tsx: Next.js metadata description replaced with honest CV-evaluator copy (no longer 'Build a tailored resume...'). - apps/web-ui/README.md: list all three routes (/, /results, /feedback), note the static-export + privacy-first posture. - apps/cli/README.md: same PDF-clarification note as the root README. - package.json descriptions (root + core + cli): remove 'tailor / build' wording; describe the deterministic evaluator. - packages/intelligence/README.md: list the eight shipped roles (matches README and the actual implementation) and correct the default archetype (Backend Engineer, not Software Engineer). - packages/eval/README.md: drop the outdated LLM-provider claim; the MVP is fully deterministic. - .claude/skills/cv-evaluation/SKILL.md: 'local MVP', not 'hosted product'; default archetype corrected. - ROADMAP.md: status note added; Phase-1 / #74 / #75 / #76 / #85 / #87 marked as recently shipped; only #37 and #78 remain in progress. Historical docs marked with status notes (not rewritten, just flagged as pre-release context): ARCHITECTURE.md, PROPOSAL.md, PHASE-1.md, V1_SCOPE.md, MVP_DEMO_PLAN.md, PR_CLEANUP_HANDOFF.md, POST_MERGE_VALIDATION.md, REMAINING_PRS_PLAN.md, PR85_ROLLBACK_PLAN.md. Each now points readers to docs/MVP_RELEASE_STATUS.md. New: - docs/REPO_DOCS_AUDIT.md records the audit date, files reviewed, files changed, outdated claims found and fixed, historical docs left intentionally unchanged, remaining risks, and the validation results. Validates: pnpm test (12/12), pnpm lint (0 errors), pnpm build (6/6, fresh --force: emits /, /_not-found, /feedback, /results). * docs: fix remaining Node version reference docs/MVP_DEMO_PLAN.md still said 'Node 22+' in the prereqs section, which conflicts with the actual repo metadata (Node >= 20.0.0 in package.json) and with the authoritative setup guide in docs/LOCAL_DEMO.md. Replace the prereqs with a short pointer to LOCAL_DEMO.md plus a one-line accurate summary, so this historical demo-readiness doc no longer contradicts current setup instructions. docs/REPO_DOCS_AUDIT.md: remove the corresponding entry from the 'remaining documentation risks' list, fix the resulting item numbering, and add a note recording that the Node-version item was resolved before merge. No code, evaluator, or rule changes. No new features. PR #37 and PR #78 untouched. Validates: pnpm test 12/12, pnpm lint 0 errors, pnpm build 6/6 (fresh --force, emits /, /_not-found, /feedback, /results). * docs: address remaining CodeRabbit comments on PR #88 Two unresolved CodeRabbit comments fixed in this commit: 1. README.md — replace hard-coded '5 issues' in the evaluator diagram with the non-fixed wording 'Issues'. evaluate() returns a variable-length issues array; a fixed count would drift as scoring changes. The other diagram labels (Score, Strengths, ATS verdict, Archetype) are kept as-is because they describe deterministic outputs that do not vary in count. 2. packages/intelligence/README.md — the previous audit pass claimed this package ships eight roles and falls back to Backend Engineer. But packages/intelligence/src/archetypes/index.ts registers only three archetypes (Software Engineer, Product Manager, Data & ML Engineer) and DEFAULT_ARCHETYPE is softwareEngineer. Update the README to reflect the actual registry. Add a note clarifying that @cv-builder/core has a separate, broader legacy/runtime registry (7 roles) used by the CLI and Web UI, and that unifying the two registries is a follow-up — see docs/ARCHETYPE_GAP_AUDIT.md. docs/REPO_DOCS_AUDIT.md updated to record that the packages/intelligence/README.md archetype-inventory row was corrected in two steps (the audit pass incorrectly bumped the package claim to 8; this commit brings it back to 3 and adds the @cv-builder/core note). No code changes. No new features. PR #37 and PR #78 untouched. Docs only. Validates: pnpm test 12/12, pnpm lint 0 errors, pnpm build 6/6. --------- Co-authored-by: Cleanup Bot <cleanup-bot@example.com>
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
5 participants
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.
Summary
This PR integrates the reviewed volunteer PR work into a coherent MVP foundation for CV Builder. It consolidates schema, intelligence/rules, prompts, archetypes, evaluator logic, and web UI changes after a full PR cleanup pass.
What changed
PRs integrated
PRs closed or superseded
PRs intentionally left open
Validation
Known risks
Handoff
Full details: docs/PR_CLEANUP_HANDOFF.md