# AGENTS.md — Build guide for Enhancv ## Project scope Build a resume from an evidence-backed career profile, arrange approved sections in one polished layout and export a readable PDF. Catalogue verdict: yes. The core loop is small enough for a capable coding agent to produce a useful local version in one sitting. For Enhancv, create visually polished resume variants from structured user evidence. The hard boundary is template design, content guidance, scoring, document rendering, and support, plus data, distribution, and coaching. Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope. ## Working agreement - Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture. - Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled. - After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran. - Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply. - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization. ## Prerequisites - Runtime and tools: TypeScript, React, SVG or Canvas and IndexedDB with a versioned JSON project format. - Before starting: A browser with IndexedDB, licensed example assets and fonts, and an agreed output size. ## Stack and architecture - TypeScript, React, SVG or Canvas and IndexedDB with a versioned JSON project format - Data design: Store CareerFact, ResumeVariant, SectionOrder and SuggestedBullet; suggested metrics or responsibilities without evidence remain unresolved edits rather than entering the final document. - Setup: A browser with IndexedDB, licensed example assets and fonts, and an agreed output size ## Security and data integrity - Maintain one document model for preview, undo and export. Use stable element IDs; save after completed gestures, handle storage quota errors and provide explicit file backups. - Do not promise ATS compatibility for every parser or fabricate achievements. Fonts and templates need appropriate rights; optional model rewriting sends only explicitly selected content. - Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible. ## Agent implementation rules - Project rule — domain: Store CareerFact, ResumeVariant, SectionOrder and SuggestedBullet; suggested metrics or responsibilities without evidence remain unresolved edits rather than entering the final document. - Project rule — scope and recovery: Do not promise ATS compatibility for every parser or fabricate achievements. Fonts and templates need appropriate rights; optional model rewriting sends only explicitly selected content. - Project rule — acceptance: Add a long job history to a two-column template; expose overflow, preserve selectable text and allow a single-column export without dropping dates or employers. - Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated. ## Optional agent skills and references - Recommended skill: [vercel-composition-patterns](https://github.com/vercel-labs/agent-skills/blob/main/skills/composition-patterns/SKILL.md) — separate document tools, property inspectors and export controls into explicit reusable React components. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. - Recommended skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — review keyboard access, focus, validation, error recovery and the readable work/review interface or HTML report. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism. ## Distribution ideas These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone. - Demonstrate this working slice using synthetic or explicitly authorized non-sensitive examples: Build a resume from an evidence-backed career profile, arrange approved sections in one polished layout and export a readable PDF. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Add a long job history to a two-column template; expose overflow, preserve selectable text and allow a single-column export without dropping dates or employers. - State the limits before asking someone to replace their existing tool: Do not promise ATS compatibility for every parser or fabricate achievements. Fonts and templates need appropriate rights; optional model rewriting sends only explicitly selected content. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Build a resume from an evidence-backed career profile, arrange approved sections in one polished layout and export a readable PDF. Confirm setup: A browser with IndexedDB, licensed example assets and fonts, and an agreed output size. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store CareerFact, ResumeVariant, SectionOrder and SuggestedBullet; suggested metrics or responsibilities without evidence remain unresolved edits rather than entering the final document. 3. Phase 3 — Connect the working view to real saved state. Maintain one document model for preview, undo and export. Use stable element IDs; save after completed gestures, handle storage quota errors and provide explicit file backups. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Do not promise ATS compatibility for every parser or fabricate achievements. Fonts and templates need appropriate rights; optional model rewriting sends only explicitly selected content. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Add a long job history to a two-column template; expose overflow, preserve selectable text and allow a single-column export without dropping dates or employers. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - template design, content guidance, scoring, document rendering, and support - proprietary recruiter data - job-board distribution - human coaching - automated application networks ## Implementation prompt Build the following focused alternative to Enhancv. Implement the focused workflow below first; the verdict is not evidence of a completed or production-certified build. WORKING SLICE Build a resume from an evidence-backed career profile, arrange approved sections in one polished layout and export a readable PDF. SETUP AND ARCHITECTURE Use TypeScript, React, SVG or Canvas and IndexedDB with a versioned JSON project format. Prerequisites: A browser with IndexedDB, licensed example assets and fonts, and an agreed output size. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success. DOMAIN MODEL AND INVARIANTS Store CareerFact, ResumeVariant, SectionOrder and SuggestedBullet; suggested metrics or responsibilities without evidence remain unresolved edits rather than entering the final document. IMPLEMENTATION CONTRACT Maintain one document model for preview, undo and export. Use stable element IDs; save after completed gestures, handle storage quota errors and provide explicit file backups. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content. APP-SPECIFIC BOUNDARY AND RECOVERY Do not promise ATS compatibility for every parser or fabricate achievements. Fonts and templates need appropriate rights; optional model rewriting sends only explicitly selected content. ACCEPTANCE SCENARIO Add a long job history to a two-column template; expose overflow, preserve selectable text and allow a single-column export without dropping dates or employers. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested. DELIVERY Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product. PROJECT RULES FOR AGENTS.md Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication. ## Completion evidence Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.