Generate grounded resume and cover letter variants, then curate and stitch. Combines deterministic scripts (scaffolding, stitching, grimoire-checklist linting) with a parallel variant-generator subagent. Generate abundance, exercise taste, stitch from selections.
A Claude Code plugin that generates grounded resume and cover letter variants, lets you curate them, and stitches final documents. Generate abundance, exercise taste, stitch from selections.
Inspired by Scott Werner's The Illusionist and the Conjurer: instead of asking for one perfect output, summon many grounded variants and recognize the right one.
grimoire.md captures your voice and rules so output sounds like you.pandoc if installed; otherwise markdown is the deliverable)./plugin marketplace add joshuaoliphant/resume-conjurer
/plugin install conjurer@resume-conjurer
/conjurer:grimoire # build your grimoire (point it at an old resume to bootstrap)
/conjurer:master-resume # build your master resume (the evidence pool)
These create and fill a workspace: a directory with grimoire.md, master-resume.md, and
applications/.
Ask Claude to tailor your resume for a job ("conjure variants for this role" + paste the JD). The
conjurer skill runs the pipeline: outline -> variants (in parallel) -> curate with you -> stitch ->
lint -> export. Output lands in applications/<slug>/.
Start in a folder that holds your current resume and launch Claude Code there:
~/job-search $ ls
resume.pdf
~/job-search $ claude
Then describe the job:
You: Help me apply to the Staff Platform Engineer role at Globex. [paste the JD]
On the first run there is no workspace yet, so the skill bootstraps one from what you already have:
Conjurer: I don't see a conjurer workspace here, but I found
resume.pdf. I'll read it to build yourmaster-resume.md(the evidence pool) and interview you briefly to capture your voice ingrimoire.md. Ready?
After setup, the pipeline runs:
Outline. It reads the JD against your master resume and picks one strategic frame (scale, friction, conviction, or multiplier), then lists the cover letter paragraphs and the resume bullets worth tailoring.
Variants. It generates four grounded variants per unit in parallel, each citing the evidence
it draws from, and writes them to applications/globex-staff-platform/variants.md.
Curate. It walks you through the units conversationally:
Conjurer: For your opening bullet, which lands better?
- Architected the billing-platform migration to event-driven services, cutting invoice latency from 40s to under 2s across three regions.
- Led the platform migration that moved billing onto an event-driven backbone, taking invoice generation from 40 seconds to two and clearing the path for regional rollout.
You: 1
Stitch. It assembles your picks into cover_letter.md and resume.md.
Lint. It runs the grimoire checklist (no em dashes in prose, no filler, no AI-generic openers, cover letter under 350 words) and fixes anything it flags.
Export. It offers PDF and docx for submission (via pandoc if installed).
~/job-search $ ls applications/globex-staff-platform
cover_letter.md cover_letter.pdf resume.md resume.pdf
jd.txt evidence.md outline.json variants.md
Every claim in those documents traces back to a line in your master resume or evidence. The model re-frames; it does not invent.
Deterministic work (scaffolding, stitching, linting) is pure-stdlib Python in
plugins/conjurer/skills/conjurer/scripts/. Generation is a skill procedure plus a parallel
variant-generator subagent. No API keys: inside Claude Code, Claude is the model.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub joshuaoliphant/resume-conjurer --plugin conjurerGenerate autonomous experiment loops with immutable runner scripts, tiered quality gates, secondary metrics, and structured METRIC output.
Capture solved problems and retrieve past solutions as structured YAML-frontmatter files. Split into compound-capture (post-solve documentation) and compound-retrieve (pre-work knowledge search) for precise triggering.
Adaptive autonomous SDLC with agent teams, native worktree isolation, task management, prompt-based hooks, and prompt objects
Build web applications where an AI agent dynamically generates HTML UI using hexagonal/ports-and-adapters architecture with HTMX for interactivity and MCP tools for data operations
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.