By papersson
Query Claude Code transcripts as work history (reports, activity logs, runbooks, friction analysis, session resume, mining recurring corrections into CLAUDE.md rules). Heavy many-session analyses run as dynamic workflows.
A small Claude Code plugin marketplace.
| Plugin | What it does |
|---|---|
worklog | Query your Claude Code transcripts as a personal work history — time reports, per-task activity logs and runbooks, friction analysis, resume-context packs, find-and-reopen, and mining recurring corrections into CLAUDE.md rules. The heavy, many-session analyses run as dynamic workflows. |
orchestrate | Turn a rough task into a well-structured dynamic-workflow invocation. A skill that decides whether a workflow is even warranted, scopes it, fills the gaps, and fires it. Non-trivial runs end with a self-contained HTML report the human can follow and verify — task-first, with the orchestration machinery subordinate. Plus reusable invocation templates. |
prose | Improve writing style without changing content. Two modes: rewrite returns clean prose silently; review returns a located, attributed critique that teaches. Strips AI/LLM and bad-prose signatures, moves toward careful human writing. Grounded in a curated craft corpus. |
Add the marketplace once:
claude plugin marketplace add papersson/papershop
Then install either plugin:
claude plugin install worklog@papershop
claude plugin install orchestrate@papershop
claude plugin install prose@papershop
worklog also ships a Nix flake (it has a Python engine to build); see
worklog/README.md for the flake input and home-manager
wiring. orchestrate and prose are pure Markdown — no build, install via the
plugin command above.
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 papersson/papershop --plugin worklogImprove writing STYLE without changing content: strip AI/LLM and bad-prose signatures, move toward careful human writing (especially technical). Two modes — rewrite (silent) and review (a located, teaching critique). Quick edits run inline; long or high-stakes pieces fan out as a dynamic workflow that diagnoses across lenses and verifies with fresh agents. Grounded in a curated craft corpus.
Turn a rough task into a well-structured dynamic-workflow invocation. A gate-first skill that defines the verifier first, then composes expressive typed-node topologies (workers, barriers, loops, gates) where every node earns decorrelated signal; gets explicit approval before firing in interactive mode; adapts shape to what the run learns and chains workflows; handles interactive vs autonomous blocking (BLOCKED/return/resume); and ends almost every run with a self-contained, task-first HTML report written to /tmp, prose-passed and agent-browser self-checked. Plus reusable invocation templates (deep-verify, rank, root-cause, migrate, report).
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment