Nisus74

Nisus74/pencil-skill

Plugin Claude Code

Plugin marketplace listing 1 plugin: pencil-dev-skill.

Nisus74/pencil-skill

Plugin Claude Code

Teaches AI coding tools to design, edit, and validate pencil.dev UIs using .pen files, .lib.pen libraries, design-system docs, and the Pencil MCP server.

Nisus74/pencil-skill

Instructions file CodexOpenCode

Instructions for Nisus74/pencil-skill, covering pencil-dev-skill: project context, project purpose, naming conventions, repository structure and project context files.

Nisus74/pencil-skill

Instructions file

Instructions for Nisus74/pencil-skill: This project's canonical context lives in AGENTS.md.

Nisus74/pencil-skill

Skill Claude CodeCodex

Use this skill for any pencil.dev work, such as designing UI in a .pen file, editing an open Pencil canvas, sketching or mocking screens, instantiating components from a .lib.pen library, reading an existing design system from a .pen or .lib.pen file, fixing batchdesign schema errors, or recovering from Pencil MCP…

Nisus74/humanise

Plugin Claude Code

An open-source Agent Skill that preserves what you mean and learns how you write from real examples.

Nisus74/humanise

Plugin Claude Code

An open-source Agent Skill that preserves what you mean and learns how you write from real examples.

Nisus74/humanise

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing guard-bash.sh via bash. From Nisus74/humanise.

Nisus74/humanise

Hook Claude Code

Runs after a tool call finishes for Write and Edit tool calls, executing post-edit.sh via bash. From Nisus74/humanise.

Nisus74/humanise

Settings file Claude Code

Agent settings declaring 2 hook events (PreToolUse, PostToolUse) and 11 allowed tools.

Nisus74/humanise

Instructions file CodexOpenCode

AGENTS.md instructions for Nisus74/humanise, covering agents.md and launch documentation.

Nisus74/humanise

Instructions file

Claude Code instructions for Nisus74/humanise, covering claude.md, the one rule: body vs soul, repo map, the acceptance gate (read before changing the engine) and commands.

Nisus74/humanise

Instructions file Gemini CLI

Gemini CLI instructions for Nisus74/humanise: Gemini CLI and Google Antigravity read this file. This repo is the humanise writing skill: it makes AI-generated prose sound like a specific human wrote it.

Nisus74/humanise

Skill Claude CodeCodex

Write, rewrite, edit and review human-facing prose in a specific person's voice. Use for emails, posts, reports, proposals, PRDs, board papers, documentation, applications, messages and any text the user will send, publish, present or sign off. Also use when the user asks for Australian English, natural writing, less…

Nisus74/humanise

Agent

Fails a draft before it ships. Invoked by humanise Step 6 (external pieces) and Step D5 (mandatory for long-form), and by the self-harness acceptance gate for high-stakes changes. Runs in a separate context with no access to the drafting rationale, because the writer shares the draft's blind spots.

Nisus74/humanise

Agent

Draft generator for the benchmark and indistinguishability stages of /humanise improve. Runs in one of two modes set by the spawn prompt, skill (full workflow) or baseline (no skill context), and writes the finished draft to a given output path.

Nisus74/humanise

Agent

Checks a draft against its brief or source before it ships: are the specific claims true and supported, and does the piece still say what the brief asked? Invoked by humanise Step 6 and Step D5 for external pieces that carry checkable claims, when a brief or source exists. Unlike the adversarial-reviewer, it receives…

Nisus74/humanise

Agent

Drafts bounded engine-change proposals from mined weakness clusters (candidates.json), in the four-part self-harness schema. Separate context; sees only the evidence and the named engine surfaces, with no access to the conversation that produced them.

Nisus74/humanise

Agent

Blind pairwise judge for the indistinguishability test (evals/indistinguishability.md). Given two texts, decides which is the real person's and names the deciding signals. No corpus, no conversation, no labels.

Nisus74/humanise

Command

Run the deterministic checker on a draft (no LLM). Wraps evals/assertions/writingchecks.py.

Nisus74/humanise

Command

(Re)generate the user's voice fingerprint from their corpus. Run after adding profile/sample-.md samples.

Nisus74/humanise

Command

Draft new content in the user's voice.

Nisus74/humanise

Command

Run one full cycle of the self-improvement loop: benchmark the skill's output, run the blind voice test, mine the accumulated evidence for weaknesses, and gate any proposed engine change. The loop's rules live in evals/self-harness-loop.md; this command executes them. Every stage is skippable, but say which stage was…

Nisus74/humanise

Command

Set up the user's voice without making them complete a profile before seeing value.