mimesis-compile SKILL.md skillA

mimesis-compile from blakecyze/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add blakecyze/skills/mimesis-compile@git:20260901.71d87fc

Pins git:20260901.71d87fc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
blakecyze/skills
Path
skills/mimesis/skills/mimesis-compile/SKILL.md
Versions recorded
2
Latest version
git:20260901.71d87fc, committed Sep 1, 2026
First version recorded
Sep 1, 2026
Size
3,917 bytes
Repository stars
5
License
MIT

Use when the user wants text written for a machine reader, not a human: "write a prompt for", "compress this for an LLM", "turn this into instructions for an agent", "make this a system prompt", "compile this into a prompt". Produces dense, structured, token-efficient instructions tuned to current frontier models, with the right delimiters, constraint ordering and the instruction sandwich. AI tells are acceptable here. Bypasses the humanisation linter by design. Not for human-facing prose…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# mimesis-compile

Domain B: the machine-facing side, and the deliberate opposite of the rest of
mimesis. The reader here is a model, not a person. Density, structure and literal
precision win. AI tells are fine. Em dashes are fine. The humanisation linter
must never run on this output, and this skill shares no machinery with the Domain
A skills. That separation is the whole design; breaking it is a bug.

## How a run works

1. Read [reference/compile.md](../../reference/compile.md) on every run. It is the
   L1 corpus, keyed to GPT-4.1 / GPT-5.x, Claude Opus 4.x and Gemini 3.x as of
   mid-2026, and it flags advice that has gone stale.
2. Establish the target. If the user named a model (`--model`, or "for Claude",
   "for an OpenAI agent"), apply that family's notes from the matrix. If not, ask
   once, or write to the cross-provider common denominator and say so.
3. Compile. Two modes, detected from phrasing:
   - **rewrite**: tighten an existing prompt or instruction block. Strip
     preamble, reorder constraints hard-to-easy, fix delimiters, apply the
     instruction sandwich for long context.
   - **draft**: build a new prompt from a loose intent, using the section
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add blakecyze/skills/mimesis-compile@sha256:6914114b199a4330

The line at the top of this page pins the label git:20260901.71d87fc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_phim6yhqn4b7vybl.svg)](https://markdownregistry.com/a/art_phim6yhqn4b7vybl)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, all committed on Sep 1, 2026.

versioncommittedcommitsizeaudit
git:20260901.71d87fc latest2026-09-01 71d87fc 3,917 BA view · diff
git:20260901.d29810e2026-09-01 d29810e 3,905 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3917 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

blakecyze/skills · 5 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_phim6yhqn4b7vybl
GET https://markdownregistry.com/api/v1/resolve?ref=blakecyze/skills/mimesis-compile
GET https://markdownregistry.com/api/v1/blob/6914114b199a4330acfc2a6e5af57c4ad376aaf678f4ed04b4f5ad9901d99005

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from blakecyze/skills

delight-character SKILL.md skill
blakecyze/skills · skills/delight/skills/delight-character/SKILL.md · Create or extend a product mascot asset set and its reaction states. Use for character production or substantial state…
git:20260911.ae14461 · audit A · 5 stars
delight-habits SKILL.md skill
blakecyze/skills · skills/delight/skills/delight-habits/SKILL.md · Design or review streak, reward, and recovery rules. Use when qualification, cadence, incentives, or progress…
git:20260911.ae14461 · audit A · 5 stars
delight SKILL.md skill
blakecyze/skills · skills/delight/skills/delight/SKILL.md · Refine how product interactions feel during UI creation or a polish pass. Build or review feedback, celebrations…
git:20260911.ae14461 · audit A · 5 stars
flow-access SKILL.md skill
blakecyze/skills · skills/flow/skills/flow-access/SKILL.md · Perform a focused accessibility review or repair of an interface, including keyboard paths, semantics, focus…
git:20260911.ae14461 · audit A · 5 stars
flow-motion SKILL.md skill
blakecyze/skills · skills/flow/skills/flow-motion/SKILL.md · Build or diagnose a specific animation, transition, or gesture interaction. Use for choreography, interruptible motion…
git:20260911.ae14461 · audit A · 5 stars
flow SKILL.md skill
blakecyze/skills · skills/flow/skills/flow/SKILL.md · Refine interface layout, typography, colour, controls, copy, accessibility, and motion. Use during UI creation or when…
git:20260911.ae14461 · audit A · 5 stars
kanso-audit SKILL.md skill
blakecyze/skills · skills/kanso/skills/kanso-audit/SKILL.md · Use when the user asks for a code review, audit, pre-PR check, quality sweep, or pattern analysis of a diff, branch…
git:20260901.d29810e · audit A · 5 stars
kanso-commit SKILL.md skill
blakecyze/skills · skills/kanso/skills/kanso-commit/SKILL.md · Use when the user asks to commit changes, stage their work, write commit messages, or split the working tree into…
git:20260901.d29810e · audit A · 5 stars
kanso-context SKILL.md skill
blakecyze/skills · skills/kanso/skills/kanso-context/SKILL.md · Use when the user asks to update, prune, audit, or create AGENTS.md, CLAUDE.md, or other agent context files. Also use…
git:20260901.d29810e · audit A · 5 stars
kanso-council SKILL.md skill
blakecyze/skills · skills/kanso/skills/kanso-council/SKILL.md · Use when the user wants a stronger, multi-model, or cross-checked audit: "convene the council", "council review"…
git:20260903.ee72ad1 · audit A · 5 stars
kanso-handoff SKILL.md skill
blakecyze/skills · skills/kanso/skills/kanso-handoff/SKILL.md · Use when the user wants the current session's context packaged for the next one: "package this session", "carry this…
git:20260903.30b5bb9 · audit A · 5 stars
kanso-nuclear SKILL.md skill
blakecyze/skills · skills/kanso/skills/kanso-nuclear/SKILL.md · Use when the user asks for a nuclear review, a thermonuclear audit, a deep maintainability sweep, a structural audit of…
git:20260901.d29810e · audit A · 5 stars

Every file in blakecyze/skills

Browse by kind, by grade A, or by owner.