agentmods.dev

partner-skill-compiler

partner-skill-compiler is a skill for Claude Code, Codex from LuuOW/meridian-mcp. It costs 50 tokens per session (622 once invoked), scanned A, original, MIT.

A guide for turning publicly available research about a person into a reusable assistant prompt and instruction file.

In plain words
What is it for?
Use it to collect evidence about someone’s identity, beliefs, working style, audience, offers, and writing habits, then turn that evidence into an agent profile.
Why use it?
It helps create a grounded partner-style assistant without confusing the person’s own statements with other people’s opinions or inventing unsupported details.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 14d ago A scan 50 tokens original MIT archived

Good fit Use it to collect evidence about someone’s identity, beliefs, working style, audience, offers, and writing habits, then turn that evidence into an agent profile.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luuow/meridian-mcp/partner-skill-compiler
View source ↗ LuuOW/meridian-mcp ask-meridian.uk
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add LuuOW/meridian-mcp --skill partner-skill-compiler
Clone the repo
git clone --depth 1 https://github.com/LuuOW/meridian-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for partner-skill-compiler

README.md
[![agentmods](https://agentmods.dev/badge/skills/luuow/meridian-mcp/partner-skill-compiler/github.svg)](https://agentmods.dev/skills/luuow/meridian-mcp/partner-skill-compiler)
Your own site
<a href="https://agentmods.dev/skills/luuow/meridian-mcp/partner-skill-compiler"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/partner-skill-compiler/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for partner-skill-compiler

Your own site · 80×15
<a href="https://agentmods.dev/skills/luuow/meridian-mcp/partner-skill-compiler"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/partner-skill-compiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 622 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00622
Opus 5.5 $0.00020 $0.00249
Sonnet 5.5 $0.00010 $0.00124
Haiku 4.5 $0.00005 $0.00062

Measured 1mo ago against content hash 02c81bfef1fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

partner-skill-compiler scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/partner-skill-compiler/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

partner-skill-compiler

Use this when the goal is to turn a researched public corpus into a practical partner-style skill or prompt that feels like the person without pretending to be them.

Goal

Compile public evidence into a partner agent that:

  • sounds directionally like the person
  • prioritizes similarly
  • uses similar mental models and examples
  • stays grounded and citation-aware

Required Buckets

  • identity_summary
  • worldview_signals
  • operating_style_signals
  • audience_signals
  • offer_signals
  • first_person_signals
  • writing_behavior_signals
  • partner_prompt

Source Priorities

Highest:

  • bio/about pages
  • self-authored newsletters and articles
  • transcript-backed episodes

Medium:

  • self-authored landing pages
  • direct profile pages

Lowest:

  • testimonials
  • customer quotes
  • widget/social embed content
  • channel landing pages

Compilation Rules

  1. Separate identity from reputation:

    • identity = what the person says they are or claims directly
    • reputation = what others say about them

  2. Separate worldview from offers:

    • worldview = what they believe, optimize for, or repeatedly emphasize
    • offers = products, newsletters, courses, services, podcasts

  3. Separate voice from biography:

    • voice = sentence shape, framing style, common openings, practical tone
    • biography = roles, history, credentials

  4. Prefer repeated patterns over one-off lines

  5. Penalize:

    • testimonial language
    • review snippets
    • chrome artifacts
    • anonymous or low-confidence claims

Partner Prompt Design

A good partner prompt should include:

  • what role the agent is simulating
  • what kinds of recommendations it should bias toward
  • what it should avoid
  • what evidence buckets it should trust most
  • an explicit boundary against private-memory fabrication

Output Rule

The final skill should frame the result as:

  • an evidence-backed partner simulation
  • not identity verification
  • not permission to impersonate the person in high-stakes contexts

Read the full file on GitHub · 99 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 99 lines · 50 tokens per session scan A 02c81bfef1fd

Subscribe to this mod's changes

partner-skill-compiler is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsResearchauthoritycompilerevidencegroundedpartnerpersonaprofilepromptpublicreusableskillsynthesize
Related

Other skills, from other repositories

special-cute-coder-wife

A coding assistant with a warm, encouraging companion style. It is designed to read errors and logs, look for overlooked details, and guide debugging step by step.

linkerlin/PUAX · 47 tokens

add

Use this skill when the user wants AI work they can trust without watching every step: the AI fixes direction first (rules, assumptions, failing checks sealed in git), builds to green, then proves the result with evidence for the human to review. Trigger when a repo has .add/, the user says "add", "/add", "start a…

pilotspace/ADD · 188 tokens

add

Use this skill when the user wants AI work they can trust without watching every step: the AI fixes direction first (rules, assumptions, failing checks sealed in git), builds to green, then proves the result with evidence for the human to review. Trigger when a repo has .add/, the user says "add", "/add", "start a…

pilotspace/ADD · 212 tokens

agent-profile

The name the resident gave you and what they wrote about themselves in the Edge City app. Read it once per private conversation, before your first reply, with the one command below; it tells you your name and the resident's own description of themselves.

Edge-City/agentvillage · 53 tokens

superpowers-zh

Use when constraining AI coding with Chinese TDD methodology, systematic debugging, code review, and verification workflows. Superpowers-zh: Chinese adaptation of the Superpowers AI-assisted programming skills and methodologies.

znlgis/opengis-skills · 45 tokens

dc

Read and act on your own Dynamite Circle membership data via the public Member API — profile (read+update), trips (CRUD), events + RSVP, virtual events + RSVP, tickets, invites (send), inbox, rooms, chapters, places lookup, locator digest. Self-contained single-file Python client (CLI / library / MCP), or a hosted MCP…

dynamitecircle/dc · 78 tokens