agentsclimarketplace

Ai config authoring

Skill grimoire-rs/grimoire/catalog/skills/ai-config-authoring

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code, Copilot, Cursor, Codex, Gemini, Zed, Amp, Kiro, Junie, and opencode — pinned by digest in a lockfile. Storage is any OCI registry; there is no service to run.

Install
npx -y skills add grimoire-rs/grimoire --skill ai-config-authoring

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Craft effective AI agent configuration — skills, rules, agents, and instructions — for any AI coding client. Use when writing or reviewing a SKILL.md, rule file, or agent definition; when deciding between a skill, rule, hook, or always-on instruction; when a config file grows past its context budget; or when a skill description fails to trigger.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.1 KB, as published. Nobody here has run it

AI Config Authoring

Core Principle: Context Is a Budget

Every always-loaded line competes with the user's actual task for model attention, and attention degrades as volume grows — bloated config makes agents ignore the instructions that matter. Pay the always-on price only for content needed every session; defer everything else behind on-demand loading (progressive disclosure). For each line, apply the deletion test: would removing it cause mistakes? If not, cut it.

Budget Table

ArtifactBudgetCost is paid
Always-on instruction file< 200 linesEvery session, every turn
Glob-scoped rule< 200 lines eachOnly while matching files are in play
Skill metadata (name + description)~100 tokens per skillEvery session, all skills
Skill body (SKILL.md)< 500 lines / < 5k tokensOnly when the skill triggers
Skill bundled filesEffectively unlimitedOnly when read or executed
SubagentIsolated windowSeparate budget; only its summary returns
HookZero contextNever — scripts run outside the context

The Artifact-Type Landscape

The first matching row picks the type. Full comparison — vendor support, failure modes, migration paths — in references/choosing-types.md.

The content is...Use
Mechanical, must happen 100% of the time, no judgmentHook
Identity, commands, conventions relevant to every taskAlways-on instruction file
A standard that applies while editing certain filesGlob-scoped rule
An occasional procedure or piece of domain knowledgeSkill
A side-effectful workflow to run only on explicit requestManual-only skill
Context-heavy research, parallel work, separate privilegesSubagent
Something that must port across clientsSkill — the only type every client hosts
Logic a machine can run rather than prose to readHook, or a script inside a skill

Root-as-Index Pattern

A root file is a table of contents, not a textbook: state the principle, compress the comparison, route to depth one level down. This file is the worked example — it stays inside the budgets it teaches, and every detail lives in references/, loaded only when a row below matches your task.

Routing Table

Read......when
references/choosing-types.mdPicking an artifact type, or migrating content between types
references/skill-design.mdWriting or restructuring a SKILL.md and its bundled files
references/rule-design.mdWriting always-on instructions or glob-scoped rules
references/agent-design.mdDefining a subagent or designing delegation between agents
references/descriptions.mdA skill or agent fails to trigger, or before finalizing any description
references/guardrails.mdYou want a copy-pastable always-on enforcement card
references/checklist.mdReviewing a config package before publishing or installing it
references/updating.mdMaintaining this guide itself — re-research protocol and search terms

Distributing Config

Config worth sharing across repositories belongs in a package manager, not copy-paste — versioning, provenance, and an update path matter as much for config as for code. This skill itself is distributed as an OCI artifact via grim. To package and publish your artifact with grim — frontmatter schemas, validation, vendor metadata — read the companion skill grim-authoring at ../grim-authoring/SKILL.md; both ship together in the grim-essentials bundle. If that file is missing, install it by identifier:

grim add ghcr.io/grimoire-rs/skills/grim-authoring:0   # installs by default
# fresh project (no grimoire.toml yet): run `grim init` first

Further Reading

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.