Skip to content
Agentmart
Submit a tool

skill-authoring

Create, review, or make substantial changes to local Pi skills.

Skill by OrestesK

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying skill-authoring?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/orestesk-skill-authoring-77c0d3

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create, review, or make substantial changes to local Pi skills. Use for skill-package structure, activation descriptions, progressive disclosure, references, helper scripts, and structural validation. Comparative activation or outcome evaluation is opt-in and outside this skill. Use pi-config for Pi placement, precedence, settings, package wiring, and approved runtime changes

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/skill-authoring

What's inside

Skill name
skill-authoring
Description
Create, review, or make substantial changes to local Pi skills. Use for skill-package structure, activation descriptions, progressive disclosure, references, helper scripts, and structural validation. Comparative activation or outcome evaluation is opt-in and outside this skill. Use pi-config for Pi placement, precedence, settings, package wiring, and approved runtime changes
License
MIT
Instructions
39 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • SKILL.md
  • activation-contract.md · references/
  • structural-validation.md · references/
  • validate_skill.py · scripts/
  • test_validate_skill.py · tests/

SKILL.md (first lines)

# Skill Authoring

Design the smallest skill package for a behavior that a current task can reach, with one clear owner

## 1. Confirm ownership and need

Before writing:
- identify the current consumer and normal task entrypoint
- inspect existing skills and runtime owners for overlap
- keep each policy with one owner instead of copying it
- keep placement, precedence, settings, and runtime mutation with `pi-config`

Do not add a skill, script, compatibility layer, or reference tree without a current consumer

## 2. Define the activation contract

Read [the activation contract](references/activation-contract.md)

Before finalizing frontmatter, list direct triggers, synonyms, near misses, requests that must not activate the skill, and owner handoffs. The description is always visible in Pi's skill catalog, so keep it precise and narrow. Put full instructions in the body

## 3. Use progressive disclosure

Keep the workflow that a current task needs in `SKILL.md`. Move optional explanations, detailed examples, and reference material into `references/` only when they improve a real task. Keep references one level deep and link them directly from the root

Add a helper script only when a current consumer repeats deterministic work. State its inputs, outputs, failures, and side effects. Add focused tests for repository-owned script behavior

## 4. Validate structure

Read [the structural validation guide](references/structural-validation.md). Find this skill's `scripts/validate_skill.py`, then run it on the candidate skill

This validator is only a local preflight. Pi's merged resource loader determines the effective result for parsing, discovery, diagnostics, and collisions

## 5. Hand off behavior and placement

Comparative activation or task-outcome evaluation is opt-in and outside this skill. Present the proposed cases, evidence, and side effects for user approval before running it. Do not promote a candidate or save an evaluation case automatically

Use `pi-config` for project or global placement, precedence, settings, package wiring, and approved runtime changes. Treat reviewer, validator, and evaluation results as evidence, not permission to edit

From OrestesK/pi, MIT.

More from OrestesK/pi

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Sep 14, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from OrestesK

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get skill-authoring running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying skill-authoring?

CallGet help
Cite this page

skill-authoring. Agent Mart. https://agentmart.dev/skills/orestesk-skill-authoring-77c0d3 (last updated 2026-10-24)