skill-writing-guidelines

skill-writing-guidelines is a skill for Claude Code, Codex from Conradgui/matt-pocock-inspired-skill-writing. It costs 38 tokens per session (910 once invoked), scanned A, original, MIT.

Practical instructions for writing and reviewing agent skills, which are instruction packages that guide a coding agent through tasks. They cover behavior contracts, responsibility boundaries, invocation, hierarchy, and related design choices.

In plain words
What is it for?
Use them to create a new skill, restructure a collection, investigate unreliable behavior, or remove an existing skill safely.
Why use it?
They reduce unpredictable triggering and execution by requiring clear inputs, branches, outcomes, and failure conditions. They also help prevent duplicated responsibilities across skills.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the matt-pocock-inspired-skill-writing plugin — 1 skill shipped together

Good fit Use them to create a new skill, restructure a collection, investigate unreliable behavior, or remove an existing skill safely.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines
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 Conradgui/matt-pocock-inspired-skill-writing --skill skill-writing-guidelines
Clone the repo
git clone --depth 1 https://github.com/Conradgui/matt-pocock-inspired-skill-writing

Made for: Claude Code, Codex.

Or install matt-pocock-inspired-skill-writing, the plugin that ships this one along with the rest of its 1 skill.

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 skill-writing-guidelines

README.md
[![agentmods](https://agentmods.dev/badge/skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines/github.svg)](https://agentmods.dev/skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines)
Your own site
<a href="https://agentmods.dev/skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines"><img src="https://agentmods.dev/badge/skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines/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 skill-writing-guidelines

Your own site · 80×15
<a href="https://agentmods.dev/skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines"><img src="https://agentmods.dev/badge/skills/conradgui/matt-pocock-inspired-skill-writing/skill-writing-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 910 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 $0.00038 $0.00910
Opus 5 $0.00019 $0.00455
Sonnet 5 $0.00008 $0.00182
Haiku 4.5 $0.00004 $0.00091

Measured 11d ago against content hash 9da0c1c91c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-writing-guidelines 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 11d 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/skill-writing-guidelines/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Writing Guidelines

Make the skill's process predictable across runs, without requiring identical outputs. Apply the active agent platform's native fields and validators; translate patterns from other harnesses instead of copying their metadata unchanged.

1. Establish the behavior contract

Use concrete runs to identify the outcome, trigger branches, near misses, inputs and state, side effects, success evidence, and failure behavior. Inspect existing callers and artifacts before changing an existing skill. Treat a user-reported symptom as high-value evidence and the proposed cause as a hypothesis to verify against files, history, tests, traces, and callers.

Done when: every genuine branch has a concrete example and an observable success or failure condition.

2. Assign responsibility

Keep reusable discipline and vocabulary in primitives, end-to-end sequencing in orchestrators, cross-session facts in narrow artifacts, platform commands behind adapters, and human discovery in a router. Give each responsibility one owner.

Done when: every proposed skill has one coherent contract and shared behavior has one source of truth.

3. Design invocation and hierarchy

Treat a model-facing description as a branch index: front-load the core action and add one trigger per genuine branch. Inline what every run needs. Move branch-only reference behind a pointer that says when and why to read it. Use leading words to compress behavior only when they are precise.

Done when: invocation mode is deliberate, every conditional resource has a firing condition, and the main path is legible without irrelevant branches.

4. Encode gates and state

Validate cheap shared preconditions before expensive work. End consequential steps with observable, exhaustive criteria. Separate discoverable facts from user decisions, and persist cross-session state in purpose-built artifacts. Isolate independent evaluation axes when one can bias another.

Done when: another agent can follow every branch without inventing the source order, authority, stopping rule, or evidence standard.

Read the full file on GitHub · 91 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 91 lines · 38 tokens per session scan A 9da0c1c91c5a

Subscribe to this mod's changes

skill-writing-guidelines is a skill published in the GitHub repository Conradgui/matt-pocock-inspired-skill-writing (7 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 910 once invoked, about $0.0002 per session on Opus 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.