Skip to content
Skills Library
AI & agents · Writing

agent-docs

/agent-docs

Authors or revises skills, AGENTS.md, and related agent guidance using current target-format rules. Use for instruction design, scope, activation, and supporting references.

Repository
pragma ↗
Licence
MIT
Last repository change
26.10.2026

Assessment and security

81/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content16 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Authors or revises skills, AGENTS.md, and related agent guidance using current target-format rules. Use for instruction design, scope, activation, and supporting references.

Original author description

Authors or revises skills, AGENTS.md, and related agent guidance using current target-format rules. Use for instruction design, scope, activation, and supporting references.

How it works

SKILL.md has no level-two headings · 13 lines, 221 words

SKILL.md preview
---
name: agent-docs
description: Authors or revises skills, AGENTS.md, and related agent guidance using current target-format rules. Use for instruction design, scope, activation, and supporting references.
---

# Agent Docs

Before authoring, check current official format and host guidance; reuse sufficiently current guidance fetched in the session. Distinguish format requirements, writing recommendations, and host-specific behavior.

Choose the appropriate home: persistent instructions at the relevant scope, a reusable skill, or a reference loaded only when needed. Inspect existing instructions and authoritative configuration before adding another copy. Keep readily discoverable current values in their source; capture the non-obvious convention or gotcha instead.

Write precise discovery/read conditions and concrete instructions that change the agent's decisions. Match procedural detail to risk; prescribe fixed sequences only when deviation would cause a concrete problem. Describe the intended behavior directly; include a restriction only when it independently protects a contract, scope, or explicit preference. Put shared essentials in the body, conditional detail behind explicit pointers, and the trigger early in the description. Remove repetition and model-common exposition without weakening user preferences or important safeguards. Add supporting resources only when their concrete use justifies them.

Validate relevant structure/metadata, scope, and reference resolution. For consequential instruction changes, consider realistic positive and near-miss activation/behavior checks; syntax alone does not demonstrate useful behavior. Match validation depth to the change and respect an agreed review/evaluation sequence.

Authoring a document does not authorize installing it, modifying unrelated instructions/configuration, or publishing it. Preserve the user's requested language and format for the artifact.

Versions

RepositoryScoreLicence
This page · bbeny123/pragma81MIT
cyijun/agent-docs-skill100MIT

Database snapshot: 13.11.2026 · package version d2a521e5df11 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100skill-creator
    Create, revise, evaluate, or package Agent Skills. Use for SKILL.md instructions, activation descriptions, and bundled resources.
  • 90writing-for-agents
    Use when creating or editing skills, or modifying AGENTS.md or other agent instruction files.
  • 100rc
    Use when you need to create, modify, or optimize a rule, AGENTS.md instruction, or skill
  • 90writing-for-agents
    Writing documents for agents. Use when creating or editing a skill, agent definition, rule, the project instruction file, or when writing a directive or brief another agent will execute.
  • 90writing-for-agents
    Writing documents for agents. Use when creating or editing a skill, agent definition, rule, the project instruction file, or when writing a directive or brief another agent will execute.
  • 100skill-builder
    Create Agent Skills with best practices, structure, validation, and testing. Use when designing or refining skills, prompts, references, or supporting files.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.