agentleFS
Sign inStart free
jscraikjscraik/Agent-Skills/Skills/agent-ops/toml/SKILL.md

toml

Skill9 starsChanged 47 days agoApache-2.0View on GitHub

Create and review TOML configuration with strict typing and predictable structure. Use when editing tool configuration files that require schema-safe TOML.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use for TOML config creation, review, or schema-safe fixes.

    line 26
  2. Distinctive:

    Prefer schema truth and low-churn edits over clever rewrites.

    line 44
  3. Distinctive:

    Prefer explicit scalars and arrays over ambiguous shapes.

    line 55
  4. Distinctive:

    Keep one responsibility per table and use dotted keys consistently.

    line 56
  5. Distinctive:

    Do not mix inline tables and expanded tables for the same object path.

    line 57
  6. Distinctive:

    Keep trailing commas out of arrays and inline tables.

    line 63
  7. Very specific:

    Run the relevant parser/schema/tool checks for touched files.

    line 67
  8. Distinctive:

    If schema ownership is unclear, pause before adding keys.

    line 72
  9. Distinctive:

    If the owning schema, value type, or validation command cannot be identified, stop and report the missing contract before editing.

    line 81

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Table of Contents

  • When to use
  • Required inputs
  • Deliverables
  • Philosophy
  • Procedure
  • TOML Guidelines
  • Editing Rules
  • Validation
  • Constraints
  • Anti-patterns
  • Failure mode
  • Gotchas
  • References

When to use

  • Use for TOML config creation, review, or schema-safe fixes.
  • Inputs: target files, owning tool, expected key paths, and compatibility constraints.
  • Deliver valid TOML with minimal key-path churn and notes for schema-impacting edits.

Required inputs

  • Target TOML file path and owning tool or schema.
  • Intended key paths, value types, and compatibility constraints.
  • Validation command or parser expected to consume the file.

Deliverables

  • Minimal TOML edit preserving existing comments and order where possible.
  • Validation evidence from parser, schema, or owning tool.
  • Notes for any type, key-path, or compatibility risk.

Philosophy

  • Prefer schema truth and low-churn edits over clever rewrites.

Procedure

  1. Confirm the consumer schema and current key paths.
  2. Make the smallest compatible edit.
  3. Validate before closeout.

TOML Guidelines

  • Preserve key order where tool owners expect readability.
  • Prefer explicit scalars and arrays over ambiguous shapes.
  • Keep one responsibility per table and use dotted keys consistently.
  • Do not mix inline tables and expanded tables for the same object path.

Editing Rules

  • Change only the smallest required key path.
  • Retain existing comments unless provably outdated.
  • Keep trailing commas out of arrays and inline tables.

Validation

  • Run the relevant parser/schema/tool checks for touched files.
  • Fail fast: stop at the first failed gate and report exact blocker evidence.

Constraints

  • If schema ownership is unclear, pause before adding keys.
  • Redact secrets and do not run destructive or network commands unless explicitly approved.

Anti-patterns

  • Redefining key paths, mixing table styles for one object, or skipping validation.

Failure mode

If the owning schema, value type, or validation command cannot be identified, stop and report the missing contract before editing.

Gotchas

  • Quoting numeric values can silently change type semantics.

See Also

SkillWhen to use
[[yaml]]Schema-aware config review for YAML-based tooling configs
[[he-fix-bugs]]Triage config parsing failures with evidence-first diagnosis

Topic map: [[agent-ops]]

References

  • Deep guidance: references/deep-guidance.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free