writers-pattern

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of written file paths. Use when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets. Do NOT use for modifying existing writers, refactoring scoring logic, or changing how writers are invoked.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validation-checked workflow, but it is verbose and keeps all detail inline rather than offloading the per-platform reference material and worked example into separate files. Conciseness and progressive disclosure are the weakest dimensions.

Suggestions

Move the repeated per-platform line-number citations and full worked example into a reference file (e.g. references/examples.md) and link to it from the main steps to improve progressive disclosure and reduce body length.

Tighten Step 2 by collapsing the four parallel per-platform append-block examples into a single compact table or one canonical example, reducing repetition without losing actionability.

De-duplicate the frontmatter format snippets (shown both in Step 4 of Instructions and again in Common Issues) to a single canonical source, cutting token cost.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence (no beginner-concept padding) and stays on-task, but at ~271 lines it repeats per-platform line citations and inline examples that could be tightened or trimmed to earn the lean anchor at 3.	2 / 3
Actionability	Provides exact function signatures, line-number citations, copy-paste-ready TypeScript blocks, and a fully executable DevCode worked example, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clear 6-step sequence with explicit 'Validation' checkpoints in nearly every step plus a Common Issues troubleshooting section provides the feedback loops the rubric rewards for file-writing operations.	3 / 3
Progressive Disclosure	Sections are well organized (Critical, Instructions, Examples, Common Issues), but no reference bundle files exist and all detail is inline in one ~271-line file; per-platform detail tables and the worked example could be split into separate reference files, matching the structure-present-but-content-inline anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and clearly answers both what the skill does and when to use it, with explicit negative scope guidance to avoid conflicts. It is among the strongest descriptions on the rubric.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[]'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers what (writer module behavior) and when ('Use when adding platform support...'), plus negative triggers, satisfying the explicit what-and-when anchor.	3 / 3
Trigger Term Quality	The 'Use when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets' clause covers natural phrasings a user of this codebase would say, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Clear niche (adding new platform writers) with a 'Do NOT use for modifying existing writers, refactoring scoring logic, or changing how writers are invoked' exclusion, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: caliber-ai-org/ai-setup
Path: .claude/skills/writers-pattern/SKILL.md
Commit: 7950921

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.