content-research-writer

A token-efficient writing partner that uses bounded research, numbered citations, evidence packets, and parallel sub-agents to outline, draft, and refine high-quality content with minimal context growth.

Install with Tessl CLI

npx tessl i github:0xrabbidfly/eric-cartman --skill content-research-writer

What are skills?

1.34x

Quality

40%

Does it follow best practices?

Impact

94%

1.34x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/content-research-writer/SKILL.md

SKILL.md

Review

Evals

Discovery

17%

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

This description focuses heavily on internal implementation details (token efficiency, sub-agents, evidence packets) rather than user-facing capabilities and triggers. It lacks natural language keywords users would say and has no explicit 'Use when' guidance, making it difficult for Claude to know when to select this skill over others.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'write an article', 'draft a blog post', 'create content', 'write with citations', 'research and write'

Replace technical jargon ('bounded research', 'parallel sub-agents', 'context growth') with user-facing benefits or concrete outputs (e.g., 'well-researched articles', 'cited content', 'long-form writing')

Specify the types of content this skill produces (articles, essays, reports, blog posts) to improve distinctiveness from other writing-related skills

Dimension	Reasoning	Score
Specificity	Names domain (writing) and some actions ('outline, draft, and refine'), but the description is padded with implementation details ('bounded research, numbered citations, evidence packets, parallel sub-agents') rather than concrete user-facing capabilities.	2 / 3
Completeness	Describes what it does (writing partner that outlines/drafts/refines) but completely lacks any 'Use when...' clause or explicit trigger guidance. The 'when' is entirely missing.	1 / 3
Trigger Term Quality	Uses technical jargon ('token-efficient', 'bounded research', 'evidence packets', 'parallel sub-agents', 'context growth') that users would never naturally say. Missing natural terms like 'write', 'article', 'blog post', 'essay', 'content creation'.	1 / 3
Distinctiveness Conflict Risk	'Writing partner' is fairly generic and could overlap with many content-related skills. The technical implementation details don't help distinguish when to use this vs other writing tools.	2 / 3
	Total	6 / 12 Passed

Implementation

62%

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

This is a well-structured skill with excellent workflow clarity and a thoughtful approach to token efficiency through bounded research and evidence packets. However, it leans toward describing processes rather than providing executable templates or concrete examples, and could benefit from splitting detailed schemas into referenced files to improve progressive disclosure.

Suggestions

Add concrete, copy-paste ready templates for evidence packets and source logs (e.g., actual markdown file content examples rather than just listing what fields should exist)

Extract the sub-agent output schema and evidence packet format into separate reference files (e.g., TEMPLATES.md) and link to them from the main skill

Consolidate repeated specifications (like 'max 5 bullets, max 2 quotes') into a single 'Packet Constraints' section referenced elsewhere

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some redundancy (e.g., repeating 'max 5 bullets, max 2 short quotes' multiple times, explaining what evidence packets are in multiple places). Some sections could be tightened without losing clarity.	2 / 3
Actionability	Provides clear structural guidance and schemas but lacks executable code examples. The workflow phases describe what to do conceptually but don't provide copy-paste ready templates, commands, or concrete file content examples that Claude could immediately use.	2 / 3
Workflow Clarity	Excellent multi-phase workflow with clear sequencing (Phases 0-6), explicit stop conditions ('Stop researching as soon as every factual claim has sufficient evidence'), and an escalation ladder with validation checkpoints. The merge rule and review process provide clear feedback loops.	3 / 3
Progressive Disclosure	Content is well-organized with clear sections and headers, but everything is in a single monolithic file. The folder structure suggests external organization but the skill itself doesn't reference separate files for detailed guidance (e.g., sub-agent templates, evidence packet templates could be in separate files).	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: 1 day 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.