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.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/content-research-writer/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

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

The content is a well-sequenced, actionable workflow with explicit checkpoints, feedback loops, and a review checklist, scoring high on workflow clarity and actionability; the main weakness is mild redundancy of the budget/cap figures across several sections.

Suggestions

State the source/packet caps once (e.g. in the Key Constraints table) and reference that table from Phase 2 and Evidence Packet to remove the repeated 3-5/8-12/5-bullet/2-quote figures.

Provide the sub-agent 'strict output schema' as a copy-pasteable template (e.g. a fenced block or JSON-like structure) instead of a prose bullet list.

Consider moving the Evidence Packet spec and Citation format into a one-level-deep reference file to tighten SKILL.md into a true overview.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence (no 'what is a citation' padding), and uses bullets/tables well; held at 4 because the source-budget and packet caps (3-5 sources, 8-12 packets, max 5 bullets, max 2 quotes) are restated across the intro, Defaults, Key Constraints table, Phase 2, and Evidence Packet sections and could be consolidated.	4 / 5
Actionability	Highly concrete for an instruction-only skill: exact folder names ('00-brief/', '01-outline/'), naming patterns ('EP-###-claim-slug.md'), a packet field list, sub-agent roles with a strict output schema, and a ready citation format; not 5 because the 'strict output schema' is a prose field list rather than a copy-pasteable template.	4 / 5
Workflow Clarity	Phases 0-6 are explicitly sequenced with an overview line, an explicit stop condition ('Stop researching as soon as every factual claim... has at least one sufficient evidence packet'), a no-source fallback, a 5-step escalation ladder (feedback loop), and a Phase 6 review checklist, satisfying clear sequence + validation + feedback loops + checklist.	5 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and a quick-reference constraints table, and no nested/buried references; not 5 because no bundle files exist and the file exceeds 50 lines, so the 'well-organized sections alone' exception does not fully apply and some spec detail (packet schema, citation format) could live in a one-level-deep reference.	4 / 5
	Total	17 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 and distinguishes the skill well via its citation/research mechanisms, but it omits any explicit 'Use when' trigger guidance and relies on mechanism jargon over natural user phrasing, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing blog posts, articles, newsletters, memos, or technical explainers that need cited sources'.

Trade one mechanism term ('evidence packets' or 'parallel sub-agents') for natural user vocabulary like 'articles', 'newsletters', or 'essays' to improve trigger-term match.

Lead with the user-facing task ('outline, draft, and refine articles and blog posts') before the efficiency mechanisms so the niche reads as a writing skill first.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('outline, draft, and refine high-quality content') plus specific mechanisms ('bounded research, numbered citations, evidence packets, and parallel sub-agents'), with only minor coverage gaps; not a full 5 because 'high-quality content with minimal context growth' is an outcome claim rather than another distinct action.	4 / 5
Completeness	The 'what' is clear (a token-efficient writing partner that outlines/drafts/refines with citations), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural verbs ('outline, draft, and refine', 'writing partner') are present, but the trigger vocabulary leans on mechanism jargon ('evidence packets', 'parallel sub-agents', 'bounded research') rather than the synonyms users actually say ('blog post', 'article', 'newsletter', 'essay', 'edit'), so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	The distinctive research-and-citation mechanisms ('evidence packets', 'parallel sub-agents', 'numbered citations', 'bounded research') carve out a clear niche with minimal conflict risk; held at 4 rather than 5 because 'writing partner' still overlaps loosely with generic writing/editing skills.	4 / 5
	Total	14 / 20 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: 0xrabbidfly/eric-cartman
Path: .github/skills/content-research-writer/SKILL.md
Commit: 0b8453f

Reviewed: 5 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.