technical-articles

Technical articles and blog posts with honest trade-offs. Use when: "write a blog post", "draft an article", "write about this", creating articles in docs/articles/.

Quality

82%

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

86%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.

A well-structured, highly actionable writing-style guide: concrete numeric rules, worked good/bad examples, a clear architecture-article workflow, and clean one-level-deep references. The only real weakness is mild redundancy across sections that could be tightened for token efficiency.

Suggestions

Dedupe the title-as-takeaway guidance so it lives in one place and is merely cross-referenced elsewhere, trimming tokens.

Add an explicit validation/feedback checkpoint to the Architecture Article Composition workflow (e.g., re-read headings to confirm each is an argument before applying the voice pass).

Consolidate the overlapping transcript-fidelity rules in 'When the User Gave You the Voice, Use It' to reduce repetition.

Dimension	Reasoning	Score
Conciseness	The body is opinionated and uses concrete before/after (good/bad) examples that earn their place, and it does not re-teach concepts Claude already knows. It is not 3 (no padded concept explanation) but not 5 because some guidance is restated across sections (e.g., the title-as-takeaway rule appears in Core Principles, Section Headings, and the good/bad lists).	4 / 5
Actionability	As an instruction-only writing skill, it provides concrete, copy-applicable rules with specific thresholds ('Max 3-4 sentences of prose before a code block', 'max 1-2 of each per article', '30-50 lines', '80-150 lines') and worked good/bad examples. Matches the 5 anchor for instruction skills where guidance is specific and covers common cases; not 4 because there are no material gaps.	5 / 5
Workflow Clarity	The Architecture Article Composition section gives a clearly numbered 3-step sequence (build private model → turn into public argument → apply voice) and rhythm rules are explicitly numbered. Not 3 because the sequence is well-defined and the destructive/batch validation cap does not apply to prose drafting, and not 5 because no explicit validation or feedback-loop checkpoints are given.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained; it has clear section headings and only one-level-deep, clearly signaled external references to ../writing-voice/SKILL.md. Per the simple-skill scoring note, a self-contained, well-organized skill with no bulk reference content to split out scores 5; not 4 because nothing that belongs in a separate file is inlined.	5 / 5
	Total	18 / 20 Passed

Description

78%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.

A strong description with an explicit 'Use when' clause and natural quoted trigger phrases, scoring high on completeness and trigger quality. The main gap is specificity, where concrete capabilities (article shapes, types of trade-offs) are not enumerated.

Suggestions

Enumerate 1-2 concrete actions or article types in the description (e.g., 'draft problem→fix writeups, mechanism explainers, and tradeoff comparisons') to lift specificity.

Add a couple of natural synonyms or extensions (e.g., 'essay', 'publish', '.md') to round out trigger term coverage toward a 5.

Narrow the broad 'write about this' trigger to reduce overlap risk with a generic writing skill.

Dimension	Reasoning	Score
Specificity	Names the domain ('technical articles and blog posts') and one distinguishing trait ('honest trade-offs'), but lists no concrete actions comparable to the rubric's worked examples. It is above 2 because a concrete trait is named, but not 4 because no list of several specific capabilities is given.	3 / 5
Completeness	Clearly answers both 'what' (technical articles and blog posts with honest trade-offs) and 'when' (explicit 'Use when:' clause listing concrete quoted trigger phrases). Matches the 5 anchor; not 4 because the 'when' is concrete and specific rather than weakly implied.	5 / 5
Trigger Term Quality	Includes three natural quoted phrases a user would actually say ('write a blog post', 'draft an article', 'write about this') plus a path-based trigger. Above 3 because the triggers are genuine natural speech with synonyms (blog post / article), but not 5 because file extensions and further synonyms (essay, publish, .md) are absent.	4 / 5
Distinctiveness Conflict Risk	The technical-articles niche plus the docs/articles/ path hint and quoted triggers make it mostly distinct with only minor overlap risk against a generic writing skill. Not 3 (clearer niche than 'Works with document files') and not 5 (the broad 'write about this' trigger and overlap with the referenced writing-voice skill leave some residual risk).	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/technical-articles/SKILL.md
Commit: abe10f3

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.