code-prose

Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior. Use when names, word choice, or comments need an editorial pass.

Quality

84%

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

87%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 tight, well-structured editorial skill that is both concise and actionable with clear sectioning and a single one-level reference. Its only real gap is workflow rigor: it instructs running existing checks after changes but does not spell out a validate→fix→re-run feedback loop for a skill that modifies code.

Suggestions

Add an explicit validation feedback loop: after running the existing checks, state that failures must be fixed and the checks re-run until they pass before considering the pass complete.

Spell out the workflow as numbered steps (review in-scope changes → apply Orwell's criteria to identifiers/comments → run existing checks → fix and re-run until green) so the sequence and checkpoint are unambiguous.

Clarify what 'run the relevant existing checks' means when no checks exist in the scope — give a fallback (e.g., note that fact to the user rather than skipping verification).

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient at roughly 40 lines, assumes Claude's competence, and never over-explains known concepts (it quotes only the four relevant Orwell rules rather than lecturing on the essay). Every token earns its place.	5 / 5
Actionability	Guidance is concrete and specific: numbered naming rules, ✅/❌ examples (lastObservedDiskContent → baseline), a vocabulary example (sync), and explicit add/delete comment criteria. As an instruction-only skill with no need for executable code, the actionable guidance covers the common cases.	5 / 5
Workflow Clarity	The opening gives a sequence (review in-scope changes → apply criteria without changing behavior → only touch in-scope code → run existing checks), but validation is a single mention with no explicit fix→re-run feedback loop. Because the skill edits code across a scope (batch-ish), the missing retry checkpoint caps this at 3.	3 / 5
Progressive Disclosure	Well-organized sections (Word choice → Names → Comments → Overfitting) with a single, clearly signaled one-level cross-reference to the refactoring skill. As a simple, single-purpose skill under 50 lines with no need for bundle files, the clean structure earns the top score.	5 / 5
	Total	18 / 20 Passed

Description

75%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 concise, third-person description that clearly states both capability and trigger, with a distinct niche and minimal conflict risk. It is slightly light on enumerated concrete actions and natural keyword variations, which caps specificity and trigger-term quality at the midpoint.

Dimension	Reasoning	Score
Specificity	Names the domain ('prose inside code — identifiers and comments') and two concrete actions (apply Orwell's rules, editorial pass) without changing behavior, matching the anchor for 1-2 concrete actions. It does not list several specific actions, so it does not reach 4.	3 / 5
Completeness	It explicitly answers both 'what' (apply Orwell's rules to identifiers and comments without changing behavior) and 'when' ('Use when names, word choice, or comments need an editorial pass') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It offers some natural keywords ('names, word choice, or comments need an editorial pass') but lacks common variations or synonyms (e.g. 'rename', 'refactor names', 'rewrite comments'). 'Editorial pass' is a slightly unusual user utterance, keeping it below 4.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (editorial prose pass on code identifiers and comments) and explicitly defers the structural half to the refactoring skill, minimizing overlap and conflict risk.	5 / 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/code-prose/SKILL.md
Commit: f9441c8

Reviewed: 3 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.