agent-style

Literature-backed English technical-prose writing rules (agent-style, 21 rules). Its lane is FORMAL technical prose (papers, design docs, proposals, READMEs, commit messages). Use ONLY when the user explicitly asks for agent-style by name (e.g. "apply agent-style", "write/revise this per agent-style rules", "iterate until agent-style clean"). NOT for de-AI-ing casual or voiced text — use remove-ai-patterns for that. Do not auto-trigger for ordinary prose or documentation tasks.

Quality

86%

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

78%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, lean ruleset skill that correctly externalizes its bulk content to references/RULES.md with a clear resolution order. The main weaknesses are minor meta-padding and the absence of an explicit verification loop for the core revision task.

Suggestions

Move the maintainer-oriented Optional Deterministic Audit and Updating sections into a separate MAINTENANCE.md (or trim them) so the user-facing overview stays leaner and earns full conciseness credit.

Inline one or two BAD→GOOD example pairs for the highest-severity rules (e.g., RULE-04 Needless words, RULE-08 Claim calibration) so Claude can apply them without first loading references/RULES.md.

Add an explicit apply→verify→iterate loop for the common "revise this per agent-style" task (e.g., "edit the prose, re-scan against RULE-01..12, repeat until no violations remain") to give the core workflow a concrete validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The 21 rules are compact one-line directives that assume Claude's competence, but the Optional Deterministic Audit and Updating sections are maintainer-oriented meta-content that slightly pads the user-facing overview.	4 / 5
Actionability	Rules give concrete good/bad word pairs ("use" over "leverage") and an executable CLI ("uv tool install agent-style"; "agent-style audit FILE"), but full BAD/GOOD example pairs are deferred to references/RULES.md, leaving minor gaps.	4 / 5
Workflow Clarity	A numbered resolution order (project RULES.md → references/RULES.md → upstream repo) sequences full-body lookup, and the Updating step has a review/flag checkpoint, but the core "revise this per agent-style" task lacks an explicit apply→verify→iterate loop.	4 / 5
Progressive Disclosure	The body is a lean overview pointing to references/RULES.md (a verified 90KB vendored snapshot) via a clearly signaled, one-level-deep resolution order, with bulk content appropriately split out and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

95%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 precise, well-scoped description that clearly states what the skill is, when to use it, and how it differs from a sibling skill. Trigger phrasings are quoted exactly as users would say them, and negative guidance prevents misfires.

Dimension	Reasoning	Score
Specificity	Names the domain ("English technical-prose writing rules", "21 rules") and concrete prose types (papers, design docs, proposals, READMEs, commit messages), giving several specific anchors with only minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what (a literature-backed ruleset for formal technical prose) and when ("Use ONLY when the user explicitly asks for agent-style by name") with concrete trigger phrases and negative boundaries.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrasings, quoting "apply agent-style", "write/revise this per agent-style rules", and "iterate until agent-style clean" exactly as a user would say them.	5 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers and an explicit disambiguation from remove-ai-patterns ("NOT for de-AI-ing casual or voiced text — use remove-ai-patterns for that"), minimizing conflict risk.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: pchalasani/claude-code-tools
Path: plugins/writing/skills/agent-style/SKILL.md
Commit: c35a135

Reviewed: about 13 hours 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.