prp-technical-writing

Writes and edits developer documentation that is easy to act on and hard to misread. Use when writing or reviewing a README, RFC, tutorial, how-to guide, reference document, or technical explanation, when the operator says "write the docs", "improve this README", "edit this RFC", or invokes /prp-technical-writing.

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

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 instruction skill with a clear numbered workflow, real one-level-deep references, and concrete verification guidance. The main improvement room is in turning the validation step into an explicit fix-and-revalidate loop and tightening conditional guidance.

Suggestions

Make Step 4 'Prove the document' an explicit feedback loop: when a check fails, fix the claim/source and re-verify before proceeding, mirroring the validate-fix-retry pattern.

Replace conditional phrasing like 'when doing so is safe and relevant' with a concrete rule for when to run vs. when to mark a claim as unverified.

Trim the Scope section's enumeration of deferred skills (UI copy, /prp-commit, /prp-pr) to a single sentence to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	Lean and directive with no explaining of concepts Claude already knows, but a few passages (e.g., the scope-exclusion detail on UI copy and commit messages) could be trimmed further, keeping it just below the every-token-earns-its-place anchor.	4 / 5
Actionability	Concrete directives throughout ('Check every named symbol, path, flag, link, count, command... Run examples and commands when safe'), and absence of code is appropriate for an instruction-only skill, but some guidance is conditional ('when doing so is safe and relevant') leaving minor gaps.	4 / 5
Workflow Clarity	Clear 1-5 sequence with an explicit validation step (Step 4 'Prove the document') and a review pass (Step 5 'Edit once more'), but validation is checklist-style rather than a fix-then-revalidate retry loop, so it falls short of the explicit-feedback-loop anchor.	4 / 5
Progressive Disclosure	The body is an overview that signals one-level-deep references ('Before drafting, read references/document-modes.md') and lists both real reference files in Resources with one-line descriptions, matching the clear-overview-with-well-signaled-references anchor.	5 / 5
	Total	17 / 20 Passed

Description

90%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 explicit what/when structure, abundant natural trigger phrases, and clear scope boundaries that distinguish it from sibling skills. The only weakness is action specificity, limited to 'writes and edits' without enumerating more concrete operations.

Dimension	Reasoning	Score
Specificity	Names the developer-documentation domain and two concrete actions ('Writes and edits'), but does not enumerate several distinct actions, matching the 1-2-concrete-actions anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	Explicitly answers both what ('Writes and edits developer documentation that is easy to act on and hard to misread') and when ('Use when writing or reviewing a README, RFC, tutorial... when the operator says...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including quoted user phrases ('write the docs', 'improve this README', 'edit this RFC') plus synonyms (README, RFC, tutorial, how-to guide, reference document, technical explanation).	5 / 5
Distinctiveness Conflict Risk	Clear developer-documentation niche with distinct triggers and explicit scope exclusions (UI copy, commit messages, PR descriptions left to other skills), giving minimal conflict risk.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: .claude/skills/prp-technical-writing/SKILL.md
Commit: d62c3ae

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.