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

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

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.

The body is a concise, well-structured instruction skill with clear sequencing, a verification checkpoint, and clean progressive disclosure into two real reference files. Its main gap is the absence of worked examples and an explicit error-recovery feedback loop in the prove step.

Suggestions

Add a short worked example (e.g. a before/after sentence edit or a verified-vs-unverified claim pair) to push actionability toward the top anchor.

Turn the "Prove the document" step into an explicit validate→fix→retry loop (verify against source, list failures, fix, re-verify) to reach the top workflow-clarity anchor.

Optionally add a brief checklist of the named-symbol categories to verify (symbol, path, flag, link, count, command, result) so the prove step reads as a concrete checklist.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive, with no explanation of concepts Claude already knows (no "what a README is" padding); every line is actionable guidance that earns its place, matching the top anchor.	5 / 5
Actionability	Concrete, specific directives (use real symbols/paths/flags; check every named symbol, path, flag, link; run examples; state what is unverified) are actionable, but as an instruction-only skill it lacks worked examples or copy-paste-ready snippets covering common cases, sitting just below the top anchor.	4 / 5
Workflow Clarity	A clear five-step sequence (establish source of truth, choose mode, write, prove, edit) with an explicit verification checkpoint in "Prove the document" and a read-only vs. edit boundary in Scope, but it lacks a structured validate→fix→retry feedback loop and checklists, so it does not reach the top anchor.	4 / 5
Progressive Disclosure	SKILL.md is a lean overview that points to two real one-level-deep reference files (document-modes.md, sentence-style.md), each signaled both at its point of use and in a Resources section with one-line descriptions, matching the top anchor for clear, well-signaled shallow references.	5 / 5
	Total	18 / 20 Passed

Description

86%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 strong: it states what the skill does and gives rich, natural trigger phrases covering multiple document types and operator phrasings. Its only weakness is that the capability verbs ("writes and edits") are somewhat generic compared to the breadth of its triggers.

Suggestions

Add one or two more concrete actions beyond "writes and edits" (e.g., "structures", "proves against source", "de-jargons") to lift specificity toward the top anchor.

Tighten the niche framing slightly to reduce residual overlap with general writing/editing skills, e.g. by foregrounding the "hard to misread / easy to act on" framing as the distinguishing purpose.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Writes and edits developer documentation"), matching the anchor for domain plus 1-2 actions; it does not list several specific actions, so it does not reach 4.	3 / 5
Completeness	Explicitly answers both what (writes/edits developer documentation easy to act on) and when ("Use when writing or reviewing a README, RFC, tutorial..."), with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including concrete document types (README, RFC, tutorial, how-to, reference) and quoted operator phrases ("write the docs", "improve this README", "edit this RFC"), matching the anchor for synonyms and natural terms.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (developer documentation) with distinct triggers and minimal conflict risk, but the domain is somewhat broader than a single-file-type niche and could lightly overlap with general writing/editing skills, so it sits just below the clearest-niche anchor.	4 / 5
	Total	17 / 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: Wirasm/prp
Path: .agents/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.