writing-clearly-and-concisely
Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.
Install with Tessl CLI
npx tessl i github:softaworks/agent-toolkit --skill writing-clearly-and-conciselyOverall
score
86%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with a clear 'Use when...' clause and good trigger term coverage across multiple content types. The main weakness is the lack of specific concrete actions—it says it applies 'Strunk's rules' but doesn't enumerate what those rules actually do (e.g., 'eliminates passive voice', 'removes unnecessary words', 'tightens sentences').
Suggestions
Add 2-3 specific actions that describe what the skill does, e.g., 'Eliminates passive voice, removes unnecessary words, tightens sentences'
Consider narrowing scope or adding more distinctive triggers to reduce potential overlap with other writing/style skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prose writing) and lists several types of content (documentation, commit messages, error messages, explanations, reports, UI text), but doesn't describe concrete actions—only mentions 'Applies Strunk's timeless rules' without specifying what those rules do. | 2 / 3 |
Completeness | Explicitly answers both what ('Applies Strunk's timeless rules for clearer, stronger, more professional writing') and when ('Use when writing prose humans will read') with a clear 'Use when...' clause at the start. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'documentation', 'commit messages', 'error messages', 'explanations', 'reports', 'UI text', 'writing', 'prose'. These are terms users naturally use when requesting help with written content. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies 'prose humans will read' and references Strunk's rules, the broad scope (documentation, commit messages, error messages, etc.) could overlap with other writing-focused skills or style guides. The Strunk reference adds some distinctiveness but isn't a strong differentiator. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that efficiently communicates writing principles without over-explaining. Its main strength is excellent progressive disclosure with clear pointers to reference files and token budgets. The primary weakness is limited actionability—while rules are listed clearly, concrete before/after examples demonstrating their application would make the skill more immediately useful.
Suggestions
Add 2-3 concrete before/after examples showing rules applied (e.g., passive→active voice transformation, removing puffery from a sentence)
Include a brief example of the subagent dispatch pattern mentioned in the Limited Context Strategy section
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, assuming Claude's competence. It provides rules as numbered lists without over-explaining concepts Claude already knows, and uses a table for quick reference to external files with token counts. | 3 / 3 |
Actionability | Provides clear rules and anti-patterns to avoid, but lacks concrete before/after examples showing the rules applied. The guidance is specific but not fully executable—no demonstration of transforming bad prose to good prose. | 2 / 3 |
Workflow Clarity | For a writing skill, the workflow is clear: write draft, optionally dispatch subagent with relevant section file, apply rules. The 'Limited Context Strategy' provides explicit steps, and the skill clearly indicates which file to use for most tasks. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, clear table pointing to one-level-deep reference files with token counts, and explicit guidance that 'most tasks need only' one specific file. Navigation is well-signaled and organized. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
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.