crafting-effective-readmes
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
76
64%
Does it follow best practices?
Impact
92%
1.12xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./dist/plugins/crafting-effective-readmes/skills/crafting-effective-readmes/SKILL.mdQuality
Discovery
67%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 has a clear 'Use when' trigger clause and identifies its domain well, but lacks specificity in the concrete actions it performs. It uses second person ('your audience') which is a minor style issue, and could benefit from more natural trigger terms and more detailed capability listing to better distinguish it from general documentation skills.
Suggestions
Add specific concrete actions like 'generates badges, creates table of contents, structures installation/usage/API sections, adds contributing guidelines'
Include more trigger term variations such as 'README.md', 'project documentation', 'repo docs', 'getting started section'
Replace second person 'your audience' with third person phrasing like 'the target audience' to match style guidelines
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (README files) and mentions some actions ('writing or improving', 'provides templates and guidance'), but doesn't list specific concrete actions like 'generate badges, create table of contents, add installation instructions, structure API documentation sections'. | 2 / 3 |
Completeness | Explicitly answers both 'what' (provides templates and guidance matched to audience and project type for README files) and 'when' ('Use when writing or improving README files'). The 'Use when...' clause is present and clear. | 3 / 3 |
Trigger Term Quality | Includes 'README' as a natural keyword users would say, but misses common variations like 'README.md', 'project documentation', 'repo description', 'getting started guide'. The terms 'templates' and 'guidance' are somewhat relevant but not primary trigger terms users would use. | 2 / 3 |
Distinctiveness Conflict Risk | README files are a fairly specific niche, but the description could overlap with general documentation skills or writing skills. The mention of 'templates and guidance matched to your audience and project type' adds some distinctiveness, but 'writing or improving' is broad enough to potentially conflict with general writing/documentation skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
62%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 instructional skill with a clear workflow for different README tasks and good use of tables for decision-making. Its main weaknesses are the lack of concrete output examples (actual README snippets) inline and some mild verbosity in the process steps. The references to external templates and guides are well-organized but unverifiable without bundle files.
Suggestions
Add at least one concrete, copy-paste-ready README example (e.g., a minimal README for a personal project) to improve actionability.
Trim the 'Step 2: Task-Specific Questions' section — some sub-questions (like 'Who needs this info most?') are things Claude can infer without explicit prompting.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary scaffolding. The tables and step-by-step process are useful but the 'Always Ask' step and some of the task-specific questions feel like padding for what Claude could infer. The content could be tightened. | 2 / 3 |
Actionability | Provides structured guidance with clear questions to ask and a decision matrix for project types, but lacks concrete examples of actual README output. No executable code or copy-paste-ready README snippets are shown inline — the templates are deferred to external files. | 2 / 3 |
Workflow Clarity | The three-step process (identify task → ask task-specific questions → confirm with user) is clearly sequenced and appropriate for this type of skill. Each task variant has explicit sub-steps, and the review task includes a validation-like checkpoint (check against actual project state). | 3 / 3 |
Progressive Disclosure | References to templates (templates/oss.md, etc.) and supporting files (section-checklist.md, style-guide.md, using-references.md) are well-signaled and one level deep. However, no bundle files were provided, so we cannot confirm these references actually exist, and the inline content includes the full project types table that could arguably live in a reference file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- softaworks/agent-toolkit
- Commit
3027f20
- 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.