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.

1.12x

Quality

70%

Does it follow best practices?

Impact

92%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crafting-effective-readmes/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is concise, well-structured, and assumes Claude's intelligence, scoring well on token efficiency. Its main weakness is fidelity: template and reference paths it points to do not exist in the bundle, and the review/update workflow lacks explicit validation checkpoints.

Suggestions

Reconcile references with the actual bundle — point to the real files (art-of-readme.md, make-a-readme.md, standard-readme-spec.md) or add the missing section-checklist.md/style-guide.md/using-references.md.

Add an explicit validation step to the 'Updating'/'Reviewing' workflow (e.g., verify README claims against package.json/main files and re-check until consistent) to lift workflow_clarity to 3.

Provide the referenced templates/oss.md, templates/personal.md, etc. (or inline minimal versions) so the Project Types table's pointers are actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence ('Always ask: Who will read this, and what do they need to know?'), with tables and terse steps rather than padded explanation. It does not explain what a README is or how projects work, so it earns the top anchor; not a 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	Provides concrete tables (task→when, type→template path) and specific drafting questions, but the template paths it points to ('templates/oss.md', 'templates/personal.md', etc.) are referenced as executable destinations that do not exist in the bundle. Not a 1 (it gives real structured guidance); not a 3 because the concrete pointers are incomplete/unfulfilled rather than copy-paste ready.	2 / 3
Workflow Clarity	A clear three-step sequence (Identify → Task-specific questions → Always ask) is present, but the 'Updating'/'Reviewing' tasks involve checking the README against live project state (package.json, main files) with no explicit validation checkpoint or feedback loop. Per the rubric's destructive/batch-operation note this caps the score at 2; not a 1 because steps are clearly sequenced, not a 3 because validation checkpoints are missing.	2 / 3
Progressive Disclosure	The body is a reasonable overview with a one-level-deep References section, but the listed references ('section-checklist.md', 'style-guide.md', 'using-references.md') do not exist in the bundle, while the actual files ('art-of-readme.md', 'make-a-readme.md', 'standard-readme-spec.md', etc.) are never referenced. Not a 1 (there is structure, not a monolithic wall); not a 3 because the references are broken/mismatched rather than clearly signaled and navigable.	2 / 3
	Total	9 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 cleanly pairs a 'Use when' trigger with a statement of what the skill provides, giving it strong completeness and distinctiveness. Its weakness is moderate specificity and trigger-term coverage — it relies on the single keyword 'README files' rather than enumerating concrete actions or natural term variations.

Suggestions

Enumerate 2-3 concrete capabilities (e.g., 'draft, section, review, and update READMEs') to lift specificity from 2 to 3.

Broaden trigger terms to natural variations users say, such as 'readme', 'READMEs', 'project docs', or 'documentation'.

Dimension	Reasoning	Score
Specificity	Quotes 'writing or improving README files' and 'provides templates and guidance matched to your audience and project type' — it names the domain and some actions (writing/improving, providing templates) but stops short of listing multiple concrete capabilities. Not a 1 (it is not vague like 'Helps with documents'); not a 3 because it does not enumerate several specific concrete actions.	2 / 3
Completeness	Explicitly states what it does ('provides templates and guidance matched to your audience and project type') and when to use it ('Use when writing or improving README files'), answering both what AND when. Matches the 3-anchor example that pairs capabilities with a 'Use when' trigger.	3 / 3
Trigger Term Quality	Includes the natural term 'README files' in a 'Use when' clause, but does not cover common variations users might say ('readme', 'READMEs', 'docs', 'documentation'). Not a 1 (it has a genuine natural keyword); not a 3 because coverage of natural variations is thin.	2 / 3
Distinctiveness Conflict Risk	The README-authoring niche is distinct and the trigger ('writing or improving README files') is unlikely to fire for unrelated skills. Not a 2 because it is more specific than 'Works with document files' and has a clear, non-overlapping trigger.	3 / 3
	Total	10 / 12 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: joshuadavidthomas/agent-skills
Path: crafting-effective-readmes/SKILL.md
Commit: 516dee7

Reviewed: 11 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.