CtrlK
BlogDocsLog inGet started
Tessl Logo

readme

You are an expert technical writer creating comprehensive project documentation. Your goal is to write a README.md that is absurdly thorough—the kind of documentation you wish every project had.

50

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/readme/SKILL.md

The canonical home for this skill is readme in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 content is highly actionable with a concrete, copy-paste-ready README template and a clear authoring workflow, but it is significantly over-long for a single SKILL.md and inlines large Rails-specific template material that would be better split into reference files. Workflow sequencing is strong though it lacks explicit validation checkpoints.

Suggestions

Move the large README section templates (architecture, env vars, deployment, troubleshooting) into a references/ file (e.g. README_TEMPLATE.md) and have SKILL.md point to it, reducing the inline body to a lean overview plus the exploration workflow.

Trim Rails-specific filler (Inertia.js, Solid Queue, Vite examples) or clearly mark it as one illustrative stack example rather than default content, to cut tokens and avoid biasing output toward Rails.

Add a final verification step to the workflow, e.g. 'After writing, verify every command in Getting Started runs on a fresh machine and that all env vars in the table appear in .env.example.'

DimensionReasoningScore

Conciseness

The body runs ~835 lines and inlines a heavily Rails-specific README template (Inertia.js, Solid Queue, Vite, schema examples) plus 8 'Writing Principles' — noticeably verbose with several padded sections that assume context Claude already has; not quite severe enough for a 1 but well below an efficient 3.

2 / 5

Actionability

Provides copy-paste-ready commands, full code blocks, env-var tables, and a concrete section-by-section output template that directly cover the common README cases; the guidance is fully executable.

5 / 5

Workflow Clarity

A clear sequence is present (explore codebase → identify deployment target → write the 12 ordered sections → apply principles), but there are no explicit validation/verification checkpoints on the produced README; minor gaps keep it just below 5.

4 / 5

Progressive Disclosure

The skill is well-sectioned with clear headers, but it is a single monolithic 835-line file with no bundle files and no external references — the large template/troubleshooting/deployment examples that belong in separate reference files are inlined, so it sits at the 'some structure but should be split' anchor.

3 / 5

Total

14

/

20

Passed

Description

48%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 states a clear purpose (generate thorough READMEs) but omits any explicit trigger guidance and uses second-person voice, costing it on completeness and specificity. It is reasonably distinct as a niche but reads more as a persona statement than a crisp skill description.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when the user asks to create or update a README.md, says "write readme" or "document this project".'

Rewrite in third person and replace quality adjectives ('absurdly thorough') with enumerated concrete actions (e.g., 'Generates a README.md covering local setup, architecture, environment variables, deployment, and troubleshooting').

Include natural keyword variants such as 'readme', 'docs', and 'document this project' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('comprehensive project documentation', 'write a README.md') with 1-2 concrete actions, but coverage is not comprehensive and it leans on quality adjectives ('absurdly thorough') rather than enumerating actions; additionally the second-person voice ('You are...', 'Your goal...') triggers a one-point specificity reduction from the anchor 3.

2 / 5

Completeness

It clearly states what the skill does ('write a README.md', 'comprehensive project documentation') but provides no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is missing — capped at 3 per the missing-trigger guidance.

3 / 5

Trigger Term Quality

Contains natural terms a user might say ('README.md', 'project documentation'), but misses common variations and synonyms such as 'readme', 'docs', or 'document this project', so it falls short of comprehensive coverage.

3 / 5

Distinctiveness Conflict Risk

README/project-documentation generation is a fairly distinct niche with minimal conflict risk against unrelated skills; only minor overlap risk exists with broader documentation skills.

4 / 5

Total

12

/

20

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (844 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.