CtrlK
BlogDocsLog inGet started
Tessl Logo

robots-txt

Use when applies to any public website. Use when auditing technical SEO foundations or diagnosing crawl coverage gaps.

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/robots-txt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured, concise overview with a clear audit workflow and exemplary progressive disclosure — implementation detail is properly split into references/rule.md, which exists and matches what the body promises. The main gaps are minor: a redundant why-it-matters opening line duplicated from the reference, and the absence of an explicit re-verification step after applying fixes.

DimensionReasoningScore

Conciseness

The body is lean — short bulleted Quick Reference, terse Check/Fix/Explain/Code Review sections — and mostly assumes Claude's competence. It loses a point because the opening line ("robots.txt is the first file crawlers fetch; misconfigured directives can silently block...") is a why-it-matters explanation Claude already knows and duplicates the same sentence verbatim in references/rule.md. Not score 3, since this is the only instance of padding and everything else earns its place; not score 5 because that duplicated motivational line could be cut.

4 / 5

Actionability

Guidance is concrete and checkable: "Fetch /robots.txt on the live domain and verify it returns HTTP 200", "Add a live Sitemap: line", "Remove any Disallow: / rules that block the whole site". Per the instruction-skill scoring note, missing code is not penalized since the guidance is actionable and the example robots.txt lives in references/rule.md, which is cleanly signaled. Not score 5 because no executable command (e.g. `curl -I`) or example directive block is inline — the concrete artifacts are one hop away in the reference.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sequence is clear and ordered, with the Check section acting as an explicit validation checkpoint (HTTP 200, syntax, accidental `Disallow: /`) and Code Review requiring the user to "describe how to verify the final page output". Not score 5 because the fix→re-verify loop is implicit — nothing tells Claude to re-run the Check after editing robots.txt — leaving a minor checkpoint gap typical of anchor 4.

4 / 5

Progressive Disclosure

The body is a short, well-sectioned overview that correctly pushes implementation details, code examples, and framework guidance to references/rule.md — a verified real file exactly one level deep, pointed to with an explicit "see `references/rule.md`" callout. This matches the anchor for a clear overview with well-signaled one-level-deep references and easy navigation.

5 / 5

Total

17

/

20

Passed

Description

32%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 effectively trigger-only: it states when to use the skill twice but never says what the skill does, and the phrase "Use when applies to any public website" is both grammatically malformed and so broad it would conflict with most web-development skills. Crucially, robots.txt — the one term that would make this distinctive and findable — is absent from the description entirely.

Suggestions

State the 'what' explicitly in third person, e.g. "Audits, creates, and fixes robots.txt files for public websites: verifies HTTP 200 responses, directive syntax, and Sitemap references."

Add the primary trigger term "robots.txt" (plus natural variations like "crawlers", "indexing", "sitemap") so the skill is findable when users mention the file by name.

Replace "Use when applies to any public website" — an overly broad, ungrammatical clause — with a scoped trigger such as "Use when robots.txt, crawler access, crawl blocking, or site indexing issues come up."

DimensionReasoningScore

Specificity

The description names no capability and never mentions robots.txt itself; the only action phrases, "auditing technical SEO foundations or diagnosing crawl coverage gaps", are generic audit/diagnosis language with no concrete action tied to the skill's actual task. It is not score 1 because those two clauses do name recognizable actions, but it fails score 3 because the domain (robots.txt) is never named and the actions are not skill-specific.

2 / 5

Completeness

Two explicit "Use when..." clauses answer 'when', but there is no 'what' at all — nothing states the skill audits, creates, or fixes a robots.txt file. This matches the anchor "only 'when' is present without 'what'". It cannot be 3 or 4 because those anchors require a clear 'what', which is entirely absent.

2 / 5

Trigger Term Quality

Relevant keywords like "technical SEO" and "crawl coverage gaps" exist, but the most natural trigger terms users would say — robots.txt, indexing, sitemap, "site not showing in Google" — are missing. Not score 4 because the coverage lacks the primary artifact term (robots.txt) and common synonyms; not score 2 because several genuinely natural SEO-audit phrases are present.

3 / 5

Distinctiveness Conflict Risk

"Use when applies to any public website" is maximally broad and would fire alongside virtually any web/SEO skill, and "auditing technical SEO foundations" overlaps heavily with sibling SEO skills (meta tags, sitemaps, canonicals). It edges above score 1 because the crawl-coverage phrasing narrows it slightly, but it lacks the niche-defining trigger (robots.txt) needed for score 3 or higher.

2 / 5

Total

9

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.