CtrlK
BlogDocsLog inGet started
Tessl Logo

llms-txt

Use when auditing public documentation portals, API references, help centers, SDK docs, or large knowledge bases. Check the final file served at `/llms.txt` and verify that the linked pages are stable, high-value, and accessible without relying on a JavaScript-only interface.

64

Quality

77%

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/llms-txt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A well-structured, concise overview body that handles progressive disclosure cleanly and lays out a coherent audit workflow. The main gap is actionability: the body tells Claude what to confirm but defers every executable detail (commands, the llms.txt format) to the reference file, leaving the in-body guidance directional rather than directly executable.

Suggestions

Add one inline executable check command (e.g., a curl status check for `/llms.txt` and linked URLs) so the Check section can be acted on without opening the reference.

Inline a minimal llms.txt format example (project heading, curated link list with one-line descriptions) in the Fix section, keeping the fuller code examples in references/rule.md.

Close the workflow loop by adding a post-Fix re-verification step (re-check that the file is served and linked URLs return HTTP 200) to satisfy the feedback-loop pattern.

DimensionReasoningScore

Conciseness

The body is lean with well-scoped sections and no explanation of concepts Claude already knows. Minor trimming is possible: the Quick Reference bullets ("Serve `llms.txt` at the root…", "Keep crawl and indexing controls in `robots.txt`") largely restate points already made in Check and Fix, which keeps it below anchor 5.

4 / 5

Actionability

Guidance names concrete goals ("Confirm that linked URLs return HTTP 200", "Add `llms.txt` at the site root with a short description of the project") but omits the how: no fetch/status-check command is given, and the llms.txt file format exists only in references/rule.md rather than as an inline example. Anchor 3 fits — concrete but incomplete with key execution details deferred; not anchor 4 since nothing in the body itself is directly executable.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review structure gives a clear sequence, and the Check section embeds verification criteria (HTTP 200 on linked URLs, llms.txt not replacing robots.txt/sitemaps), satisfying most checkpoints. It falls short of anchor 5 because there is no re-verify step after Fix and no explicit ordered step list, leaving a minor validation gap.

4 / 5

Progressive Disclosure

The body is a short, well-organized overview (Quick Reference, Check, Fix, Explain, Code Review) that defers all implementation detail to a single, clearly signaled, one-level-deep reference: "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — a real file in the bundle. This matches the anchor-5 pattern of a clean overview with well-signaled shallow references.

5 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description with an explicit "Use when" trigger clause and concrete, verifiable audit actions anchored to a distinctive artifact (`/llms.txt`). Third-person voice is used throughout, and no fluff or over-claims are present. The only weaknesses are minor: a few missing natural trigger synonyms and slight overlap risk with generic docs-audit phrasing.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Check the final file served at `/llms.txt`", "verify that the linked pages are stable, high-value, and accessible without relying on a JavaScript-only interface" — going beyond the 1-2 actions of anchor 3. It falls short of anchor 5 only because coverage isn't comprehensive (no fix or reporting actions named).

4 / 5

Completeness

Both questions are answered explicitly: the what ("Check the final file served at `/llms.txt` and verify that the linked pages are stable, high-value, and accessible") and the when ("Use when auditing public documentation portals, API references, help centers, SDK docs, or large knowledge bases") with concrete trigger contexts. This matches the anchor-5 pattern exactly.

5 / 5

Trigger Term Quality

Natural triggers like "documentation portals, API references, help centers, SDK docs, large knowledge bases" plus the distinctive `llms.txt` term give good keyword coverage a user would actually say. A few natural variants (e.g., "developer docs", "docs site", "llms-full.txt") are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The `llms.txt` check is a clear niche with distinct triggers, but the broad opening phrase "auditing public documentation portals" creates minor overlap risk with general documentation/SEO audit skills. It is mostly distinct rather than minimally-conflicting (anchor 5) because the domain terms alone don't disambiguate before the llms.txt specifics appear.

4 / 5

Total

17

/

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.