CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-rss

Use when testing the rss golden build

Quality

54%

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 ./tests/golden/phase2/rss/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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, genuinely navigable feed digest with a real one-level-deep reference bundle, but it carries duplicated metadata and a padded inline tag list, and it never tells the reader how to actually work through the lookup flow. As a lookup skill it functions, though the article summaries inlined in the overview are near the limit of what belongs in SKILL.md.

Suggestions

Merge the "Feed Statistics" section into "Feed Information" (or drop it) — Total Articles, Feed Type, Authors, and category counts are all already stated elsewhere in the body.

Move the 55-entry tag list into a `references/tags.md` file and keep only the top handful of tags inline with a pointer, removing the "... and 5 more" truncation noise.

Add a short explicit lookup sequence, e.g. "1. Find the category in Navigation below; 2. Open `references/<category>.md` for full article content; 3. Use `references/index.md` if the category is unknown" — this converts the implicit navigation into a clear workflow.

DimensionReasoningScore

Conciseness

The body is dense data rather than verbose prose, but the "Feed Statistics" section duplicates Total Articles, Feed Type, and Authors already given above, the truncated feed Description is repeated noise, and 47 inline `tagNN` entries are padding. Mostly efficient but could be tightened — anchor 3, not 4, because the duplication and tag-list padding are more than minor.

3 / 5

Actionability

"When to Use This Skill" lists concrete lookup purposes ("Reference articles...", "Look up specific topics covered in the feed") and the Navigation section names real per-category files, but the guidance stops at pointing — there are no concrete instructions for how to use the article data once found. Some concrete guidance, incomplete — anchor 3.

3 / 5

Workflow Clarity

The lookup path (category → `references/<file>.md` → `references/index.md`) is present but implicit; no explicit step sequence or guidance on navigating between the overview and reference files. It is not a destructive or batch skill, so no validation cap applies, but the implied workflow only reaches anchor 3, not 4, since the navigation flow is never spelled out.

3 / 5

Progressive Disclosure

SKILL.md is a true overview with a real five-file `references/` bundle; all referenced paths (dev_ops.md, python.md, uncategorized.md, unnamed.md, index.md) exist and are clearly signaled one level deep ("See `references/index.md` for complete feed structure"). Good structure — anchor 4, not 5, because the 55-tag list and duplicated statistics are inlined in SKILL.md rather than split into a reference file.

4 / 5

Total

13

/

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 a placeholder-quality trigger line: it provides a narrow "when" but completely omits what the skill does, what content it holds, or what actions it supports. It would rarely be selected correctly because a user has essentially no way to know it contains an RSS feed reference library.

Suggestions

State the "what" explicitly, e.g. "Provides a categorized reference of articles from the Example Engineering Blog RSS feed (dev ops, Python, uncategorized), with per-category files, authors, and tags."

Add concrete natural trigger phrases users would actually say, such as "Use when looking up Example Engineering Blog posts, finding articles by Jane Doe or John Roe, or browsing posts tagged Dev Ops or Python."

Replace the internal jargon "rss golden build" with user-facing terms like "RSS feed", "blog articles", or "engineering blog posts" so the description is distinguishable from build/testing skills.

DimensionReasoningScore

Specificity

"Use when testing the rss golden build" names a domain but lists zero concrete actions or capabilities. It falls between anchor 1 (no concrete actions) and anchor 2 (names domain, minimal actions) — the domain is named, so it sits at 2 rather than 1.

2 / 5

Completeness

Only a weak "when" is present ("Use when testing...") with no "what" whatsoever — the description never states what the skill does. This matches anchor 2 exactly; it cannot reach 3 because there is no capability statement to pair with a trigger.

2 / 5

Trigger Term Quality

The only keywords are "testing", "rss", and "golden build" — one or two generic terms, with "golden build" being internal jargon rather than a phrase a user would naturally say. Natural trigger variations and synonyms are entirely absent.

2 / 5

Distinctiveness Conflict Risk

"rss golden build" is a niche trigger term that is mostly distinct with only minor overlap risk against generic testing-related skills. It is more specific than anchor 3's "Works with document files" but lacks the concrete, comprehensive trigger set of anchor 5.

4 / 5

Total

10

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

yusufkaraaslan/Skill_Seekers

Path

tests/golden/phase2/rss/SKILL.md

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.