CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-pptx

Use when testing the pptx golden build

Quality

47%

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/pptx/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%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 works as a navigable index — references are real, clearly signaled, and one level deep — but most of the inlined material is scraper-generated padding rather than instruction. There is no workflow, no actionable guidance, and the long truncated code example wastes tokens.

Suggestions

Remove the scraper metadata blocks (Presentation Information, Presentation Statistics, per-example 'Quality' scores) and the broken 50-line variable-assignment example; move any retained examples into references/deck.md.

Replace the vague 'When to Use This Skill' bullet list with one or two concrete instructions tied to the reference files, e.g., 'For slide-by-slide content including speaker notes, read references/deck.md.'

State the single expected action explicitly (consult references/index.md then deck.md) so the skill has an unambiguous workflow even though it is a reference-style skill.

DimensionReasoningScore

Conciseness

The body is padded with scraper metadata (Presentation Information, Presentation Statistics, quality labels like 'Quality: 6.0/10') and a ~50-line trivial variable-assignment example ('x0 = 0' ... 'x37 = 37', truncated mid-line) that teaches nothing. It is not the worst case (anchor 1 requires extensive explanation of concepts Claude already knows), so anchor 2 ('noticeably verbose; several padded sections') is the best fit.

2 / 5

Actionability

The 'When to Use This Skill' bullets ('Understand golden_pptx concepts and fundamentals', 'Review presentation content and key points') are high-level hints, and the code blocks are extracted presentation artifacts ('pip install thing', a truncated placeholder function) rather than executable guidance. This matches 'minimal concrete guidance; high-level hints but missing the specific steps to execute' rather than anchor 3, whose code would at least run as shown.

2 / 5

Workflow Clarity

No sequence of steps exists anywhere in the body; the only direction is the Navigation pointer to references/index.md. The simple-skill exception (score 5 for an unambiguous single action) does not apply because the intended action is never stated, leaving 'rough direction present but poorly defined' as the best fit over anchor 1, which requires the content to be incoherent rather than merely directionless.

2 / 5

Progressive Disclosure

Scored against the actual bundle: references/deck.md and references/index.md exist, are explicitly signaled in a Navigation section ('Reference Files: references/deck.md', 'See references/index.md for complete presentation structure'), and index.md links one level deep to deck.md. It falls short of anchor 5 because content that belongs in references (full code examples, tables, statistics) is inlined in SKILL.md instead of being appropriately split.

4 / 5

Total

10

/

20

Passed

Description

36%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 short and has an explicit 'Use when...' trigger, but it names almost no concrete capabilities, leaving the 'what' essentially unanswered. It reads more like an internal test note than a user-facing skill description, and would be hard to distinguish from other pptx-related skills.

Suggestions

State concrete capabilities in third person, e.g., 'Extracts slide content, speaker notes, tables, and code examples from the golden_pptx reference deck.'

Expand trigger terms with natural variations users would say: pptx, PowerPoint, presentations, .pptx, golden build verification.

Pair the 'when' clause with an explicit 'what' clause so both halves of the completeness question are answered, e.g., '... Use when the user asks about the golden pptx deck, its slides, notes, or embedded examples.'

DimensionReasoningScore

Specificity

The phrase 'testing the pptx golden build' names a domain and one minimal action (testing), but lists no concrete capabilities (e.g., what is tested, how, or what output is produced). It matches 'names the domain but actions are minimal or generic' rather than anchor 3, which requires 1-2 concrete actions beyond the domain name.

2 / 5

Completeness

The description provides an explicit 'when' ('Use when testing the pptx golden build') but no meaningful 'what' — no capabilities or actions are described beyond a vague testing reference. This matches anchor 2 ('only when is present without what') better than anchor 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

'pptx' and 'testing' are relevant keywords a user might say, but the description misses common variations and synonyms (presentations, PowerPoint, .pptx files, golden build verification). It fits 'some relevant keywords but missing common variations or synonyms' and is not the level-4 example of good coverage.

3 / 5

Distinctiveness Conflict Risk

'pptx golden build' is a somewhat specific niche, but with no capability description it is hard to distinguish from generic pptx/presentation skills, so overlap risk remains. It is not level 4 ('mostly distinct') because the description gives no unique capability signature beyond the niche name.

3 / 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/pptx/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.