CtrlK
BlogDocsLog inGet started
Tessl Logo

pptx-author

Build PowerPoint decks headless with python-pptx.

54

Quality

63%

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 ./optional-skills/finance/pptx-author/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 complete, executable code and a clear structural skeleton for building decks, supported by sensible conventions and a slide-type checklist. It is mostly concise and well-organized; the main gaps are a missing explicit post-save validation checkpoint and a couple of inline blocks that could be reference files.

Suggestions

Add an explicit validation checkpoint after `prs.save(...)` — e.g. reopen the file with python-pptx and assert slide count / placeholder text — to close the workflow-clarity gap.

Consider moving the 13-item pitch-deck checklist and/or the full Skeleton into a `references/` file referenced from the body, improving progressive disclosure toward level 5.

Trim minor over-explanation such as the one-idea-per-slide gloss and the rationale for `pip install python-pptx` to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is mostly lean — code-heavy with short directive prose like "Never transcribe numbers from memory" and "Native pptx.chart charts are fragile" — with only minor over-explanation (e.g. restating the python-pptx install rationale and the one-idea-per-slide gloss), placing it just below the fully lean level 5.

4 / 5

Actionability

It provides copy-paste-ready, fully executable code: the full Skeleton builds a multi-slide deck, the openpyxl `nr()` helper resolves named ranges, and `add_picture`/`add_table` snippets are concrete and complete, covering the common cases the skill targets.

5 / 5

Workflow Clarity

There is a clear output contract, setup, conventions, and a slide-type checklist giving sequence, plus a recalc-before-read warning; however the batch/destructive-adjacent save step lacks an explicit validate-after-save checkpoint, so it sits just below the level-5 'explicit validation steps' anchor.

4 / 5

Progressive Disclosure

The body is well-organized into clear sections (Output contract, Setup, Core conventions, Skeleton, Binding, Checklist, When NOT to use) with no bundle files to split out, but it inlines a fairly long Skeleton and 13-item checklist that could live in a reference, leaving it just below the ideal level-5 split.

4 / 5

Total

17

/

20

Passed

Description

45%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 clear and distinctive about what the skill does (headless python-pptx deck building) but omits any explicit 'Use when...' trigger guidance and lacks natural trigger-term variants like 'presentations' or '.pptx'. Adding a trigger clause and synonyms would materially raise completeness and trigger-term quality.

Suggestions

Append an explicit 'when' clause, e.g. 'Use when you need to generate a .pptx file artifact from a model rather than drive a live PowerPoint session.'

Add natural trigger terms and synonyms users would say — 'presentations', '.pptx files', 'pitch decks', 'slides' — to broaden keyword coverage.

Optionally list 1-2 more concrete capabilities (e.g. embed charts from a workbook, bind table values to named ranges) to lift specificity toward level 4.

DimensionReasoningScore

Specificity

"Build PowerPoint decks headless with python-pptx" names the domain and one concrete action (build decks) plus the concrete tool (python-pptx), but lists no other specific actions like charts, templates, or table binding, fitting the 'domain and 1-2 concrete actions' anchor rather than the multi-action level 4.

3 / 5

Completeness

The description gives a clear 'what' (build decks headless with python-pptx) but contains no 'Use when...' trigger clause or equivalent explicit 'when' guidance, which the guidelines cap at 3; with only an implied trigger it sits at the 'clear what, missing when' boundary, here scored 2 as the when is entirely absent rather than weakly implied.

2 / 5

Trigger Term Quality

"PowerPoint decks" and "python-pptx" are relevant keywords, but natural user phrases like 'presentations', '.pptx', 'slides', or 'pitch decks' are absent, leaving common variations missing per the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The headless python-pptx framing carves a clear niche distinct from a live PowerPoint skill, with only minor overlap risk against a broader presentation skill, matching the 'mostly distinct; minor overlap risk' anchor rather than the more generic level 3.

4 / 5

Total

12

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.