CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paper-tweet-generator

Generates a structured reading tweet from an academic paper (PDF, Word, or Text), highlighting specific product advantages. Use when the user wants to turn a document into a social media post or reading summary.

Quality

74%

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 ./scientific-skills/Other/paper-tweet-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 core Workflow section is well-sequenced with accurate, executable commands that match the real bundle scripts, and reference content is properly split into one-level-deep files. The body is dragged down by extensive templated filler sections and by validation/usage commands that reference `extract_pdf.py --help` and an output format that no script actually produces.

Suggestions

Remove the generic filler sections (Key Features, Implementation Details, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling) and keep only the Workflow, Requirements, Scripts, References, and When Not to Use sections to cut roughly half the body's tokens.

Fix the broken validation paths: `scripts/extract_pdf.py` does not support `--help` and does not produce the claimed "Result file / Validation summary / Assumptions" output, so either drop the Quick Validation section or replace it with a real check such as `python scripts/extract_text.py <sample.pdf> test_output.txt`.

Resolve the script inconsistency: document both `extract_text.py` and `extract_pdf.py` in the Scripts section (or remove `extract_pdf.py`), and add a short example of the final assembled tweet so the output contract is concrete.

DimensionReasoningScore

Conciseness

Roughly half the body is templated padding: "Key Features" merely restates the frontmatter description ("Scope-focused workflow aligned to: Generates a structured reading tweet...") and lists files; "Implementation Details" opens with the dead pointer "See `## Workflow` above for related details" followed by generic filler like "Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable"; and "Required Inputs", "Output Contract", "Validation and Safety Rules", and "Failure Handling" are generic boilerplate that adds no skill-specific value. This matches the anchor for several unnecessary padded sections; it is not a 3 because the padding is extensive rather than occasional, and not a 1 because the core "Workflow" section itself is lean and on-point.

2 / 5

Actionability

The primary path is executable and accurate: "Run: `python scripts/extract_text.py <file_path> extracted_content.txt`" matches the script's real interface, and the documented "Warning: No text extracted" handling matches the script's actual stderr message; glob patterns ("**/*.pdf") and per-section word limits are concrete. Minor gaps: the Example Usage and Quick Validation sections run `python scripts/extract_pdf.py --help`, which the script does not support (it would treat --help as a file path), the "Expected output format" block ("Result file: paper_tweet_generator_result.md / Validation summary: PASS/FAIL") is fabricated by no script, and there is no example of the final assembled tweet. These are peripheral, so it stays at 4 rather than 3, but they prevent a 5.

4 / 5

Workflow Clarity

The three-step workflow (locate/extract → generate sections → final assembly) is clearly sequenced, with explicit error checkpoints in the risky step: "If the extraction fails or returns empty text (check stderr logs), inform the user", "If 'Warning: No text extracted' is logged, the PDF is likely a scanned image", plus a documented fallback. It is not a 5 because steps 2-3 lack validation or feedback loops (no check that all sections were produced or conform to limits) and the Quick Validation path is broken; not a 3 because validation checkpoints are explicit rather than missing or implicit, and this is not a destructive or batch operation so the 3-cap does not apply.

4 / 5

Progressive Disclosure

Good bundle structure: prompts are correctly split into `references/prompt_templates.md` and extraction logic into `scripts/extract_text.py`, both real files, one level deep, and clearly signaled via dedicated "Scripts" and "References" sections. Not a 5 because of organization inconsistencies: two scripts exist but the "Scripts" section documents only one while Example Usage and "Key Features" reference the undocumented `extract_pdf.py`, and the inline generic sections clutter the overview; not a 3 because content is genuinely well-split and easy to navigate rather than inlined or buried.

4 / 5

Total

14

/

20

Passed

Description

78%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 strong: it clearly states what the skill does, for which inputs, and when to use it, with natural trigger phrases. Its main weaknesses are modest action coverage (one primary deliverable rather than several listed capabilities) and missing file-extension/synonym triggers.

DimensionReasoningScore

Specificity

"Generates a structured reading tweet from an academic paper (PDF, Word, or Text), highlighting specific product advantages" names the domain (with input formats) plus one or two concrete actions, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because it does not list several specific actions (e.g., extraction, summarization, formatting as separate capabilities), and not a 2 because the action and domain are concrete rather than minimal or generic.

3 / 5

Completeness

It explicitly answers both what ("Generates a structured reading tweet from an academic paper (PDF, Word, or Text), highlighting specific product advantages") and when ("Use when the user wants to turn a document into a social media post or reading summary") with concrete trigger phrases. This clearly matches the top anchor; a 4 would require a weaker or less explicit 'when' clause, which is not the case here.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "academic paper", "PDF, Word, or Text", "tweet", "social media post", "reading summary" — phrases users would plausibly say. Not a 5 because it omits file extensions (.pdf, .docx, .txt) and common synonyms ("summarize a paper", "article", "post"), and not a 3 because the trigger vocabulary is broad and natural rather than missing common variations.

4 / 5

Distinctiveness Conflict Risk

The academic-paper-to-tweet niche with product-advantage highlighting is mostly distinct with specific triggers. It is not a 5 because "turn a document into a social media post or reading summary" could overlap with generic summarization or social-media-writing skills, and not a 3 because the niche is far more specific than the anchor example "Works with document files".

4 / 5

Total

16

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Other/paper-tweet-generator/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.