CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-abstract-author

Write the abstract after the paper body has been revised, using the final claims and evidence.

61

Quality

73%

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 ./src/opensquilla/skills/bundled/paper-abstract-author/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tight, well-structured instruction spec with a concrete output template and clear hard rules, and as a simple single-purpose skill it needs no external references or validation loops. Its only gap is the absence of a worked example abstract to anchor tone and length.

DimensionReasoningScore

Conciseness

The body is lean throughout: compact input list, a minimal LaTeX output-contract code block, and terse imperative 'Hard rules' with no padding or explanation of what an abstract is. Every token earns its place and it assumes Claude's competence, matching the level-5 anchor; it is not below 5 since there is no over-explanation to trim.

5 / 5

Actionability

Concrete guidance is present: an exact LaTeX fragment template, a 250-350 word target, and specific hard rules ('Cover problem, approach, evidence, main result, and significance'). It is mostly executable with a minor gap (no example abstract to model tone/length), fitting level 4; not level 5 because no worked example is provided, and not level 3 because the template and rules are directly usable.

4 / 5

Workflow Clarity

This is a single-purpose, non-destructive instruction skill (no batch/destructive operation, so the validation cap does not apply) and the simple-skill exception holds: inputs, output contract, and hard rules make the single action unambiguous. It meets the level-5 'single action is unambiguous' condition; not below 5 because there are no missing checkpoints for a text-generation task.

5 / 5

Progressive Disclosure

The skill is under 50 lines, requires no external references, and is organized into clear sections (Inputs, Output contract, Hard rules); no bundle files exist or are needed. Per the guideline, such a simple skill can score 5 with just well-organized sections, matching the level-5 anchor; there is no structure problem to drop it.

5 / 5

Total

19

/

20

Passed

Description

53%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 clearly states what the skill does but omits an explicit 'Use when...' trigger clause and lacks the breadth of concrete actions and natural synonyms that would push it higher. It is specific to its niche but only moderately complete as a routing signal.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the paper body is finalized and the abstract needs to be drafted or rewritten from the final claims and evidence.'

Broaden natural trigger terms to include synonyms users actually say, such as 'abstract', 'paper summary', and 'draft the abstract'.

Mention the LaTeX output format in the description so the skill's concrete deliverable is visible at routing time.

DimensionReasoningScore

Specificity

Names the domain ('abstract') and concrete conditions ('after the paper body has been revised', 'using the final claims and evidence') but stops at 1-2 actions without listing the fuller coverage (LaTeX output, structure). It is not level 4 because it does not list several specific actions; it is above level 2 because the actions named are concrete, not generic.

3 / 5

Completeness

It has a clear 'what' ('Write the abstract') but the 'when' is only weakly implied by the temporal condition ('after the paper body has been revised') with no explicit 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger clause caps completeness at 3. Not level 4 because 'when' is not explicit, not level 2 because the 'what' is clear.

3 / 5

Trigger Term Quality

The relevant keywords present are 'abstract', 'paper body', and 'claims and evidence', but natural variations users might say ('summary', 'draft the abstract', 'paper summary') are missing. It fits the 'some relevant keywords but missing common variations or synonyms' anchor and not level 4, which requires good coverage with only a few terms missing.

3 / 5

Distinctiveness Conflict Risk

The niche (writing a paper abstract from the revised body) is specific and unlikely to trigger for unrelated skills, with only minor overlap risk against other academic-paper-writing skills. It is mostly distinct with minor overlap risk, fitting level 4; not level 5 because it could still overlap with sibling paper-authoring skills.

4 / 5

Total

13

/

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.

Validation15 / 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
TokenRhythm/opensquilla
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.