CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paper-spine-deliver

Render, inspect and package an existing scientific paper with requested Word, PDF, LaTeX or other editable sources, bibliography and figures.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./paperspine5/core/01_PaperSpine4/src/skill-editions/paper-spine-deliver/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 exceptionally lean and encodes a sensible end-to-end workflow with explicit validation and a fix-rebuild loop, but it provides no executable detail (commands, tools, procedures) and its reference links point outside the skill directory where the target files are absent. It reads as an orchestration-level overview that depends on unverifiable external references for its substance.

Suggestions

Add concrete, executable guidance for the core operations — e.g. the actual render commands, an inspection procedure for output pages, and how to verify references/figures — instead of purely high-level directives.

Move reference files (manuscript-format.md, publication-surface.md, EDITION-MANAGEMENT.md) into the skill's own references/ directory and use relative links that resolve within the bundle, or inline the essential details.

Present the workflow as an explicit numbered sequence with validation checkpoints, and clarify the jargon in the final paragraph ("the orchestrator's existing check") which is opaque without external context.

DimensionReasoningScore

Conciseness

The body is ~130 words of purely directive prose with no padding and no explanation of concepts Claude already knows; every sentence instructs an action or states a constraint. Matches the "lean and efficient; every token earns its place" anchor; not 4 because there are no instances of over-explanation to trim.

5 / 5

Actionability

Directives like "Generate the requested formats from coherent sources" and "inspect the real output pages" state what to do but give no commands, tools, or procedures for rendering or inspection. Some guidance is concrete ("check its contents and that its sources and assets open after extraction", "keep private inputs outside that package"), so it rises above the high-level-hints level, but key execution details are missing or delegated to references.

3 / 5

Workflow Clarity

A coherent sequence runs through the prose (resolve inputs → generate formats → inspect real output pages → fix and rebuild affected formats → deliver links → verify ZIP contents → report gaps), with explicit validation points and a fix-rebuild feedback loop appropriate for document manipulation. Not 5 because steps are not signposted (no numbered sequence or commands) and validation after rebuild is implicit; not 3 because checkpoints are explicit rather than missing.

4 / 5

Progressive Disclosure

References are clearly signaled ("Use [manuscript format](../../skill/references/manuscript-format.md) and [publication surfaces](../../skill/references/publication-surface.md)"), but they point outside the skill's own directory (two levels up, plus ../EDITION-MANAGEMENT.md) and no referenced files exist in the bundle, so navigation cannot be verified. The body also lacks any section headers, leaving organization minimal.

3 / 5

Total

15

/

20

Passed

Description

66%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.

A concise, specific description with good domain keywords, but it omits any explicit "Use when..." trigger guidance, which caps its completeness and weakens its trigger function. Adding a trigger clause mentioning manuscripts, format conversion requests, and paper delivery would resolve the main weakness.

Suggestions

Add a "Use when..." clause, e.g. "Use when the user asks to convert, render, or package a scientific paper or manuscript into Word, PDF, LaTeX, or other editable sources for delivery or submission."

Include the synonym "manuscript" and common file extensions (.docx, .pdf) as trigger terms, since users in this domain most often say "manuscript" rather than "scientific paper".

Mention the fix/rebuild capability (correcting misplaced figures or broken references and regenerating affected formats) so the capability coverage matches the skill body.

DimensionReasoningScore

Specificity

"Render, inspect and package" lists several concrete actions with enumerated artifacts ("Word, PDF, LaTeX or other editable sources, bibliography and figures"), but the fix/rebuild capability described in the body is not covered, leaving a minor gap. Not 5 because coverage is not comprehensive; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear (render, inspect and package a scientific paper with sources, bibliography and figures), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. The word "requested" only weakly implies a trigger.

3 / 5

Trigger Term Quality

Includes natural terms users would say: "scientific paper", "Word", "PDF", "LaTeX", "bibliography", "figures". Not 5 because common synonyms and extensions are missing — notably "manuscript" (the domain's most natural term, which appears only in the body), ".docx/.pdf", and "submission"; not 3 because keyword coverage is genuinely good.

4 / 5

Distinctiveness Conflict Risk

The "existing scientific paper" packaging niche with bibliography and figure assets is mostly distinct, but "Render... Word, PDF" creates minor overlap risk with generic document-conversion or LaTeX skills. Not 5 because format-rendering language is shared with broader document skills; not 3 because the scientific-paper delivery framing is specific.

4 / 5

Total

15

/

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

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

WUBING2023/PaperSpine

Path

paperspine5/core/01_PaperSpine4/src/skill-editions/paper-spine-deliver/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.