CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-spine

Write, rewrite, or build a paper or report (journal, conference, report, review, competition) end to end, then output LaTeX/PDF/Word. The main PaperSpine entry point that orchestrates every step.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./src/skill/SKILL.md

The canonical home for this skill is paper-spine in WUBING2023/PaperSpine

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 a well-structured orchestrator with an explicit, heavily gated 12-stage workflow and concrete executable commands, scoring top marks on workflow clarity. Its weaknesses are redundancy (pandoc/Word and Chinese-report recipes repeated) and references to a scripts/ directory not present in the bundle.

Suggestions

Consolidate the repeated pandoc/Word-guard recipes and the Chinese completion-report rule into a single reference (e.g., references/latex.md) and point to it instead of restating it in Stage 8, Stage 12, and the User-Facing Language section.

Either include the referenced `scripts/*.py` gate/guard files in the bundle or note explicitly that they are installed elsewhere, so the copy-paste commands are verifiably executable.

Move the full Writing Rationale Matrix schema and the config-field table into their respective reference playbooks, keeping SKILL.md an overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient with dense routing tables and concrete gate commands, but the pandoc/Word-guard recipe and the Chinese completion-report rule are each repeated nearly verbatim two or three times across Stage 8, Stage 12, and the User-Facing Language section, which could be tightened into a single reference.

3 / 5

Actionability

Guidance is concrete and largely copy-paste ready (exact `progress_check.py --gate` commands, full pandoc invocations with flags, file-path expectations), but several referenced gate scripts live in a `scripts/` directory that is not present in the bundle, leaving minor gaps.

4 / 5

Workflow Clarity

A clear 12-stage sequence is given with a gate after each stage, an anti-skip rule, a resume-first rule, a loop rule, and a final hard gate with multiple checkpoints and explicit error-recovery routing — matching the anchor for explicit validation steps with feedback loops.

5 / 5

Progressive Disclosure

The overview routes to one-level-deep `references/*.md` playbooks via clear routing tables and all referenced reference files exist, but the body inlines material that could live in references (full Writing Rationale Matrix schema, the config field table, repeated pandoc recipes) and references a `scripts/` directory absent from the bundle.

4 / 5

Total

16

/

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.

The description states a clear, concrete capability with strong venue and output-format specificity, but it omits an explicit 'Use when...' trigger clause and leans on internal 'entry point' framing. Trigger-term coverage is good but lacks common synonyms like 'manuscript' or 'draft'.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when the user asks to write, rewrite, or draft a journal/conference/report/review paper and produce LaTeX, PDF, or Word output').

Add common synonyms such as 'manuscript', 'draft', and 'thesis' to broaden trigger-term coverage.

Drop or de-emphasize the internal 'The main PaperSpine entry point that orchestrates every step' framing in favor of user-facing trigger language.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Write, rewrite, or build', 'output LaTeX/PDF/Word') and enumerated venue domains, but the closing 'orchestrates every step' sentence is abstract orchestration framing rather than a concrete capability, leaving minor gaps.

4 / 5

Completeness

The 'what' is clearly stated (write/rewrite/build a paper end to end, then output formats), but there is no explicit 'Use when...' trigger clause; the second sentence is internal 'entry point' framing rather than user-facing trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

Natural user terms like 'Write, rewrite', 'paper or report', 'LaTeX/PDF/Word', and the venue types are present, but common synonyms such as 'manuscript', 'draft', or 'thesis' are missing.

4 / 5

Distinctiveness Conflict Risk

The academic paper/report writing pipeline with LaTeX/PDF/Word output and venue enumeration carves a distinct niche, with only minor overlap risk against general writing skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 30 missing

Warning

Total

15

/

16

Passed

Repository
WUBING2023/PaperSpine
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.