CtrlK
BlogDocsLog inGet started
Tessl Logo

nanoresearch-writing

Draft a LaTeX research paper from all previous stage outputs

54

Quality

61%

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 ./skills/nanoresearch-writing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and well-organized for a simple skill, with clear sequencing and named tooling. Its main weakness is actionability — it describes steps rather than giving executable commands — and a lack of explicit validation checkpoints in the compile/assembly workflow.

Suggestions

Add concrete, executable invocations for the named tools (e.g., example generate_latex / compile_pdf / generate_figure calls with expected arguments and outputs) so steps are copy-paste ready.

Insert an explicit validation checkpoint after compiling (e.g., 'If compile_pdf reports errors, fix the LaTeX source and re-run compile_pdf until it succeeds') to add a feedback loop to the batch workflow.

Specify how to detect or handle upstream-output problems (missing files, failed experiments) before drafting, turning step 1's parse step into a verifiable precondition.

DimensionReasoningScore

Conciseness

The body is lean and well-structured, naming only tools, inputs, a numbered process, and outputs without explaining concepts Claude already knows or padding with unnecessary context; every section earns its place.

3 / 3

Actionability

It names specific tools (generate_latex, compile_pdf, generate_figure) and concrete file paths, but provides no executable code or copy-paste-ready commands — the 13 process steps are procedural descriptions rather than directly runnable instructions, matching 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

The 13 steps are clearly sequenced with named inputs and a final 'verify the output' step, but for a batch assembly/compile operation there is no explicit validate→fix→retry feedback loop; per the guidelines, missing validation checkpoints for batch operations caps workflow_clarity at 2.

2 / 3

Progressive Disclosure

The skill is under 50 lines, single-purpose, and well-organized into clearly labeled sections (Purpose, Tools Required, Input, Process, Output) with no bundle files present; per the simple-skills scoring note, this warrants a 3 without external file references.

3 / 3

Total

10

/

12

Passed

Description

50%

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 accurate and names a concrete domain and action but is a single short clause with no explicit trigger guidance or 'when to use' context. It is clear but minimal, scoring at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when writing up a research paper from ideation, planning, and experiment outputs').

Include natural trigger-term variations users would say, such as 'paper', 'manuscript', 'write-up', or 'drafting the paper'.

Optionally enumerate the concrete sub-actions (e.g., 'assemble LaTeX sections, generate figures and tables, compile a bibliography and PDF') to lift specificity from a single action to multiple concrete actions.

DimensionReasoningScore

Specificity

The description names a concrete action ('Draft a LaTeX research paper') and the input domain ('previous stage outputs'), but lists only a single action rather than multiple specific concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It states what the skill does ('Draft a LaTeX research paper from all previous stage outputs') but provides no explicit 'when should Claude use it' trigger; per the guidelines, a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

'LaTeX research paper' is a relevant natural term, but 'previous stage outputs' is technical jargon unlikely to be user-spoken, and there are no common variations (paper, manuscript, write-up) or a 'Use when...' clause, matching 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

'Draft a LaTeX research paper' is a somewhat distinct niche and the pipeline dependency ('from all previous stage outputs') reduces conflict risk, but the absence of explicit distinguishing triggers leaves it only somewhat specific rather than a clearly demarcated niche.

2 / 3

Total

8

/

12

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
OpenRaiser/NanoResearch
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.