CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

achemso-latex-manuscript

Write ACS-style manuscript sections against the local achemso LaTeX template, using deterministic template edits and preserving BibTeX structure.

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 ./writing_skills/achemso-latex-manuscript/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A well-structured, lean instruction-only skill with concrete tool and artifact guidance, but its workflow lacks any validation or feedback checkpoint for LaTeX editing, and its external references cannot be verified against the bundle. Adding a compile/verify step and confirming the _references paths resolve would lift both dimensions.

Suggestions

Add an explicit validation checkpoint to the workflow, e.g. 'After editing, compile or lint the working .tex (or re-read the fragment against the template) and fix errors before recording it in latex_artifact_refs.'

Verify the ../_references/style-and-revision-checks.md and ../_references/submission-and-editorial-readiness.md paths resolve from the skill's mount location, or inline the essential checks if they are small.

Trim the duplicated read-only-asset statements (workflow step 2 vs. the Template discipline bullet) and add a minimal example of an apply_aider_edits SEARCH/REPLACE block for a section insert.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no LaTeX or BibTeX concept explanations — but has minor repetition: workflow step 2 ('do not try to edit the read-only mounted asset directly') restates the Template discipline bullet 'The mounted asset is reference-only; any edited TeX should live under the writable run workspace', and workflow step 1 re-states the Quick Start read instruction. This matches anchor 4 (efficient, minor trims possible) rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

For an instruction-only skill the guidance is mostly executable: named tools ('apply_aider_edits' for SEARCH/REPLACE edits), concrete artifact paths ('assets/achemso-demo.tex', 'assets/achemso-demo.bib'), a defined output contract ('section_tex' as primary output, record paths in 'latex_artifact_refs'). Minor gaps remain — no example SEARCH/REPLACE edit and no skeleton of a section fragment — so it sits at anchor 4 rather than anchor 5's copy-paste-ready coverage of common cases.

4 / 5

Workflow Clarity

Steps 1-6 are clearly sequenced, but this is document/TeX manipulation and there is no validation checkpoint — no compile check, no re-read/review step; the only error-handling rule ('If the template and the evidence disagree, preserve the evidence and adapt the prose') resolves conflicts rather than validating output. This matches anchor 3 (steps listed but validation gaps), not anchor 4 which requires most checkpoints present.

3 / 5

Progressive Disclosure

The body is a well-organized overview with clearly signaled, one-level-deep references, and the two bundled assets are real files. However, the two 'Read ../_references/...' links point outside the skill bundle and do not resolve within the provided bundle structure (only assets/ exists), leaving navigation partially unverifiable and contributing some inline rule detail (Template discipline / Editing rules) that could live in those references — matching anchor 4 rather than anchor 5.

4 / 5

Total

15

/

20

Passed

Description

70%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 specific, distinctive description with concrete named actions, but it omits any explicit 'Use when...' trigger guidance, which both caps completeness and forces trigger-term inference from domain vocabulary alone. Adding one sentence of trigger conditions (e.g., 'Use when the writing lane is producing an ACS/achemso LaTeX draft') would resolve the gap.

Suggestions

Add an explicit trigger clause, e.g. 'Use when drafting or revising sections of an ACS journal manuscript based on the achemso template.'

Include a few more natural user synonyms such as 'journal', 'paper', 'submission', or '.tex' alongside 'ACS-style' and 'manuscript'.

Optionally name the primary output (section-level .tex fragments) so the 'what' covers what the skill produces, not just what it edits.

DimensionReasoningScore

Specificity

The description lists several concrete actions in a named domain — 'Write ACS-style manuscript sections', 'deterministic template edits', 'preserving BibTeX structure' — with only minor coverage gaps (e.g., no mention of the output/assembly step). It exceeds anchor 3 (only 1-2 concrete actions) but falls short of anchor 5's comprehensive coverage.

4 / 5

Completeness

The 'what' is clear and specific (writing ACS-style manuscript sections with deterministic template edits and BibTeX preservation), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines cap at 3. The when-conditions must be inferred entirely from the domain terms.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'ACS-style', 'achemso', 'LaTeX', 'manuscript', 'BibTeX', 'template'. Common variations like 'paper', 'journal', 'submission', or the '.tex' extension are missing, keeping it below anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The combination of 'achemso', 'ACS-style', and 'BibTeX structure' defines a clear niche with distinct trigger terms and minimal conflict risk; a user or router naming any of these terms would almost certainly intend this skill over a generic writing or LaTeX skill.

5 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/CatMaster

Path

writing_skills/achemso-latex-manuscript/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.