Tessl • The management layer for AI agent skills

SkillPublic

catalysis-prior-art-and-benchmarking

Use this skill when a catalysis workflow needs literature-grounded benchmark papers, prior-art mapping, representative method conventions, or evidence-backed comparisons.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/catalysis-prior-art-and-benchmarking/SKILL.md

Quality

Content

78%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 lean, well-organized instructional body that gives an executable depth-selection table, sensible method defaults, and a clear output contract. The main improvement opportunities are adding a concrete example invocation/query for run_literature_research and a brief verification cue for benchmark claims.

Suggestions

Add one concrete example of a framed literature query with its matching run_literature_research call (e.g., depth and query text) to make the workflow copy-paste executable.

Include a short verification cue in the workflow, such as cross-checking a reported benchmark value against a second source before using it to justify method defaults.

Merge or trim the Overview, which duplicates the frontmatter description, to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is efficient and free of concept explanations Claude already knows, with each section earning its place; only minor tightening is possible (e.g., the Overview largely restates the description, and "A good literature result for catalysis should identify..." could be more direct).	4 / 5
Actionability	The Quick Start gives an executable decision table mapping need to concrete tool calls ("call `run_literature_research` with `depth=quick`" through `depth=deep_report`), and the Output Contract specifies deliverables; the gap is that no example query or parameter invocation is shown, leaving the exact call shape to inference.	4 / 5
Workflow Clarity	The three workflow steps are clearly sequenced (frame question → align with stage → extract conventions) and the Method-critical defaults plus Output Contract act as completion and correctness checks, so the sequence and most checkpoints are present; only minor validation guidance (e.g., how to verify a benchmark claim is representative) is missing.	4 / 5
Progressive Disclosure	This is a short (~40-line), single-purpose skill with no bundle files; per the rubric's simple-skill guidance, well-organized sections (Overview, Quick Start, Suggested tools, Workflow, defaults, Output Contract, References) score full marks without external file references, and its References section points to sibling skills rather than hiding needed detail.	5 / 5
	Total	17 / 20 Passed

Description

75%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 solid, domain-anchored description with an explicit use-when clause and several specific deliverables. Its main weakness is that it never states the skill's action in verb form — the what is implied by the objects of the "needs" clause — and it lacks synonym-level trigger coverage.

Suggestions

Lead with what the skill does in third-person verb form (e.g., "Maps prior art and compiles literature-grounded benchmarks for catalysis workflows") before the use-when clause.

Add natural trigger synonyms such as "citations", "representative papers", or "reference/benchmark systems" to broaden keyword coverage.

Sharpen the trigger with user-facing phrasing like "when the user asks for supporting literature, benchmark comparisons, or prior-art for a catalyst system".

Dimension	Reasoning	Score
Specificity	The description names several specific deliverables — "literature-grounded benchmark papers, prior-art mapping, representative method conventions, or evidence-backed comparisons" — going beyond 1-2 actions, but they are outcome categories rather than concrete actions with verbs, so comprehensiveness falls just short of a 5.	4 / 5
Completeness	It has an explicit "Use this skill when..." trigger clause and embeds the what (benchmark papers, prior-art mapping, method conventions) inside it, but never states what the skill actually does (e.g., "finds and synthesizes..."), so the what is present but implicit rather than explicit.	4 / 5
Trigger Term Quality	Natural terms like "catalysis", "benchmark papers", "prior-art", and "literature" cover what a catalysis researcher would plausibly say, but common variations such as "citations", "papers", or "reference systems" are missing.	4 / 5
Distinctiveness Conflict Risk	The catalysis domain with benchmarking/prior-art framing carves a mostly distinct niche with concrete triggers, though it retains minor overlap risk with general literature-search or research skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/CatMaster
Path: skills/catalysis-prior-art-and-benchmarking/SKILL.md
Revision: c87fc76

Reviewed: 9 hours ago

Discovery Implementation Validation

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.

catalysis-prior-art-and-benchmarking

Table of Contents

Is this your skill?