brenda-database

Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/brenda-database/SKILL.md

Quality

Content

53%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 highly actionable, well-structured skill whose main weaknesses are substantial duplication across the Core Capabilities, Helper Scripts, and Common Workflows sections and a missing validation feedback loop in its workflows, plus one code example referencing a nonexistent function.

Suggestions

Collapse the nine "Core Capabilities" snippets and six "Common Workflows" into a small set of distinct end-to-end examples; drop the per-function "Helper Scripts" inventory in favor of docstrings or the API reference.

Add explicit validation checkpoints to workflows (e.g., verify parsed Km values are numeric and non-empty before computing best-kinetic-performer, retry or fall back on Fault/TransportError) to lift workflow clarity.

Remove or fix the extract_substrate_products example (the function does not exist in scripts/brenda_queries.py) and move the inline BRENDA response-format section into references/api_reference.md.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is noticeably verbose: six "Common Workflows" largely re-run calls already shown in the nine "Core Capabilities" sections, "Helper Scripts" re-lists every function already demonstrated, rate-limit guidance appears in three places, and "Data Extraction Patterns" teaches generic regex parsing Claude already knows.	2 / 5
Actionability	Code examples are concrete and mostly executable (all documented functions were verified present except one), with real auth setup and a try/except error-handling section; the gap is that the "Process Reaction Data" example imports extract_substrate_products, which does not exist in any bundled script.	4 / 5
Workflow Clarity	The six workflows have clear sequences and some implicit guards ("if enzymes:", "if pathway:"), but none include explicit validate-then-proceed checkpoints or fix-retry loops; per the rubric's cap for database operations without feedback loops, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The bundle is well used: references/api_reference.md (499 lines, verified real) is clearly signaled one level deep and correctly carries the bulk SOAP API detail, though the body still inlines ~40 lines of response-format documentation and a full function inventory that duplicate the reference file.	4 / 5
	Total	13 / 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 strong, specific description with concrete named actions and a clearly distinct niche, weakened only by the absence of an explicit "Use when..." trigger clause and some capability coverage gaps relative to the body content.

Suggestions

Append an explicit trigger clause, e.g. "Use when querying enzyme kinetics (Km, kcat), EC-number reaction data, or cross-organism enzyme comparisons from BRENDA."

Mention additional documented capabilities such as inhibition/activation data and enzymatic pathway construction to close the coverage gap with the body.

Add common synonyms like "enzyme kinetics", "substrate specificity", and "turnover number" to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions with named parameters ("Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information"), but omits body capabilities like inhibition data, pathway construction, and visualization, leaving minor coverage gaps.	4 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause; "for biochemical research and metabolic pathway analysis" only weakly implies when, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes natural user phrasings like "BRENDA enzyme database", "kinetic parameters (Km, kcat)", and "metabolic pathway analysis", but misses common variations such as "enzyme kinetics lookup" or "substrate specificity".	4 / 5
Distinctiveness Conflict Risk	Names a specific database (BRENDA) and protocol (SOAP API), giving it a clear niche with distinct triggers and minimal risk of triggering for the wrong skill.	5 / 5
	Total	16 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (727 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/brenda-database/SKILL.md
Commit: 4082a2e

Reviewed: 1 day ago

Table of Contents

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.