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

69%

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 ./backend/cli/skills/databases/brenda-database/SKILL.md

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.

The content is highly actionable with executable code and verified bundle references, but it is verbose and its multi-step workflows lack explicit validation checkpoints for the risky batch/API operations involved. Tightening repeated boilerplate and adding validate-then-proceed steps would raise the two midpoint dimensions.

Suggestions

Add explicit validation/verification checkpoints to the Common Workflows (e.g. check the API returned non-empty results, confirm EC number format before querying, retry-with-backoff on TransportError) to introduce validate->fix->retry feedback loops.

Consolidate the repeated import boilerplate and the nine near-identical call-and-print sections into a single canonical pattern plus a compact capability table, moving per-capability detail into the existing reference/script files.

Move the full helper-script function lists (currently inlined for all three scripts) into references or keep only key functions inline with a pointer to the script, reducing inline bulk while preserving discoverability.

Dimension	Reasoning	Score
Conciseness	The ~710-line body is mostly efficient with genuinely useful code, but repeats import boilerplate and a near-identical call/print pattern across nine capability sections and re-states the description in 'When to Use', so it could be noticeably tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready Python with real function names and signatures, real BRENDA response formats ('organism...#substrate...#kmValue*...'), and references scripts that actually exist, covering the common cases comprehensively.	5 / 5
Workflow Clarity	The six Common Workflows have a clear sequence with concrete code, but they involve batch/network operations against an authenticated API and lack explicit validation checkpoints or validate->fix->retry feedback loops, which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Good structure with clearly signaled one-level-deep references (references/api_reference.md and the three scripts/*.py, all verified to exist), though substantial script/API content (full function lists and code for nine capabilities) is inlined rather than split into separate files.	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.

The description is specific and well-niched with strong concrete actions and distinctiveness, but it lacks an explicit 'Use when...' trigger clause, capping completeness at the midpoint. Adding a clear usage-trigger sentence would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when the user asks for enzyme kinetic parameters like Km or kcat, reaction equations, or organism-specific enzyme data from BRENDA').

Add common synonyms and natural phrasings users might say, such as 'enzyme kinetics', 'enzyme data', or a standalone 'BRENDA' trigger term.

Tighten to fully comprehensive action coverage by adding the remaining capabilities (e.g. inhibition/activation, environmental pH/temperature, pathway construction) that the body documents.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions ('Retrieve kinetic parameters (Km, kcat)', 'reaction equations', 'organism data', 'substrate-specific enzyme information') with only minor coverage gaps, matching the 'several specific actions' anchor just below the fully comprehensive level.	4 / 5
Completeness	Clearly states what the skill does (access BRENDA via SOAP API, retrieve kinetic parameters etc.) but has no explicit 'Use when...' trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage including 'enzyme', 'kinetic parameters', 'Km, kcat', 'reaction equations', 'organism data', 'substrate', and 'metabolic pathway', though a few natural user phrasings and synonyms (e.g. 'enzyme kinetics', a plain 'BRENDA' trigger) are missing.	4 / 5
Distinctiveness Conflict Risk	A clear niche (BRENDA enzyme database via SOAP API) with distinct domain triggers ('Km, kcat', 'enzyme', 'reaction equations') and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (719 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

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/brenda-database/SKILL.md
Commit: 3a6c3a9

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.