encori-api

Access ENCORI (StarBase) database for miRNA-target, RNA-RNA, and other regulatory data. Invoke when user asks to search ENCORI or retrieve regulatory interactions.

Quality

60%

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 ./scientific-skills/Evidence Insight/encori-api/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.

The ENCORI-specific content (capabilities list and eight executable endpoint examples) is strong and actionable, but it is buried under extensive generic boilerplate and duplicated validation sections that hurt token efficiency. Workflow guidance is present but generic and redundant rather than concrete to the ENCORI task.

Suggestions

Delete the generic boilerplate sections (When to Use, Key Features, Implementation Details, Output Contract, Validation and Safety Rules, Failure Handling, Deterministic Output Rules, Completion Checklist) that restate process guidance Claude already knows; keep only the ENCORI-specific Usage and Examples.

Consolidate the duplicated validation sections ('Validation Shortcut' and 'Quick Validation') into one concrete check, and replace the --help-only checks with a real example that validates an actual API response.

Standardize the script path across all examples (use 'scripts/encori_client.py' consistently) so commands are copy-paste correct from the skill directory.

Dimension	Reasoning	Score
Conciseness	Roughly half the body is generic boilerplate Claude already knows ('validate the request, choose the packaged workflow, and produce a bounded deliverable', 'keep results reproducible') plus duplicated validation sections ('Validation Shortcut' and 'Quick Validation' both run --help), making it noticeably verbose with several padded sections despite the useful ENCORI-specific parts.	2 / 5
Actionability	The eight endpoint examples are concrete, copy-paste-ready commands with real arguments covering each module, but executable guidance has a minor gap: example paths are inconsistent ('scripts/encori_client.py' vs '.trae/skills/encori-api/scripts/encori_client.py') and reference a hardcoded path that may not match the install location.	4 / 5
Workflow Clarity	Sequenced workflows appear in multiple places ('Example run plan', 'Recommended Workflow', 'Completion Checklist') but they are generic and redundant, and the validation checkpoints are superficial (mostly --help syntax checks) rather than concrete validation of ENCORI query results.	3 / 5
Progressive Disclosure	The body is well-sectioned with clear headers and references its two real bundle scripts (encori_client.py, validate_skill.py) one level deep under scripts/, with no nested reference chains; the main gap is inlining all endpoint detail in one long file and the inconsistent script paths.	4 / 5
	Total	13 / 20 Passed

Description

66%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 third-person, answers both what and when, and is highly distinctive thanks to the named ENCORI/StarBase database. It is held back by a single generic action verb and a trigger clause that omits the StarBase synonym and specific interaction-type keywords.

Suggestions

Replace the single 'Access' verb with several concrete actions (e.g., 'Query miRNA-target, RNA-RNA, RBP-target, and ceRNA interactions from ENCORI/StarBase').

Add 'StarBase' and the specific data types (miRNA-target, RNA-RNA, ceRNA) to the trigger clause so users using those terms activate the skill.

Drop the vague 'other regulatory data' catch-all in favor of naming the actual endpoint categories.

Dimension	Reasoning	Score
Specificity	Names the domain (ENCORI/StarBase database) and concrete data types (miRNA-target, RNA-RNA, regulatory data), but the action is a single verb ('Access ... database for') rather than multiple distinct actions, and 'other regulatory data' is a vague catch-all.	3 / 5
Completeness	Clearly answers both 'what' (access ENCORI for miRNA-target, RNA-RNA, regulatory data) and 'when' ('Invoke when user asks to search ENCORI or retrieve regulatory interactions'), but the 'when' clause is somewhat narrow with only two trigger conditions and could be more comprehensive.	4 / 5
Trigger Term Quality	Includes relevant natural terms ('search ENCORI', 'retrieve regulatory interactions') but misses common synonyms a user would say, notably 'StarBase' (named in the 'what' but absent from the trigger) and the specific interaction types miRNA-target/RNA-RNA as trigger phrases.	3 / 5
Distinctiveness Conflict Risk	Targets a specific named database (ENCORI/StarBase) with distinct trigger terms, giving it a clear niche and minimal conflict risk with other skills.	5 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/encori-api/SKILL.md
Commit: 63c61d3

Reviewed: 5 hours 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.