CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

73%

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 ./scientific-skills/Evidence Insight/encori-api/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 endpoint documentation is genuinely strong — eight concrete, copy-paste-style commands covering every subcommand — but it is embedded in a large amount of auto-generated template boilerplate that dilutes it, and several path/reference errors (wrong script path prefix, nonexistent CONFIG block, bogus cd directory) break copy-paste executability.

Suggestions

Fix the executable paths: replace the '.trae/skills/encori-api/scripts/encori_client.py' prefix in all examples with the actual bundle-relative 'scripts/encori_client.py', and replace the 'cd "20260316/scientific-skills/Evidence Insight/encori-api"' line with the real skill directory.

Delete or collapse the generic template sections (When to Use, Key Features, Implementation Details, Output Contract, Deterministic Output Rules, Completion Checklist, Recommended Workflow) into a few skill-specific lines, and remove the 'Edit the in-file CONFIG block' instruction since the script is argparse-based with no CONFIG block.

Merge the four overlapping validation sections (Validation Shortcut, Quick Validation, Example run plan validation step, Recommended Workflow validation step) into one concrete validation step tied to an actual command.

DimensionReasoningScore

Conciseness

Roughly half the body is generic template filler that adds no skill-specific information: "Use this skill when the request matches its documented task boundary", "Structured execution path designed to keep outputs consistent and reviewable", "Keep output field names stable and do not rename documented keys across examples", plus four overlapping workflow/validation sections (Example run plan, Recommended Workflow, Quick Validation, Validation Shortcut). This matches anchor 2's 'several unnecessary explanations or padded sections'; it is not 3 because the padding is extensive and systematic rather than occasional.

2 / 5

Actionability

The 8 endpoint examples are concrete, fully-specified commands (e.g. "encori_client.py miRNATarget --target PDCD4 --cellType HeLa"), but executability is undermined by key-detail errors: examples 1-8 use a path prefix (".trae/skills/encori-api/scripts/encori_client.py") that does not exist in the bundle, the Example Usage section cds to a bogus directory ("20260316/scientific-skills/Evidence Insight/encori-api"), the instruction "Edit the in-file CONFIG block" references a block that does not exist in the argparse-based script, and "See ## Usage above for related details" is a dangling cross-reference. This lands between anchors 3 and 4 — concrete guidance with genuine missing key details — and closer to 3 given the broken paths.

3 / 5

Workflow Clarity

The sequence is present with explicit checkpoints: "Recommended Workflow" (validate request → select execution path → produce output → final validation pass), concrete validation commands ("python -m py_compile scripts/encori_client.py", "python scripts/encori_client.py --help", "python scripts/validate_skill.py --help"), and a Failure Handling section with recovery steps. Not anchor 5 because the workflow steps themselves are generic boilerplate ("Select the documented execution path and prefer the simplest supported command") rather than a skill-specific ordered procedure for choosing an endpoint and arguments, and the redundancy of four overlapping workflow sections dilutes the actual sequence.

4 / 5

Progressive Disclosure

Scored against the actual bundle: the two referenced scripts ("scripts/encori_client.py", "scripts/validate_skill.py") both exist, references are one level deep, and the body is sectioned with clear headers. Not anchor 5 because the ~200-line monolithic body inlines substantial boilerplate (deterministic output rules, completion checklist, generic contracts) that should be trimmed or split, the inconsistent dual path convention ("scripts/..." vs ".trae/skills/...") obscures navigation to the bundle files, and "See ## Usage above" is an unclear in-page pointer.

4 / 5

Total

13

/

20

Passed

Description

82%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 well-formed description with an explicit 'Invoke when...' trigger clause, a named niche database, and concrete natural keywords. Its main limitation is thin action coverage — it says the data types accessible but enumerates only 'access'/'retrieve' as actions rather than several specific operations.

DimensionReasoningScore

Specificity

The description names the domain ("ENCORI (StarBase) database") and specific data types ("miRNA-target, RNA-RNA, and other regulatory data"), but the only actions stated are "Access" and "retrieve" — 1-2 concrete actions, not the several distinct actions of anchor 4. It is not anchor 2 because the data-type enumeration makes the capability scope concrete rather than generic.

3 / 5

Completeness

Clearly answers both: what — "Access ENCORI (StarBase) database for miRNA-target, RNA-RNA, and other regulatory data"; when — "Invoke when user asks to search ENCORI or retrieve regulatory interactions", an explicit trigger clause with concrete phrases. It matches anchor 5 exactly; anchor 4 would require a weaker or less explicit 'when' clause.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "ENCORI", "StarBase", "miRNA-target", "RNA-RNA", "search ENCORI", "retrieve regulatory interactions" — terms a user of this database would actually say. Not anchor 5 because common synonyms and sub-feature terms a user might naturally use (e.g. "RNA interactomes", "ceRNA", "RBP", "CLIP-seq data") are absent.

4 / 5

Distinctiveness Conflict Risk

"ENCORI (StarBase)" names a specific database, giving the skill a clear niche with distinct triggers and minimal overlap risk with generic data-retrieval skills. It is not anchor 4 because no closely related skill would plausibly fire on these triggers — the database name itself disambiguates.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.