CtrlK
BlogDocsLog inGet started
Tessl Logo

tf-target-gene-regulatory-network

Use when analyzing transcription factor (TF) regulatory networks using Dorothea database. Input gene list, identify regulating transcription factors, generate TF-Target network visualization. For: transcription factor enrichment analysis, gene regulatory network research.

65

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 skill body: executable install/usage/test commands, a complete arguments table, mapped error codes, and a clear four-step workflow with escalation to troubleshooting. The main weaknesses are redundancy — two tables listing the same reference files and Methods repeating Workflow content — and references to bundle paths (tests/, database/) that do not exist.

Suggestions

Fix or remove the broken bundle references: "tests/data/" and "database/database-get.R" are cited in the body but neither tests/ nor database/ exists in the skill bundle.

Consolidate the duplicated reference listings — the "When to Read External Files" table and the closing "Reference Files" table list the same four files; keep one.

Merge the "Methods" section into "Workflow" (or trim it) — Dorothea confidence levels, local-database search paths, and layout options are each stated twice, and the canonical visualization tokens are repeated in both "Entry Point" and "Arguments".

DimensionReasoningScore

Conciseness

Mostly efficient, but there is real duplication: the "When to Read External Files" table and the closing "Reference Files" table list the same four files; "Methods" restates Workflow content (Dorothea confidence levels in Step 1 and again in Methods; local-database search paths in Step 1 and again under "Local Database Feature"); and the canonical tokens "fr, curve, diamond, triangle, square" appear in both "Entry Point" and "Arguments". This fits the 'could be tightened' anchor — not 4 because the duplication exceeds minor instances, not 2 because there is no concept-explaining padding and most content (args, errors, examples) earns its place.

3 / 5

Actionability

Everything needed to execute is concrete and copy-paste ready: install commands, verification via "Rscript scripts/main.R --help", five complete runnable example invocations covering basic/file-input/mouse/custom-styling/local-database cases, a full arguments table with defaults and required-flag notes, error-code tables with solutions, exit status codes, and a test procedure with expected output files. Matches the fully-executable top anchor; examples cover the common cases.

5 / 5

Workflow Clarity

A clear four-step sequence (Load Database → Identify Regulating TFs → Generate Network Data → Visualize Network) with checkpoints in the surrounding sections: an error table mapping codes to solutions, "IF error persists, READ: references/troubleshooting.md" as a feedback loop, and test verification ("verify tests/output_human/plot/TF_Network_Plot.pdf ... exist and are non-empty"). Not 5 because the workflow steps themselves carry no inline validation checkpoints — error handling and verification live in separate sections rather than being integrated into the sequence; not 3 because checkpoints and recovery paths are clearly present.

4 / 5

Progressive Disclosure

Good structure scored against the actual bundle: all four referenced files (references/algorithm.md, troubleshooting.md, cli-guide.md, visualization-parameters.md) exist and are one level deep (no nested references found), and navigation is clearly signaled by two tables and inline links. Not 5 because the body references paths absent from the bundle — "tests/data/" in the external-files table and "database/database-get.R" in Installation — creating broken navigation, and the reference-file listing is duplicated in two tables.

4 / 5

Total

16

/

20

Passed

Description

83%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 description that explicitly states both what the skill does and when to use it, with concrete actions and a distinct Dorothea-based niche. Weaknesses are minor: a few natural trigger synonyms are missing and the enrichment-analysis phrasing creates slight overlap risk with generic enrichment skills. The description uses third person and avoids fluff.

DimensionReasoningScore

Specificity

Concrete actions are stated: "identify regulating transcription factors" and "generate TF-Target network visualization", plus the domain via "Dorothea database". This matches the anchor listing several specific actions with minor gaps — not 5 because coverage is incomplete (no mention of the exportable network table, Excel/PDF outputs, or CLI execution that the skill actually provides; "Input gene list" is a precondition, not an action), and not 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what — "Input gene list, identify regulating transcription factors, generate TF-Target network visualization"; when — "Use when analyzing transcription factor (TF) regulatory networks using Dorothea database" plus "For: transcription factor enrichment analysis, gene regulatory network research". A clear 'Use when' clause with concrete trigger phrases is present, matching the top anchor; a score of 4 would require the 'when' to be weaker or less explicit than it is.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "transcription factor (TF)" (full form plus abbreviation), "gene regulatory network", "gene list", "Dorothea", "transcription factor enrichment analysis" — phrasings a genomics user would naturally say. Not 5 because common synonyms like "regulon", "master regulator", "upstream regulators", or "gene set" are missing; not 3 since the term coverage is well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

"Dorothea database" and "TF-Target network" carve out a clear niche, but "transcription factor enrichment analysis" and "gene regulatory network research" overlap with the broad family of enrichment/network-analysis skills. Mostly distinct with minor overlap risk against closely related skills — not 5 (minimal conflict risk) because of that enrichment-analysis overlap; not 3 since the database and output type are highly distinctive.

4 / 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
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.