CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

de-summary

Summarise pre-computed differential expression results with ranked gene lists, biological themes, and publication-ready interpretation.

Quality

75%

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 ./skills/de-summary/SKILL.md
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.

This is a highly actionable, well-structured instruction-only skill with concrete thresholds, tool-specific column handling, and useful behavioral guardrails against known failure modes. Its weaknesses are mild redundancy across sections and a missing error-recovery path for invalid input.

Suggestions

Cut or merge 'Why This Exists' and 'Scope' into the Trigger section — both repeat information already stated there — and state the disclaimer once instead of in both the example JSON and the Safety section.

Add a brief failure path to step 1 of the workflow: what to do when required columns (gene identifier, log2FoldChange, padj) are missing or unrecognizable, e.g. report the found columns and ask the user before proceeding.

Consider moving the full example output JSON to a one-level-deep reference file (e.g. references/example-output.md) and keeping only a truncated sample inline.

DimensionReasoningScore

Conciseness

The core workflow is lean, but several sections pad or duplicate: 'Why This Exists' is motivational ('a structured summary... is generated in seconds'), 'Scope' restates the Trigger's do-not-fire list, the disclaimer appears both in the Example Output JSON and the Safety section, and 'Agent Boundary' overlaps the Gotchas. It is not 2 because nothing explains concepts Claude already knows (no primer on what DE or padj is).

3 / 5

Actionability

The guidance is fully concrete: exact thresholds ('padj < 0.05 AND |log2FoldChange| >= 1.0'), sort and tie-break rules, enumerated column variants ('adj.P.Val for limma, FDR for edgeR'), named housekeeping genes (GAPDH, ACTB, TUBB), a 30% significance flag, and a complete example JSON covering the common case. Per the scoring notes, absence of code in an instruction-only skill is not penalized when the guidance is this executable.

5 / 5

Workflow Clarity

Seven clearly sequenced steps with validation checkpoints at step 1 (required-column check) and step 6 (pitfall flags), which fits 'clear sequence with most checkpoints present'. It is not 5 because there is no error-recovery loop — what to do when required columns are missing (abort, ask the user, best-effort?) is left unspecified. The workflow is read-only summarization, not destructive or batch, so the workflow-clarity cap does not apply.

4 / 5

Progressive Disclosure

The skill has no bundle files (no references/, scripts/, or assets/ exist), and the single body is well-organized with clear section headers and no nested references, matching 'good structure; most content appropriately placed'. It does not reach 5 because the body exceeds the under-50-line simple-skill exemption and material like the full example output could live in a one-level-deep reference file.

4 / 5

Total

16

/

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 specific and domain-scoped with mostly natural trigger terms, but it omits any 'when to use' guidance, capping completeness. Folding a 'Use when...' clause with the strongest trigger phrases into the description would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user provides a DESeq2/edgeR/limma results table and asks for a summary, top DE genes, or interpretation.'

Fold 2-3 of the frontmatter trigger_keywords (e.g. 'top DE genes', 'DE summary') into the description text itself so natural phrases are visible where descriptions are surfaced.

Mention the concrete inputs/outputs (CSV/TSV DE table in, markdown report and JSON out) to sharpen both specificity and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ('pre-computed differential expression results') and several concrete deliverables ('ranked gene lists, biological themes, and publication-ready interpretation'), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because it uses a single verb with objects rather than multiple distinct actions and omits thresholds, output formats, and input table types.

4 / 5

Completeness

It clearly answers 'what' (summarises pre-computed DE results into ranked lists, themes, and interpretation) but contains no 'Use when...' clause or equivalent trigger guidance in the description, which caps completeness at 3 per the judging guidelines. It is not 4 because the 'when' is entirely absent rather than merely implicit or weak.

3 / 5

Trigger Term Quality

'differential expression', 'summarise', and 'gene lists' are natural user phrasings with good coverage, but common variations a user would say — 'RNA-seq', 'top DE genes', tool names like DESeq2/edgeR — appear only in the frontmatter trigger_keywords, not in the description itself. Better than 3 (relevant keywords are present and mostly natural), not 5 (synonyms and tool/file variations are missing from the description text).

4 / 5

Distinctiveness Conflict Risk

'Pre-computed' plus the summarise/interpret framing carve out a clear niche distinct from upstream DE-analysis skills like rnaseq-de, with only minor overlap risk against closely related enrichment or visualization siblings. Not 5 because terms like 'biological themes' and 'interpretation' could plausibly fire for a pathway-enrichment skill.

4 / 5

Total

15

/

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

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository

ClawBio/ClawBio

Path

skills/de-summary/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.