CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

package-split

Inventory the APIs other modules consume, to choose package-split extraction boundaries.

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 ./.agents/skills/package-split/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 body is an exemplar of token-efficient, operationally dense guidance: real commands with flags, sequencing with an approval gate, honest caveats about over-approximation, and test integration. Its only gaps are minor — placeholder bracket syntax instead of a fully copy-paste invocation and no guidance on interpreting the JSON evidence or handling unparsed files.

DimensionReasoningScore

Conciseness

Every sentence carries operational information — exit codes ("always exit 0 on success (2 on usage or input errors)"), skip behavior for unparsed files, output paths, and the over-approximation caveat — with zero explanation of concepts Claude already knows; nothing is trimmable, matching the lean anchor rather than the minor-over-explanation anchor at 4.

5 / 5

Actionability

Concrete executable commands with real flags ("api-usage --module ddtrace.internal.coverage [--source-path ddtrace ...]") plus specific workflow variants (production-first, combined, test-only scans) and output location guidance; bracketed placeholder notation and the absence of an output-interpretation example keep it just below the copy-paste-ready anchor at 5, while it is well above the pseudocode/incomplete anchor at 3.

4 / 5

Workflow Clarity

A clear ordered sequence is present — production scan, then combined inventory, then api-surface, then "propose a narrow supported API ... and get scope and naming approved before moving code", then fixtures and "scripts/run-tests and scripts/lint" — with an explicit approval gate and test validation; it lacks an error-recovery loop (e.g. what to do with files in the "unparsed" field), fitting anchor 4 rather than 5. The operations are read-only analysis, so the destructive/batch validation cap does not apply.

4 / 5

Progressive Disclosure

The body is under 50 lines, needs no external reference documents, and is well organized (usage block, per-command bullets, closing workflow guidance), so the simple-skill exception applies and the well-organized-sections anchor at 5 fits; there is no inlined bulk content that belongs in separate files.

5 / 5

Total

18

/

20

Passed

Description

53%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 states a clear, concrete capability in an appropriately terse third-person form, but it omits any "Use when..." trigger guidance and natural synonyms, which limits discoverability and keeps completeness and trigger-term quality at the midpoint. It is distinctive within a narrow niche yet under-specified relative to what the skill actually offers.

Suggestions

Add an explicit trigger clause, e.g. "Use when splitting a package, extracting a module into its own package, or deciding which symbols belong in a supported API."

Include natural user phrasings and synonyms such as "package split", "extract a module", "carve out", "modularize", or "public API surface" so the description matches how users actually ask.

Mention both capabilities rather than one — e.g. that it also groups consumed symbols by owning module and zone and suggests extraction candidates — to broaden specificity coverage.

DimensionReasoningScore

Specificity

"Inventory the APIs other modules consume, to choose package-split extraction boundaries" names one concrete action plus its purpose, matching the 1-2-concrete-actions anchor; it does not list several specific actions (score 4) and is far more concrete than generic domain-naming (score 2).

3 / 5

Completeness

The "what" is clear (inventory consumed APIs to pick extraction boundaries), but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3; the purpose clause only weakly implies when to use it.

3 / 5

Trigger Term Quality

Relevant domain keywords are present ("APIs", "modules", "package-split", "extraction"), but common natural phrasings users would say — "split this package", "extract a module", "modularize", "carve out" — are missing, matching the some-keywords-but-missing-synonyms anchor.

3 / 5

Distinctiveness Conflict Risk

"package-split extraction boundaries" carves out a narrow refactoring niche with minimal overlap against unrelated skills, but it could still collide with generic dependency-analysis or refactoring skills since no explicit triggers distinguish it, fitting the mostly-distinct anchor rather than the fully-distinct one.

4 / 5

Total

13

/

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

referenced_paths_exist

Referenced path issues: 4 possibly missing (scripts/import-analysis/layers.json, scripts/lint, scripts/package-split, scripts/run-tests), 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

DataDog/dd-trace-py

Path

.agents/skills/package-split/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.