CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

subsystem-summary-of-transactions

read this skill for a token-efficient summary of the transactions subsystem

Quality

66%

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 ./.claude/skills/subsystem-summary-of-transactions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 a dense, well-organized codebase reference with concrete file/class/method pointers and clearly sequenced data flows. Its main weaknesses are a monolithic single-file structure with no progressive disclosure via reference files, and some redundancy across the parallel-apply and transaction-frame sections.

Suggestions

Split the detailed class/method reference ("Key Classes and Data Structures", "Key Utility Modules") into references/ files (e.g. key-classes.md, flows.md), keeping SKILL.md as a concise overview with clearly signaled links.

Consolidate the redundant parallel-apply material spread across "Parallel Apply Infrastructure", "Parallel Apply Architecture", and "Threading Model" into a single section, and trim the overlap between "Key Files" and "Key Classes".

Add a short task-oriented index mapping common goals ("add a new operation", "trace a fee refund", "understand offer crossing") to the relevant files and classes to further boost actionability.

DimensionReasoningScore

Conciseness

The body is dense and factual with zero concept padding — it never explains what XDR, DEX, or a signature is, and assumes Claude's competence throughout. It falls short of 5 due to redundancy: TransactionFrame and the parallel-apply infrastructure are each described across multiple sections ("Key Files", "Key Classes", "Parallel Apply Architecture", "Threading Model").

4 / 5

Actionability

Concrete navigation pointers abound — exact file names ("TransactionFrame.h/.cpp"), method names ("commonValid", "processFeeSeqNum"), and call chains ("convertWithOffersAndPools() which iterates matching offers" → "crossOfferV10() → exchangeV10()"). Not 5 because there is no executable code or commands; for a codebase-reference skill the guidance is nonetheless specific and usable.

4 / 5

Workflow Clarity

Data flows are explicitly numbered and sequenced ("1. Deserialization ... 5. Parallel Apply"; the parallel-apply architecture steps 1-7) and show where validation occurs in the pipeline ("checkValid() → ... commonValid() → ... checkAllSignaturesUsed()"). Not 5 because these document the code's behavior rather than giving Claude an operative workflow with feedback loops; not 3 because sequencing is complete and checkpoints are shown.

4 / 5

Progressive Disclosure

The entire ~290-line reference is inline in SKILL.md with no bundle files — the detailed class/method reference (200+ lines of it) that could live in separate reference files is fully inlined. It is not 2 because the internal structure is good with clear section headers and hierarchies; it is not 4 because nothing is split out into or signaled from separate files.

3 / 5

Total

15

/

20

Passed

Description

45%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 names its domain but provides only one generic action ("summary") and completely omits trigger guidance. Adding a "Use when..." clause and concrete content keywords (transaction frames, operations, signature verification, apply pipeline) would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. "Use when exploring or modifying the transactions subsystem in stellar-core: transaction frames, operations, signature verification, or the apply pipeline."

Replace the meta-instruction "read this skill for" with third-person capability statements that list the concrete contents (key files, class hierarchy, validation/apply flows, protocol-version gates).

Include natural trigger synonyms users would say — "transaction processing", "TransactionFrame", "Soroban apply", "offer exchange" — to improve keyword coverage and distinctiveness.

DimensionReasoningScore

Specificity

The description names its domain ("transactions subsystem") but the only action offered is the generic "token-efficient summary" — no concrete capability actions are listed. It is not 3 because it lacks even 1-2 concrete actions like "extracts content"; not 1 because the domain is explicitly named.

2 / 5

Completeness

The "what" is stated ("a token-efficient summary of the transactions subsystem") but the "when" is entirely absent — there is no "Use when..." clause or equivalent trigger guidance, which caps this dimension at 3 per the judging guidelines. Not 4 because the trigger context is not even weakly explicit.

3 / 5

Trigger Term Quality

"transactions subsystem" is a relevant keyword, but the description misses the natural phrases a user would actually say ("transaction processing", "how transactions are applied", "TransactionFrame", "stellar-core"). It is not 2 because the keyword is domain-relevant rather than generic like "files".

3 / 5

Distinctiveness Conflict Risk

"transactions" alone would overlap with database-transaction or payment-processing skills, and "transactions subsystem" narrows it only somewhat without naming stellar-core or the codebase. It is somewhat specific but could still collide with similar skills, matching anchor 3.

3 / 5

Total

11

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

stellar/stellar-core

Path

.claude/skills/subsystem-summary-of-transactions/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.