CtrlK
BlogDocsLog inGet started
Tessl Logo

subsystem-summary-of-scp

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

52

Quality

58%

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-scp/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.

A well-organized, information-dense reference that documents the SCP subsystem comprehensively — files, classes, protocol phases, timers, ownership, and data flows — with concrete identifiers throughout and no wasted explanation. Its main weaknesses are the fully-inlined monolithic structure with no progressive disclosure into reference files, and partial redundancy between the class-level sections and the flow-level sections.

Suggestions

Split the per-class API reference (Key Classes and Data Structures) into one-level-deep reference files (e.g. references/classes.md, references/protocol-phases.md) and keep SKILL.md as a shorter overview with clearly signaled links, so only the needed detail loads into context.

Trim the overlap between the method-level descriptions in the class sections and the SCP Protocol Phases / Key Data Flows sections, which restate the same nomination and ballot behaviors from a second angle.

DimensionReasoningScore

Conciseness

The body is dense and reference-style with no padding and no explanations of concepts Claude already knows — every entry carries codebase-specific information (paper variables X/Y/Z/b/p/p'/h/c, method semantics, constants like MAX_ADVANCE_SLOT_RECURSION=50). It falls short of 5 because the Phases, Control Flow, and Data Flows sections partially restate behavior already documented at the method level.

4 / 5

Actionability

As an instruction-only reference skill, it is maximally concrete: real file names, class names, member variables, method signatures, and their exact semantics, all directly usable for code navigation or question answering. It stays below 5 only because there are no executable commands or worked usage examples, and it is not 3 since nothing is vague or pseudocode.

4 / 5

Workflow Clarity

The multi-step processes it documents are clearly sequenced: numbered envelope-processing and emission flows, per-phase goal/state/transition breakdowns for nomination/PREPARE/CONFIRM/EXTERNALIZE, and the documented validation mechanisms of the subject system (isStatementSane, checkInvariants, value sanity checks). It is a descriptive reference rather than an operational skill, so there are no Claude-facing validation checkpoints, keeping it below 5.

4 / 5

Progressive Disclosure

The document is well-sectioned with clear headers and an ownership diagram, but roughly 330 lines of per-class API reference live entirely inline in SKILL.md with no references/ files at all — the class-by-class detail is exactly the content that could be split into one-level-deep reference files, matching the anchor-3 pattern of a long API reference inline in the main file.

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 is short and names its domain and deliverable, but it reads as an instruction to the reader ("read this skill") rather than a third-person capability description, provides no 'Use when' trigger guidance, and omits the synonyms (Stellar Consensus Protocol, stellar-core) that would both improve retrieval and disambiguate it from the scp file-copy command.

Suggestions

Add an explicit trigger clause, e.g. "Use when exploring, summarizing, or answering questions about the SCP (Stellar Consensus Protocol) subsystem in stellar-core".

Rewrite in third-person descriptive voice ("Summarizes the SCP subsystem of stellar-core...") instead of the imperative "read this skill for...".

Include natural trigger synonyms such as "Stellar Consensus Protocol", "stellar-core consensus", "nomination", and "balloting" to improve keyword coverage and reduce collision with the scp file-transfer command.

DimensionReasoningScore

Specificity

The description names its domain ("the scp subsystem") and a single generic deliverable ("a token-efficient summary"), which is a base-3 level of specificity; the imperative second-person voice ("read this skill for...") incurs the rubric's 1-point voice penalty, landing it at 2.

2 / 5

Completeness

It states a clear 'what' ("a token-efficient summary of the scp subsystem") but contains no 'Use when...' clause or any equivalent trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It includes relevant keywords ("scp", "subsystem", "summary") but misses the natural variations and synonyms users would actually say, such as "Stellar Consensus Protocol", "stellar-core", or "consensus" — terms the body itself establishes as the domain vocabulary.

3 / 5

Distinctiveness Conflict Risk

"the scp subsystem" is niche, but "scp" collides with the ubiquitous secure-copy file-transfer command, so outside a stellar-core repository context the description risks triggering for the wrong skill; it is not clearly distinct enough for 4.

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
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.