CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

subsystem-summary-of-work

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

Quality

65%

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-work/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 for the work subsystem that mostly avoids explaining things Claude already knows. Its main structural weakness is that it is a single monolithic document: the per-class detail should be split into references/ files behind a concise overview, and a few redundant or garbled sections could be tightened.

Suggestions

Split per-class API reference into one-level-deep reference files (e.g., references/basic-work.md, references/work-scheduler.md) and keep SKILL.md as a compact overview with clearly signaled links.

Redraw or replace the ASCII state-transition diagram — it is visually garbled and duplicates the clearer numbered Lifecycle Flow.

Deduplicate the scheduling explanation between the WorkScheduler "Scheduling Model" paragraph and the "Main Scheduling Loop" section.

DimensionReasoningScore

Conciseness

The body is dense, factual tables and bullets with no general-concept padding, but minor trimming is possible: the garbled ASCII state-transition diagram and the scheduling model explained twice (in the WorkScheduler section and again in "Main Scheduling Loop").

4 / 5

Actionability

Concrete, specific reference material throughout: exact method tables ("setState(s) Validates transition legality... Automatically converts FAILURE→RETRYING"), the mAbortChildrenButNotSelf behavioral detail, and a real usage example ("in DownloadApplyTxsWork (a BatchWork), each yielded WorkSequence contains..."). No executable code, but for a reference/summary skill the specifics are largely complete with only minor gaps (e.g., no signatures or file paths for following up).

4 / 5

Workflow Clarity

The FSM lifecycle is clearly sequenced (numbered Lifecycle Flow 1-7, Retry Mechanism, notification propagation, abort/shutdown flow) and there are no destructive or batch operations requiring validation steps. Not a 5 because the state diagram is visually confusing and some transitions described in prose (e.g., terminal restart via startWork) are hard to trace in the diagram.

4 / 5

Progressive Disclosure

A ~370-line monolith with no bundle files at all (no references/, scripts/, or assets/ exist). Section headers are good, but the per-class API-reference tables (BasicWork, Work, WorkScheduler, WorkSequence, BatchWork, ConditionalWork, WorkWithCallback) clearly belong in separate one-level-deep reference files with SKILL.md as overview.

3 / 5

Total

15

/

20

Passed

Description

41%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 identifies a real niche but reads as meta-instruction to Claude rather than a capability statement with user-facing triggers. It lacks a "what it covers" breakdown and any "Use when..." clause, leaving it unlikely to surface when users ask about work scheduling, retries, or task trees in stellar-core.

Suggestions

Rewrite in third person with concrete coverage, e.g. "Summarizes stellar-core's work subsystem: the BasicWork FSM, hierarchical Work trees, WorkScheduler scheduling, sequential/batched/conditional execution, retry with backoff, and abort/shutdown semantics."

Add an explicit trigger clause: "Use when asked about the work subsystem, work scheduling, cranks, retries, or task execution in stellar-core."

Drop "read this skill for" and "token-efficient" — reader-directed meta-language and internal jargon that no user would say.

DimensionReasoningScore

Specificity

"a token-efficient summary of the work subsystem" names the domain but offers only one generic action ("summary"); the imperative "read this skill for" is reader-directed rather than third-person, applying the -1 penalty from a base of 3.

2 / 5

Completeness

The "what" is stated ("token-efficient summary of the work subsystem") but there is no "when" clause at all — "read this skill for" is meta-instruction, not trigger guidance — so completeness is capped at 3 per the guidelines.

3 / 5

Trigger Term Quality

The only real keywords are "work subsystem" and "summary"; "token-efficient" is meta-jargon no user would say, and natural phrases like stellar-core, BasicWork, WorkScheduler, task execution, or retry/backoff are absent.

2 / 5

Distinctiveness Conflict Risk

"the work subsystem" is a fairly distinct niche within the stellar-core codebase, but without naming stellar-core or its key classes (BasicWork, WorkScheduler) it risks minor overlap with generic scheduling/workflow skills.

4 / 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-work/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.