CtrlK
BlogDocsLog inGet started
Tessl Logo

subsystem-summary-of-process

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

55

Quality

61%

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-process/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.

The body is a well-organized, information-dense technical summary that delivers exactly what the description promises: concrete classes, members, flows, platform differences, and error-handling notes with no filler. Its weaknesses are mild — some cross-section repetition, no executable code sample of the runProcess/async_wait pattern, and all API detail inlined in the single file.

DimensionReasoningScore

Conciseness

The body is dense, factual reference material with essentially no padding and no re-explanation of concepts Claude already knows (it does not explain what a subprocess or asio is). It falls just short of anchor 5 because some information repeats across sections — exit handling and shutdown behavior appear in 'Key Control Flows', 'Key Data Flows', and the 'Platform Differences' table — so a modest trim is possible ('minor instances... that could be trimmed').

4 / 5

Actionability

As a summary/reference skill, its guidance is concrete rather than instructive: real file names ('ProcessManagerImpl.cpp'), exact signatures ('runProcess(cmdLine, outputFile)'), precise constants ('Config::MAX_CONCURRENT_SUBPROCESSES', exit code 127 handling), and platform-specific calls ('posix_spawnp()', 'CreateProcess() with CREATE_NEW_PROCESS_GROUP'). It is not 5 because there is no copy-paste-ready code or command a Claude could execute directly — the content informs rather than operates, and a small usage example of the runProcess/async_wait pattern would close that gap.

4 / 5

Workflow Clarity

The 'Key Control Flows' section lays out clearly numbered sequences for launch, POSIX and Windows exit handling, shutdown, and concurrency control, with a documented validation mechanism ('checkInvariants() validates consistency... Called at key state transitions'). It does not reach 5 because the flows are descriptive of the codebase rather than operational workflows with explicit feedback loops, and the shutdown path's retry behavior ('loops up to 3 times sleeping 10ms') is narrated rather than checkpointed — minor validation gaps per anchor 4.

4 / 5

Progressive Disclosure

There is a clear header hierarchy (Overview, Key Files, Key Classes, Control Flows, Ownership, Data Flows, Platform Differences, Error Handling) that makes the ~200-line document navigable, and no bundle files exist (no references/, scripts/, or assets/), so nothing is buried or nested. It does not score 5 because the full API/member detail (e.g., every ProcessExitEvent::Impl member and PosixSpawnFileActions internals) sits inline in SKILL.md where a split — e.g., a platform-details or class-reference file — could keep the main file leaner; 'minor organization gaps' per anchor 4.

4 / 5

Total

16

/

20

Passed

Description

48%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 its niche (the process subsystem) but is skeletal: it names no concrete capabilities, omits any 'when to use' guidance, and uses imperative second-person voice rather than the third person. It reads as a bare pointer rather than a self-contained description that would surface the skill at the right moment.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about the process subsystem, subprocess spawning, ProcessManager, or how stellar-core runs external commands.'

Rewrite in third person and enumerate concrete capabilities: 'Summarizes the stellar-core process subsystem: the ProcessManager API (runProcess, shutdown), posix_spawnp/CreateProcess spawning, async exit handling via SIGCHLD, and the two-phase shutdown lifecycle.'

Include natural synonyms users would say — 'subprocess', 'spawn', 'external commands', 'ProcessManager' — alongside 'process subsystem' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("the process subsystem") but offers only a single generic action ("a token-efficient summary") — matching anchor 2 ('Names the domain but actions are minimal or generic', e.g. 'Processes PDF files') rather than anchor 3, which expects 1-2 concrete actions. Additionally, the imperative 'read this skill' addresses the reader in second-person voice, which the guidelines penalize by reducing specificity by 1 (base 3 → 2); it is not above 2 because no concrete capability (spawning subprocesses, shutdown handling, exit-code mapping) is stated.

2 / 5

Completeness

The 'what' is present ('a token-efficient summary of the process subsystem') but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which the guidelines state should cap completeness at 3. It does not score 4 because the usage context is not merely implicit but missing altogether.

3 / 5

Trigger Term Quality

Relevant keywords exist ('process subsystem', 'summary', 'token-efficient') but common variations users would actually say are missing: 'subprocess', 'spawn', 'ProcessManager', 'runProcess', 'stellar-core'. This matches anchor 3 ('Some relevant keywords but missing common variations or synonyms') — not 4, which requires good coverage with only a few natural terms missing, and not 2, since the terms present are relevant rather than purely generic.

3 / 5

Distinctiveness Conflict Risk

'the process subsystem' carves out a fairly distinct niche within its codebase and is unlikely to trigger for unrelated skills; residual overlap risk with generic OS-process/subprocess topics and sibling subsystem-summary skills keeps it at anchor 4 ('Mostly distinct; minor overlap risk') rather than 5, which demands clearly distinct trigger phrases that this description lacks.

4 / 5

Total

12

/

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.