CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

boost-asio-pro

Use when writing or reviewing asynchronous C++ networking code with Boost.Asio or standalone Asio — TCP/UDP servers and clients, SSL/TLS, timers, strands, io_context, co_spawn, awaitable, async_read/async_write, asio::spawn, yield_context, or pre-C++20 completion-handler callbacks.

72

Quality

91%

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

The canonical home for this skill is boost-asio-pro in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary SKILL.md body: it routes by toolchain first, hard-codes verified version floors, inlines only the rules that are genuinely easy to get wrong (strand write interleaving, buffer ownership, executor types), and delegates full implementations to real, one-level-deep reference files and CI-verified examples. Validation is baked in as a compile-it checklist. The only trimmable fat is slight duplication between the Overview and later sections.

DimensionReasoningScore

Conciseness

The body is dense and expert-level throughout — it assumes competence (never explains what Asio or coroutines are), and time-sensitive version numbers are consolidated into a dedicated 'version floors' table rather than scattered prose. Minor duplication keeps it below anchor 5: the CI-verified claim appears in both the Overview and Worked examples sections, and the Overview sentence 'Use this skill whenever async C++ networking code is being written or reviewed' repeats the frontmatter description.

4 / 5

Actionability

Fully executable guidance throughout: concrete detection commands ('dpkg -l libboost-dev', 'brew info boost'), a version→style→file decision table, exact flags ('$<$<CXX_COMPILER_ID:GNU>:-fcoroutines>', 'BOOST_ERROR_CODE_HEADER_ONLY'), a copy-paste-ready namespace shim code block, and links to three CI-verified implementations. This matches anchor 5 ('copy-paste ready code or commands; specific examples cover the common cases').

5 / 5

Workflow Clarity

A clearly sequenced multi-step process ('Step 1: pick the style' → 'Step 2: version floors' → 'Step 3: the rules') with an explicit validation checkpoint ('It compiles. Build it — most of the mistakes above are compile-time'), a terminal 'Before you call it done' checklist mapping back to each rule, and a Mistake→Fix anti-patterns table for error recovery. This matches anchor 5 (clear sequence, explicit validation, feedback paths, checklist).

5 / 5

Progressive Disclosure

The body is a genuine overview/router with only the highest-value rules inline; all five referenced files (coroutines.md, pre-cpp20.md, classic-boost.md, ssl.md, build.md) exist in references/, are exactly one level deep, and are clearly signaled via the decision table's 'Read' column and per-topic pointers. This matches anchor 5 ('clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation').

5 / 5

Total

19

/

20

Passed

Description

86%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.

A strong, highly specific trigger description that enumerates exactly the API vocabulary users would mention and covers both Boost and standalone Asio variants. Its only weakness is structural: the 'what' and 'when' are fused into a single 'Use when writing or reviewing...' clause, leaving the skill's distinct deliverables implicit. Third-person voice and comprehensive trigger coverage are exemplary.

Suggestions

Split the fused clause to explicitly state deliverables before the trigger, e.g. 'Write and review version-correct async C++ networking code (style selection, version floors, CI-verified examples). Use when writing or reviewing...'

Name the skill's concrete outputs — version compatibility guidance, per-style reference files, and CI-verified worked examples — so the 'what' answers what the skill provides, not just what the user is doing.

DimensionReasoningScore

Specificity

The description names the domain ('asynchronous C++ networking code with Boost.Asio or standalone Asio') and concrete actions ('writing or reviewing') with a near-comprehensive scope enumeration ('TCP/UDP servers and clients, SSL/TLS, timers, strands, io_context, co_spawn, awaitable, async_read/async_write'), but it lists only two action verbs rather than multiple distinct deliverable actions, so it matches anchor 4 ('several specific actions; minor gaps') rather than anchor 5.

4 / 5

Completeness

An explicit 'Use when...' trigger is present and the 'what' is embedded ('writing or reviewing asynchronous C++ networking code... with [these features]'), but what and when are merged into a single clause and the skill's distinct deliverables are not enumerated separately. It sits between anchor 4 ('both what and when; when could be more explicit') and anchor 5, and is noticeably above the midpoint rather than a clear anchor-5 match.

4 / 5

Trigger Term Quality

It covers the natural vocabulary a user doing Asio work would actually say — 'io_context', 'co_spawn', 'awaitable', 'async_read/async_write', 'asio::spawn', 'yield_context', 'strands', 'completion-handler callbacks' — including both library synonyms (Boost.Asio and standalone Asio). This matches anchor 5's comprehensive coverage including synonyms; anchor 4 ('a few natural terms missing') understates it.

5 / 5

Distinctiveness Conflict Risk

The niche is unmistakable — Boost.Asio/standalone Asio with API-level triggers like 'co_spawn', 'awaitable', and 'yield_context' — so it would not fire for any other skill. This matches anchor 5 ('clear niche with distinct triggers; minimal conflict risk'). Voice is third-person, so no specificity penalty applies.

5 / 5

Total

18

/

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

alirezarezvani/claude-skills

Path

engineering/boost-asio-pro/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.