ax-cpp-agent-observability

Use when writing C++ code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/cpp/skills/ax-cpp-agent-observability/SKILL.md

Quality

Content

61%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 dense, competent API reference with executable core snippets and useful guardrails, weakened by a missing bundle: every referenced file (API.md, examples/, the usage observer example) is absent, so progressive disclosure largely fails. It also reads as a topical reference rather than a workflow, with no sequenced steps or validation checkpoints for the tasks it lists.

Suggestions

Ship the referenced files with the skill (API.md, examples/, src/examples/cpp/generation/usage_observer.cpp) or remove/fix the references so navigation points to real bundle content.

Move the ~40-symbol "Relevant API Surface" listing into a bundled reference file and link to it, keeping only the handful of symbols needed for the core patterns inline.

Add a short ordered workflow for the main tasks (inspect traces -> register usage observer -> attribute by tenant -> debug via examples) with a verification step such as running the no-key examples to confirm the setup.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence ("Package Facts", dense actionable bullets, no concept tutorials). The ~40-symbol inline dump in "Relevant API Surface" is the main over-inclusion that could be trimmed or moved to a reference file, keeping it at anchor 4 rather than 5.	4 / 5
Actionability	Two executable C++ snippets (core pattern, usage observer) plus exact symbol names and pointers to a runnable example ("src/examples/cpp/generation/usage_observer.cpp"). Falls short of anchor 5 because `llm` is undefined in the core pattern and most claimed tasks (tracing, action logs, replay, diagnostics) get no code, only an API name listing.	4 / 5
Workflow Clarity	The body is organized topically (When To Use, Package Facts, patterns, guardrails) but never sequences a multi-step process or provides checkpoints. Anchor 3 fits: structure and guidance exist, but there is no explicit step order or validation across the multiple tasks the skill claims to cover, so it cannot reach anchor 4's clear-sequence bar.	3 / 5
Progressive Disclosure	The body references `API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`, and `src/examples/cpp/generation/usage_observer.cpp`, but no bundle files exist (no references/, scripts/, or assets/ directories), so navigation points to files that are not shipped. Combined with the inlined API symbol dump that belongs in a separate file, this matches anchor 2 (minimal structure, inlined content, broken/buried references).	2 / 5
	Total	13 / 20 Passed

Description

78%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 description with an explicit trigger clause, a distinctive niche anchored by the unique package name, and a list of concrete capability areas. Its main weakness is that the what and when are merged into one clause and common observability synonyms (telemetry, monitoring, logging) are absent.

Dimension	Reasoning	Score
Specificity	Names several concrete capability areas ("agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging") tied to a specific package and language. Not 5 because these are capability nouns without concrete action verbs; not 3 because coverage goes well beyond 1-2 items.	4 / 5
Completeness	Both what and when are present, with an explicit "Use when writing C++ code with `axllm` for..." trigger. The what is fused into the same clause as a purpose list rather than stated as a distinct capability statement, so it matches anchor 4 (when explicit, what could be more explicit) rather than anchor 5.	4 / 5
Trigger Term Quality	Good natural phrases a user would say ("agent tracing", "usage accounting", "action logs", "production debugging", "C++") anchored by the unique package name `axllm`. A few common synonyms like "telemetry", "monitoring", "metrics", or "logging" are missing, so it falls short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche: C++ code with the uniquely named `axllm` package for observability tasks. The package name and language constraint make it highly distinguishable from any other skill with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: ax-llm/ax
Path: packages/cpp/skills/ax-cpp-agent-observability/SKILL.md
Commit: 3f630a0

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.