CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-cpp-flow

Use when writing C++ code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

Quality

71%

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 ./packages/cpp/skills/ax-cpp-flow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 pattern-library skill with strong, executable C++ examples for flow composition and a well-organized front half. Its weaknesses are the verbose, inline 'Astra Session Work' section that belongs in a reference file, and the absence of an explicit step-by-step workflow with checkpoints.

Suggestions

Move the 'Astra Session Work' section's dense detail (MCP policy, cancellation, session adapters, validators, parallel worker semantics) into a separate reference file (e.g. references/astra-sessions.md) and keep a short summary with a clearly signaled link in SKILL.md.

Add a minimal example showing how to construct the `client` passed to `forward()` and the `fn` passed to `axllm::caching_function`, so the code examples are fully copy-paste runnable.

Add a short ordered workflow (e.g. 1. pick transport from examples (no-key vs provider), 2. build the flow with reads/writes, 3. run with forward, 4. verify output) so the intended usage sequence is explicit rather than implicit in section order.

DimensionReasoningScore

Conciseness

The flow-pattern sections are dense and factual with no explanation of concepts Claude already knows, but the ~26-line 'Astra Session Work' section is a wall of compressed prose covering MCP policy, cancellation, session adapters, and validators that could be substantially tightened or split. Mostly efficient overall, with clear room for trimming — matching the 'mostly efficient but some unnecessary content' anchor.

3 / 5

Actionability

Provides multiple concrete, executable C++ code blocks (core flow, typed programs, branch, fan-out/join, refine pipeline, forward, caching) plus specific API names like `add_child_agent`, `set_tool_authorizer`, and `axllm::caching_function`. Minor gaps keep it from fully copy-paste-ready: `client` and `fn` are used in examples but never constructed.

4 / 5

Workflow Clarity

There is an organized progression (When To Use → Package Facts → Core Pattern → More Patterns → run/cache → Guardrails) and the Guardrails give decision rules ('Start from package examples... before inventing a new call shape', 'Use no-key examples for deterministic local checks'), but no explicit step sequence with validation checkpoints — the intended workflow is implicit in section order. No destructive or batch operations, so the workflow cap does not apply.

3 / 5

Progressive Disclosure

Header structure is good and Package Facts lists reference targets (`API.md`, `axir-api.json`, `examples/`), but no bundle files actually exist alongside the skill, and the long inline 'Astra Session Work' reference material clearly belongs in a separate file. This matches the anchor of some structure with content that should be separate kept inline.

3 / 5

Total

13

/

20

Passed

Description

73%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 focused, domain-pinned description with an explicit 'Use when' trigger and a good spread of natural domain keywords. Its main weakness is that it lists subsystems rather than concrete actions, leaving the 'what does this skill do' side implicit.

DimensionReasoningScore

Specificity

Names the domain ('C++ code with `axllm`') and concrete feature areas ('flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components'), but the only action named is 'writing' — no distinct concrete actions like composing, debugging, or running flows. This fits the 'names domain and 1-2 concrete actions' anchor better than the level-4 anchor, which expects a list of specific actions.

3 / 5

Completeness

The explicit 'Use when writing C++ code with `axllm` for...' clause answers 'when' clearly, and the 'what' (helping write such code for the listed subsystems) is discernible but implicit. Both are present with the 'when' side stronger, matching the anchor where both exist but one could be more explicit.

4 / 5

Trigger Term Quality

Includes good natural keywords a user of this package would say ('C++', 'flows', 'nodes', 'caching', 'nested programs'), though some terms are jargon-leaning ('program graphs', 'optimizer components') and common variants ('workflow', 'AxFlow') are missing. Good coverage but short of the comprehensive synonym-level coverage of the top anchor.

4 / 5

Distinctiveness Conflict Risk

The '`axllm`' package name pins a clear niche and the C++ language qualifier narrows it further, so the risk of triggering for an unrelated skill is minimal. Only the generic 'writing C++ code' phrasing carries any overlap risk, which is not enough to drop below the clear-niche anchor.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

ax-llm/ax

Path

packages/cpp/skills/ax-cpp-flow/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.