CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-cpp-playbook

Use when writing C++ code with `axllm` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./packages/cpp/skills/ax-cpp-playbook/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%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 lean, well-organized body that respects token budget and delegates detail appropriately. Its weaknesses are a non-executable core code example and the absence of a sequenced workflow with validation checkpoints for the evolve/verify/rollback process it describes.

Suggestions

Make the Core Pattern executable by showing llm construction, the shape of `examples`, and a `metric_fn` signature — or point to one specific runnable example file that demonstrates the full loop.

Add a short numbered workflow for evolving a playbook (seed → attach → evolve → verify → rollback on regression) with an explicit validation checkpoint before persisting changes.

Include a minimal no-key deterministic check snippet so the "use no-key examples for deterministic local checks" guardrail is actionable without leaving the skill.

DimensionReasoningScore

Conciseness

The body is lean and dense — terse fact lists ("Language: C++", "Package: `axllm`") and compact guardrails — with no explanation of concepts Claude already knows. Every section earns its place, matching the top anchor; there is no over-explanation to trim that would justify a 4.

5 / 5

Actionability

The Core Pattern uses undefined placeholders (`*llm`, `examples`, `metric_fn`), making it a shape sketch rather than executable code, and the skill itself defers exact syntax elsewhere ("Start from package examples for exact native syntax"). This matches "pseudocode instead of executable code; missing key details" rather than the mostly-executable guidance of a 4.

3 / 5

Workflow Clarity

Only a rough sequence exists (the 3-line Core Pattern: create program → playbook → evolve) with no explicit ordering, validation checkpoints, or error-recovery loop for the evolve/verify/rollback process the skill centers on; verification and rollback are mentioned as features, not as workflow steps. Matches a rough sequence with many gaps rather than the listed-steps-with-validation-gaps of a 3.

2 / 5

Progressive Disclosure

A single-file skill under 50 lines with well-organized sections and no bundle files to disclose; detail is appropriately delegated to package artifacts clearly listed under Package Facts ("Package API docs: `API.md` and `axir-api.json`", "Runnable examples: `examples/`"). Per the under-50-lines exception this warrants the top score.

5 / 5

Total

15

/

20

Passed

Description

71%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, appropriately niche description that explicitly covers both what and when with several concrete capability areas. Its main weakness is jargon-heavy phrasing ("context-engineering surface", "run-end learning") that users would not naturally say, weakening trigger-term quality.

Suggestions

Add natural trigger phrases users would actually say, e.g., "Use when the user asks to evolve a playbook, learn from failed runs, or improve prompts from feedback".

Pair package jargon terms with plain-language synonyms (e.g., "run-end learning (learning from failed agent runs)") so the description matches how users phrase the need.

DimensionReasoningScore

Specificity

Lists several concrete capability areas — "playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program" — though each is phrased in package jargon rather than plain actions. It is not a 5 because the actions lack the plain-language comprehensiveness of the top anchor, and not a 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

Explicitly answers both: "what" via the capability list and "when" via "Use when writing C++ code with `axllm`". Not a 5 because the when-clause lacks concrete trigger phrases a user would say, not the vague-what/no-when of a 3.

4 / 5

Trigger Term Quality

Relevant keywords are present ("C++", "axllm", "playbook"), but phrases like "context-engineering surface" and "agent-bound verified evolution" are package jargon users would not naturally say, and common variations (e.g., "evolve a playbook", "learn from run failures") are missing. Matches "some relevant keywords but missing common variations or synonyms" rather than the good-with-few-gaps coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

Clear niche — C++ development with the specific generated package `axllm` for playbook evolution — with distinct triggers ("axllm", "playbook()") and minimal overlap risk with other skills.

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-playbook/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.