dual-axis-skill-reviewer

Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/dual-axis-skill-reviewer/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with real, executable commands and clean progressive disclosure via verified reference files. It is held back by minor cross-section redundancy and a missing explicit validation step before the merge operation.

Suggestions

Remove the duplicated 90-threshold and weighted-average facts from the 'Resources' section since they already appear in 'When to Use' and Step 3.

Add an explicit validation checkpoint in Step 3 (e.g., confirm the LLM review JSON validates against `references/llm_review_schema.md` before running the merge).

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullets and copy-paste commands, but facts are repeated across sections (the 90-point threshold appears in both 'When to Use' and 'Resources'; the weighted-average mechanic in both Step 3 and 'Resources') and Step 2's orchestrator prose could be tightened, placing it at 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands with concrete flags throughout (e.g., `uv run "$REVIEWER" --project-root . --emit-llm-prompt --output-dir reports/`), matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The four-step sequence is clearly numbered (run auto+prompt, run LLM review, merge, optional controls), but there is no explicit validation checkpoint (e.g., verifying the LLM review JSON conforms to the schema before merge), so it sits at 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	The body is a concise overview with well-signaled, one-level-deep references to real bundle files (`references/llm_review_schema.md`, `references/scoring_rubric.md`, and `scripts/run_dual_axis_review.py`, all present), matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 is strong on completeness and distinctiveness, with an explicit 'Use when...' clause and a clear niche. It loses points on trigger-term naturalness (jargon-heavy) and on specificity due to the second-person 'you need' phrasing.

Suggestions

Rewrite in third person to avoid the specificity penalty (e.g., 'Use when reproducible quality scoring is needed' instead of 'Use when you need...').

Soften jargon and add common user phrasings like 'audit' or 'evaluate skills' alongside 'review skills' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ('deterministic code-based checks (structure, scripts, tests, execution safety)' and 'LLM deep review findings'), which reaches the specificity anchor, but the second-person phrasing 'Use when you need' triggers the -1 specificity penalty per the judging guidelines.	2 / 3
Completeness	It clearly answers what ('Review skills... using a dual-axis method: (1)... and (2)...') and when via an explicit 'Use when you need reproducible quality scoring..., want to gate merges..., or need concrete improvement items...' clause, matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Natural terms like 'review skills', 'quality scoring', and 'gate merges with a score threshold' are present, but the description leans on jargon ('deterministic code-based checks', 'LLM deep review findings', 'auto-axis') and omits common variations such as 'audit' or 'evaluate skills', so it lands at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche (a meta-reviewer for `skills/*/SKILL.md` quality scoring and merge gating) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/dual-axis-skill-reviewer/SKILL.md
Commit: 62a1635

Reviewed: 5 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.