Index of every page on this site: llms.txt
All skills
tradermonty avatar

/dual-axis-skill-reviewer

@f95e770
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/tradermonty/claude-trading-skills/dual-axis-skill-reviewer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈108 tokens for metadata: the name and description. ≈1.1k when used: this file. ≈678 more on demand in 2 files.

Description uses 5.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈432 characters, or 5.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Dual Axis Skill Reviewer

Run the dual-axis reviewer script and save reports to reports/.

The script supports:

  • Random or fixed skill selection
  • Auto-axis scoring with optional test execution
  • LLM prompt generation
  • LLM JSON review merge with weighted final score
  • Cross-project review via --project-root
  • Non-scoring display of skills-index.yaml production verification declarations

When to Use

  • Need reproducible scoring for one skill in skills/*/SKILL.md.
  • Need improvement items when final score is below 90.
  • Need both deterministic checks and qualitative LLM code/content review.
  • Need to review skills in a different project from the command line.

Prerequisites

  • Python 3.9+
  • uv (recommended — auto-resolves pyyaml dependency via inline metadata)
  • For tests: uv sync --extra dev or equivalent in the target project
  • For LLM-axis merge: JSON file that follows the LLM review schema (see Resources)

Workflow

Determine the correct script path based on your context:

  • Same project: skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py
  • Global install: ~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

The examples below use REVIEWER as a placeholder. Set it once:

# If reviewing from the same project:
REVIEWER=skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

# If reviewing another project (global install):
REVIEWER=~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

Step 1: Run Auto Axis + Generate LLM Prompt

uv run "$REVIEWER" \
  --project-root . \
  --emit-llm-prompt \
  --output-dir reports/

When reviewing a different project, point --project-root to it:

uv run "$REVIEWER" \
  --project-root /path/to/other/project \
  --emit-llm-prompt \
  --output-dir reports/

Step 2: Run LLM Review

  • Use the generated prompt file in reports/skill_review_prompt_<skill>_<timestamp>.md.
  • Ask the LLM to return strict JSON output.
  • When running inside Claude Code, let Claude act as orchestrator: read the generated prompt, produce the LLM review JSON, and save it for the merge step.

Step 3: Merge Auto + LLM Axes

uv run "$REVIEWER" \
  --project-root . \
  --skill <skill-name> \
  --llm-review-json <path-to-llm-review.json> \
  --auto-weight 0.5 \
  --llm-weight 0.5 \
  --output-dir reports/

Step 4: Optional Controls

  • Fix selection for reproducibility: --skill <name> or --seed <int>
  • Review all skills at once: --all
  • Skip tests for quick triage: --skip-tests
  • Change report location: --output-dir <dir>
  • Increase --auto-weight for stricter deterministic gating.
  • Increase --llm-weight when qualitative/code-review depth is prioritized.

Output

  • reports/skill_review_<skill>_<timestamp>.json
  • reports/skill_review_<skill>_<timestamp>.md
  • reports/skill_review_prompt_<skill>_<timestamp>.md (when --emit-llm-prompt is enabled)

When the target project has a skills-index.yaml entry with a complete verification block, JSON and Markdown reports also show its declared axes, not_verified gaps, non-applicable axes, and all_applicable_axes_passed. This section is informational only. It is excluded from auto/LLM/final scores and does not replace a live high-severity issue check.

Installation (Global)

To use this skill from any project, symlink it into ~/.claude/skills/:

ln -sfn /path/to/claude-trading-skills/skills/dual-axis-skill-reviewer \
  ~/.claude/skills/dual-axis-skill-reviewer

After this, Claude Code will discover the skill in all projects, and the script is accessible at ~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py.

Resources

  • Auto axis scores metadata, workflow coverage, execution safety, artifact presence, and test health.
  • Auto axis detects knowledge_only skills and adjusts script/test expectations to avoid unfair penalties.
  • LLM axis scores deep content quality (correctness, risk, missing logic, maintainability).
  • Final score is weighted average.
  • If final score is below 90, improvement items are required and listed in the markdown report.
  • Script: skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py
  • LLM schema: references/llm_review_schema.md
  • Rubric detail: references/scoring_rubric.md

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning1mo5 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill is a utility for auditing AI agent skills, performing automated quality checks and facilitating deep LLM reviews. It safely handles external input using safe YAML parsing and includes security-positive features like PII detection. While it can execute tests on evaluated projects, this is a core documented function performed through secure subprocess calls.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

  • Runlayer8mo

    2/6 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at f95e770. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 months ago

README badge

README badge for tradermonty/claude-trading-skills/dual-axis-skill-reviewer