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.
What this skill does
# 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` ## 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: ```bash # 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 ```bash uv run "$REVIEWER" \ --project-root . \ --emit-llm-prompt \ --output-dir reports/ ``` When reviewing a different project, point `--project-root` to it: ```bash uv run "$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 ```bash 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) ## Installation (Global) To use this skill from any project, symlink it into `~/.claude/skills/`: ```bash 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`
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.