Loading...
Loading...
Found 1,943 Skills
Evaluate third-party agent skills for security risks before adoption or update. Use when: (1) Installing or updating a skill from skills.sh, ClawHub, or any public registry, (2) Auditing skills for security risks or reviewing PRs that add/update skill dependencies, (3) Building a team/org allowlist of approved skills, (4) Investigating suspicious skill behavior or answering "is this skill safe?" / "should we adopt this skill?"
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats
Benchmark any agent skill to measure whether it actually improves performance. Use when the user wants to evaluate, test, or compare a skill against baseline, or when they mention "benchmark", "eval", "skill performance", or "does this skill help". Runs isolated eval sessions with and without the skill, grades outputs via layered grading (deterministic checks + LLM-as-judge), analyzes behavioral signals, and generates a comparison report with a USE / DON'T USE verdict.
Model free cash flow to evaluate project or business value. Use for investment decisions, valuation, and understanding cash dynamics.
M&A strategy for acquiring companies or being acquired. Covers strategic rationale assessment, target screening, due diligence frameworks, valuation methodologies, deal structure, negotiation strategy, integration planning, and post-acquisition execution. Use when evaluating acquisitions, preparing to be acquired, conducting due diligence, planning integration, negotiating deal terms, or when user mentions M&A, acquisition, merger, acqui-hire, due diligence, valuation, LOI, earnout, integration, or deal structure.
For non-perishable things, future life expectancy is proportional to current age. Use for technology selection, evaluating frameworks/libraries, and predicting tool longevity.
A/B test agent variants measuring quality and total session token cost across simple and complex benchmarks. Use when creating compact agent versions, validating agent changes, comparing internal vs external agents, or deciding between variants for production. Use for "compare agents", "A/B test", "benchmark agents", or "test agent efficiency". Do NOT use for evaluating single agents, testing skills, or optimizing prompts without variant comparison.
Code-first Netra best-practices playbook covering setup, instrumentation, context tracking, custom spans/metrics, integration patterns, evaluation, simulation, and troubleshooting.
Apply the DeLone and McLean Information Systems Success Model to evaluate IS effectiveness through six interdependent dimensions. Use this skill when the user needs to assess system quality, information quality, or service quality of an IS, diagnose why users are dissatisfied, measure net benefits of a system investment, or when they ask 'how do we measure IS success', 'why are users unhappy with this system', or 'is our system delivering value'.
Evaluates Claude Agent Skills on 10 quality axes with letter grades (A+ through F) and specific improvement recommendations. Use when auditing a skill, comparing skills, prioritizing improvements, or performing quality control on a skill library. Activate on "grade skill", "evaluate skill", "skill quality", "skill audit", "skill review", "rate skill". NOT for creating skills (use skill-architect), grading code quality, or evaluating non-skill documents.
Optional Stage 0 of the feature workflow — clarify vague ideas through dialogue until they are ready to enter the design phase. The role of AI is a thinking partner: dig out the real problem the user wants to solve (instead of sticking to the first solution they blurt out), actively evaluate the solution when the user brings it up, and propose better alternatives if necessary. After the discussion, output {slug}-brainstorm.md to document the results. Trigger scenarios: The user says "I have an unclear idea", "Let's brainstorm first", "The feature direction is still undecided", or the user brings a specific solution but wants to hear other ideas first. Skip this stage and proceed directly to design if the idea is already clear and the user does not want to discuss the solution further. This stage also does not handle bugs and refactoring.
Patterns for DeFi market analysis, screening, and comparison using DefiLlama MCP tools. Covers valuation ratios (P/S, P/F), growth screening with pct_change columns, multi-metric protocol comparison, category comparison, and cross-entity analysis. Use when users ask to compare protocols, screen for undervalued projects, analyze growth trends, or do sector analysis.