irfad7/claude-power-skills
20 skills
$npx skills add irfad7/claude-power-skillsSkillInstalls
anti-distillationWhen working on sensitive projects, proprietary code, or systems where context leakage is a concern.autodreamWhen ending a session, consolidating memory, or when memory files feel stale or contradictory.batch-modeWhen the user needs to perform the same operation across multiple files, components, or entities.bughunterWhen the user wants to find bugs, test edge cases, stress-test code, or perform adversarial analysis of their codebase.code-reviewWhen the user wants a thorough code review of changes, a PR, a file, or a feature branch.codebase-insightWhen the user wants to deeply understand a codebase, map its architecture, or build a persistent mental model for future sessions.context-compressionWhen conversation context is getting long, when approaching token limits, when the user says "compress," "summarize context," "too long," "running out of…coordinator-modeWhen the user has a complex task that would benefit from multiple agents working in parallel or in sequence.effort-estimateWhen the user needs accurate effort estimates for tasks, features, or projects.frustration-awareWhen the user shows signs of frustration, impatience, or dissatisfaction. Also use proactively to calibrate tone.kairos-sessionWhen starting or ending a work session, or when context files need maintenance.magic-docsWhen the user wants to generate documentation from their codebase.pr-autofixWhen the user has PR review feedback to address, CI failures to fix, or wants to automatically resolve common PR issues.prompt-speculationUse proactively after completing any task to suggest logical next steps.security-reviewWhen the user wants a security audit, vulnerability assessment, or security hardening of their codebase.session-reviewWhen ending a work session and wanting to capture what was accomplished, what was learned, and what to do next.stuck-recoveryWhen you or the user are going in circles, stuck on a problem, or repeating failed approaches.thinkbackWhen the user wants to review past decisions, understand why something was built a certain way, audit decision quality, or learn from past reasoning.ultraplanWhen the user needs to plan a complex feature, system, or project that requires deep creative exploration before execution.undercover-modeWhen contributing to public or open-source repositories where AI attribution should be hidden.