Do not add features, refactor, or improve beyond what was asked
Langue du texte source : anglais
Menu
Skills dans ce dépôt
SkillsMP a collecté 507 skills depuis Lord1Egypt/ai-skillforge. Ouvrez un skill pour examiner sa source et ses détails.
Lord1Egypt/ai-skillforgeAffichage de 40 skills collectés sur 507.
Do not add features, refactor, or improve beyond what was asked
Langue du texte source : anglais
Do not add error handling for impossible scenarios; only validate at boundaries
Langue du texte source : anglais
Avoid introducing security vulnerabilities like injection, XSS, etc.
Langue du texte source : anglais
Users primarily request software engineering tasks; interpret instructions in that context
Langue du texte source : anglais
Instructs dream memory consolidation to reconcile feedback and project memories against CLAUDE.md, deleting stale memories or flagging possible CLAUDE.md drift
Langue du texte source : anglais
Instructions for handling shared team memories during dream consolidation, including deduplication, conservative pruning rules, and avoiding accidental promotion of personal memories
Langue du texte source : anglais
Instructs Claude to avoid using emojis unless the user explicitly asks for them
Langue du texte source : anglais
Instructions for executing actions carefully.
Langue du texte source : anglais
Instructs Claude to respond to open-ended questions with analysis, options, and tradeoffs instead of jumping to implementation, waiting for user agreement before writing code
Langue du texte source : anglais
Instructions for when to fork subagents and rules against reading fork output mid-flight or fabricating fork results
Langue du texte source : anglais
Requires Claude to start the dev server and verify UI or frontend changes in a browser before reporting completion
Langue du texte source : anglais
System prompt for displaying the current git status at the start of the conversation
Langue du texte source : anglais
Core interactive-agent identity and harness instructions for terminal markdown output, permissions, system reminders, compaction, tool use, and code references
Langue du texte source : anglais
System prompt for hooks configuration. Used for above Claude Code config skill.
Langue du texte source : anglais
Instructions for using the SendUserMessage tool
Langue du texte source : anglais
Generates a concise 4-part summary (what's working, hindrances, quick wins, ambitious workflows) for the insights report
Langue du texte source : anglais
Analyzes aggregated usage data to identify friction patterns and categorize recurring issues
Langue du texte source : anglais
Identifies ambitious future workflows and opportunities for autonomous AI-assisted development
Langue du texte source : anglais
Extracts structured facets (goal categories, satisfaction, friction) from a single Claude Code session transcript
Langue du texte source : anglais
Generates actionable suggestions including CLAUDE.md additions, features to try, and usage patterns
Langue du texte source : anglais
Instructions for providing educational insights when learning mode is active
Langue du texte source : anglais
Main system prompt for learning mode with human collaboration instructions
Langue du texte source : anglais
Describes the purpose and guidelines for per-user memory files that accumulate details about the user's role, goals, knowledge, and preferences across sessions
Langue du texte source : anglais
Describes the user feedback memory type that stores guidance about work approaches, emphasizing recording both successes and failures and checking for contradictions with team memories
Langue du texte source : anglais
Instructions for using persistent file-based memory, including memory file format, scope, indexing, and stale-memory handling
Langue du texte source : anglais
Lists categories of information that should not be saved in memory, even when the user asks
Langue du texte source : anglais
Instructs the agent to verify memory records against current file/resource state and delete stale memories that conflict with observed reality
Langue du texte source : anglais
Describes the behavior and constraints of minimal mode, which skips hooks, LSP, plugins, auto-memory, and other features while requiring explicit context via CLI flags
Langue du texte source : anglais
One of the six rules for using the sleep command.
Langue du texte source : anglais
System prompt for previewing UI options in a side-by-side layout
Langue du texte source : anglais
Instructs Claude to keep user-facing updates readable and outcome-first, answer directly after work completes, match response format to task complexity, and limit code comments to non-obvious constraints
Langue du texte source : anglais
System prompt for telling Claude to using parallel tool calls
Langue du texte source : anglais
Instructions on how to compact when the user decided to compact only a portion of the conversation, with a structured summary format and analysis process
Langue du texte source : anglais
Phase four of plan mode.
Langue du texte source : anglais
System prompt for providing information about Windows PowerShell 5.1
Langue du texte source : anglais
Instructs Claude to prefer editing existing files instead of creating new ones
Langue du texte source : anglais
System reminder injected during remote planning sessions that instructs Claude to explore the codebase, produce a diagram-rich plan via ExitPlanMode, and implement it with a pull request upon approval
Langue du texte source : anglais
System reminder that configures a remote planning session to explore the codebase, produce an implementation plan via ExitPlanMode, and handle plan approval, rejection, or teleportation back to the user's local terminal
Langue du texte source : anglais
Instructs Claude on how to use the REPL tool effectively with dense JavaScript scripts, shorthands, batching rules, and API reference for investigation tasks
Langue du texte source : anglais
Instructions for using a dedicated scratchpad directory for temporary files
Langue du texte source : anglais