Retrospective workflow to evaluate the most recent command/session slice and drive improvements to workflow assets (skills, agents, commands, hooks). Triggers: fix workflow, workflow improvement, retrospective, session analysis, workflow efficiency, command optimization, skill improvement, hook refinement Use when: execution felt slow, confusing, repetitive, or fragile, workflow assets need improvement, analyzing recent session for optimization opportunities DO NOT use when: implementing features - focus on feature work first. DO NOT use when: the issue is user error rather than workflow design. Improves the workflow assets themselves, not the feature work.
/plugin marketplace add athola/claude-night-market/plugin install pensive@claude-night-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Use this skill after running a command or completing a short session slice where execution felt slow, confusing, repetitive, or fragile.
This skill focuses on improving the workflow assets (skills, agents, commands, hooks) that were involved, not on feature work itself.
fix-workflow:slice-capturedfix-workflow:workflow-recreatedfix-workflow:improvements-generatedfix-workflow:plan-agreedfix-workflow:changes-implementedfix-workflow:validatedslice-captured)Identify the most recent command or session slice in the current context window and capture:
/command if present)If the slice is ambiguous, pick the most recent complete attempt and state the exact boundary you chose.
workflow-recreated)Reconstruct the workflow as a numbered list of steps (5–20 steps):
Also record friction points:
improvements-generated)Generate 3–5 distinct improvement approaches and score each on:
Prefer small, high-leverage changes:
plan-agreed)Choose 1 approach and define:
Keep the plan bounded: aim for ≤ 5 files changed unless the workflow truly spans more.
changes-implemented)Apply changes following sanctum conventions:
commands/, agents/, skills/, hooks/plugins/sanctum/tests/validated)Validation should include at least 2 of:
Record the before/after comparison as metrics, not prose:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.