Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".
git clone https://github.com/rohitg00/pro-workflow.git--- name: replay-learnings description: Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about". --- # Replay Learnings Like muscle memory for your coding sessions. Find and surface relevant learnings before you start working. ## Trigger Use when starting a new task, saying "what do I know about", "before I start", "replay", or "remind me about". ## Workflow 1. Extract keywords from the task description (e.g. "auth refactor" → `auth`, `middleware`, `refactor`). 2. Search learnings/memory for matching patterns: ```bash grep -i "auth\|middleware" .claude/LEARNED.md 2>/dev/null grep -i "auth\|middleware" .claude/learning-log.md 2>/dev/null grep -A2 "\[LEARN\]" CLAUDE.md | grep -i "auth\|middleware" ``` 3. Check session history for similar work — what was the correction rate? 4. Surface the top learnings ranked by relevance. 5. If no learnings found, suggest starting with the scout agent to explore first. ## Output ``` REPLAY BRIEFING: <task> ======================= Past learnings (ranked by relevance): 1. [Testing] Always mock external APIs in auth tests (applied 8x) Mistake: Called live API in tests, caused flaky failures 2. [Navigation] Auth middleware is in src/middleware/ not src/auth/ (applied 5x) 3. [Quality] Add error boundary around auth state changes (applied 3x) Session history for similar work: - 2026-02-01: auth refactor — 23 edits, 2 corrections (8.7% rate) - 2026-01-28: auth middleware — 15 edits, 4 corrections (26.7% rate) ^ Higher correction rate — review patterns before starting Suggested approach: - Mock external APIs (learning #1) - Check src/middleware/ first for auth code (learning #2) ``` ## Guardrails - Rank by relevance, not recency. - Include the original mistake context so the learning is actionable. - Flag high correction-rate sessions as areas requiring extra care. - If no learnings match, say so explicitly rather than forcing irrelevant results.
["Identify the specific task or project you're about to start and replace [TASK_DESCRIPTION] with a clear description (e.g., 'planning the Q3 marketing campaign for our new eco-friendly product line').","Specify the types of mistakes or learning areas to focus on by replacing [SPECIFIC_MISTAKE_TYPE], [KEY_LEARNING_AREA], and [CONTEXTUAL_FACTOR] with relevant keywords (e.g., 'audience segmentation', 'customer engagement patterns', 'sustainability messaging').","Set the timeframe for prioritizing recent learnings by replacing [TIMEFRAME] with a period like '12 months' or 'last quarter'.","Review the summarized lessons and actionable takeaways, then adjust your approach to incorporate these insights before proceeding with the task.","For best results, combine this skill with a quick review of recent correction history or project post-mortems. Tools like Notion, Confluence, or your company's internal wiki work well for this."]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/rohitg00/pro-workflow/tree/main/skills/replay-learningsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Before starting [TASK_DESCRIPTION], search our internal knowledge base, correction history, and past project archives for relevant learnings. Focus on: (1) [SPECIFIC_MISTAKE_TYPE] from similar past projects, (2) [KEY_LEARNING_AREA] patterns that emerged, and (3) [CONTEXTUAL_FACTOR] that influenced outcomes. Summarize the top 3 most relevant lessons with actionable takeaways. Prioritize learnings from the last [TIMEFRAME] where possible.
Before diving into the Q3 marketing campaign strategy for our new eco-friendly product line, I pulled up our correction history from the last 6 months and found three critical lessons that directly apply to this initiative:
First, the 2023 'GreenHome Launch' campaign failed to segment our audience properly, leading to a 40% lower engagement rate among Gen Z consumers. The post-mortem revealed we assumed eco-consciousness correlated with age, when in reality, our most engaged segment was actually 25-34 year old professionals with moderate incomes. For this campaign, I recommend segmenting by values (prioritizing sustainability) rather than demographics, with tailored messaging for each vertical.
Second, our 'Sustainable Packaging' project last quarter showed that customers respond 2.3x better to concrete impact statements ('This saves 120 gallons of water') than vague claims ('We're eco-friendly'). The campaign materials should include specific environmental benefits for each product variant.
Third, the 'EcoCart' initiative revealed that our discount structure was too complex for customers to understand quickly. Simplifying the tiered discount system to a single 'save 15% when you choose sustainable options' message increased conversion by 28%. For this campaign, we should present the sustainability premium as a clear value-add rather than a separate cost.
These lessons suggest we should: 1) Create 3 distinct audience personas based on sustainability values rather than age, 2) Include specific environmental impact metrics in all campaign materials, and 3) Simplify the value proposition to focus on the sustainability benefit as the primary differentiator. The GreenHome campaign's failure to segment properly cost us $1.2M in potential sales - let's not repeat that mistake.skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan