ワンクリックで
deepwork-jobslearn
Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Calculate current allocation percentages, identify drift from targets, analyze margin efficiency
Gather current portfolio positions, values, and prices from Robinhood using bin/robinhood CLI
Create specific rebalancing recommendations based on drift analysis
Compile comprehensive human-readable daily report with all analysis and recommendations
Daily Permanent Portfolio analysis with allocation drift and rebalancing recommendations
Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow.
| name | deepwork_jobs.learn |
| description | Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it. |
| hooks | {"Stop":[{"hooks":[{"type":"prompt","prompt":"You must evaluate whether Claude has met all the below quality criteria for the request.\n\n## Quality Criteria\n\n1. **Conversation Analyzed**: Did the agent review the conversation for DeepWork job executions?\n2. **Confusion Identified**: Did the agent identify points of confusion, errors, or inefficiencies?\n3. **Instructions Improved**: Were job instructions updated to address identified issues?\n4. **Instructions Concise**: Are instructions free of redundancy and unnecessary verbosity?\n5. **Shared Content Extracted**: Is lengthy/duplicated content extracted into referenced files?\n6. **doc spec Reviewed (if applicable)**: For jobs with doc spec outputs, were doc spec-related learnings identified?\n7. **doc spec Updated (if applicable)**: Were doc spec files updated with improved quality criteria or structure?\n8. **Bespoke Learnings Captured**: Were run-specific learnings added to AGENTS.md?\n9. **File References Used**: Do AGENTS.md entries reference other files where appropriate?\n10. **Working Folder Correct**: Is AGENTS.md in the correct working folder for the job?\n11. **Generalizable Separated**: Are generalizable improvements in instructions, not AGENTS.md?\n12. **Sync Complete**: Has `deepwork sync` been run if instructions were modified?\n\n## Instructions\n\nReview the conversation and determine if ALL quality criteria above have been satisfied.\nLook for evidence that each criterion has been addressed.\n\nIf the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response OR\nall criteria appear to be met, respond with: {\"ok\": true}\n\nIf criteria are NOT met AND the promise tag is missing, respond with:\n{\"ok\": false, \"reason\": \"**AGENT: TAKE ACTION** - [which criteria failed and why]\"}\n"}]}],"SubagentStop":[{"hooks":[{"type":"prompt","prompt":"You must evaluate whether Claude has met all the below quality criteria for the request.\n\n## Quality Criteria\n\n1. **Conversation Analyzed**: Did the agent review the conversation for DeepWork job executions?\n2. **Confusion Identified**: Did the agent identify points of confusion, errors, or inefficiencies?\n3. **Instructions Improved**: Were job instructions updated to address identified issues?\n4. **Instructions Concise**: Are instructions free of redundancy and unnecessary verbosity?\n5. **Shared Content Extracted**: Is lengthy/duplicated content extracted into referenced files?\n6. **doc spec Reviewed (if applicable)**: For jobs with doc spec outputs, were doc spec-related learnings identified?\n7. **doc spec Updated (if applicable)**: Were doc spec files updated with improved quality criteria or structure?\n8. **Bespoke Learnings Captured**: Were run-specific learnings added to AGENTS.md?\n9. **File References Used**: Do AGENTS.md entries reference other files where appropriate?\n10. **Working Folder Correct**: Is AGENTS.md in the correct working folder for the job?\n11. **Generalizable Separated**: Are generalizable improvements in instructions, not AGENTS.md?\n12. **Sync Complete**: Has `deepwork sync` been run if instructions were modified?\n\n## Instructions\n\nReview the conversation and determine if ALL quality criteria above have been satisfied.\nLook for evidence that each criterion has been addressed.\n\nIf the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response OR\nall criteria appear to be met, respond with: {\"ok\": true}\n\nIf criteria are NOT met AND the promise tag is missing, respond with:\n{\"ok\": false, \"reason\": \"**AGENT: TAKE ACTION** - [which criteria failed and why]\"}\n"}]}]} |
Standalone skill - can be run anytime
Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.
Goal: Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.
Think deeply about this task. Reflect on the current conversation to identify learnings from DeepWork job executions, improve job instructions with generalizable insights, and capture bespoke (run-specific) learnings in AGENTS.md files in the deepest common folder that would contain all work on the topic in the future.
Analyze the conversation history to extract learnings and improvements, then apply them appropriately:
Scan the conversation for DeepWork slash commands that were run
/job_name.step_idIdentify the target folder
git diff to see where changes were made on the branchIf no job was specified, ask the user:
.deepwork/jobs/Review the conversation for:
Confusion signals
Inefficiency signals
Error patterns
Success patterns
For each learning identified, determine if it is:
Generalizable (should improve instructions):
doc spec-Related (should improve doc spec files):
Bespoke (should go in AGENTS.md):
src/api/"config/settings.yml"Review the conversation for doc spec-related improvements:
Quality Criteria Changes
Document Structure Changes
Metadata Updates
Signals for doc spec improvements:
For each generalizable learning:
Locate the instruction file
.deepwork/jobs/[job_name]/steps/[step_id].mdMake targeted improvements
Keep instructions concise
Preserve instruction structure
Track changes for changelog
Review all instruction files for the job and identify content that:
Extract to shared files:
Create shared files in .deepwork/jobs/[job_name]/steps/shared/
conventions.md - Coding/formatting conventions used across stepsexamples.md - Common examples referenced by multiple stepsschemas.md - Data structures or formats used throughoutReference from instructions using markdown includes or explicit references:
## Conventions
Follow the conventions defined in `shared/conventions.md`.
Benefits of extraction:
If doc spec-related learnings were identified:
Locate the doc spec file
doc_spec: .deepwork/doc_specs/[doc_spec_name].md).deepwork/doc_specs/[doc_spec_name].mdUpdate quality_criteria array
Update example document
Update metadata as needed
Example doc spec update:
# Before
quality_criteria:
- name: Visualization
description: Include charts
# After
quality_criteria:
- name: Visualization
description: Include Mermaid.js charts showing spend breakdown by service and month-over-month trend
The AGENTS.md file captures project-specific knowledge that helps future agent runs.
Determine the correct location
Use file references where possible
path/to/file.ext for [description]"AGENTS.md structure: See .deepwork/jobs/deepwork_jobs/templates/agents.md.template for the standard format.
Writing entries
file.ext:42If instruction files were modified:
Bump version in job.yml
Add changelog entry
- version: "[new_version]"
changes: "Improved [step] instructions based on execution learnings: [brief description]"
Run deepwork sync (if instructions were modified)
deepwork sync
If skills were regenerated, look at the "To use the new skills" section in the deepwork sync output and relay these exact reload instructions to the user (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code)
When adding entries to AGENTS.md, prefer these patterns:
Good (references):
- API endpoints follow REST conventions. See `src/api/routes.ts` for examples.
- Error handling pattern: See `src/utils/errors.ts:15-30`
- Configuration schema: Defined in `config/schema.json`
Avoid (duplicating):
- API endpoints should return JSON with this format: { status: ..., data: ... }
- Error handling should use try/catch with custom error classes
- Configuration requires these fields: name, version, ...
<promise>✓ Quality Criteria Met</promise>User: /deepwork_jobs.learn
Claude: I'll analyze this conversation for learnings from DeepWork job executions.
**Conversation Analysis**
I found the following job executions:
1. `/competitive_research.identify_competitors` - Completed
2. `/competitive_research.research_competitors` - Completed with 2 iterations
3. `/competitive_research.comparative_analysis` - Completed
**Identified Issues**
1. **Confusion in step 2**: The instructions didn't specify that competitor research should include pricing information. This caused an extra iteration.
2. **Missing context**: The agent had to ask about the industry focus, which should have been carried forward from step 1.
**Classification**
- Generalizable: Add pricing to research requirements in instructions
- Bespoke: This project focuses on B2B SaaS in the HR tech space
**Actions Taken**
1. Updated `.deepwork/jobs/competitive_research/steps/research_competitors.md`:
- Added "Include pricing information (tiers, models, approximate ranges)" to research requirements
- Added note about carrying forward industry context from previous step
2. Created `./competitive_research_output/AGENTS.md`:
```markdown
# Project Context for Competitive Research
## Job-Specific Context
### competitive_research
#### Industry Focus
- Domain: B2B SaaS, HR Technology sector
- See `identify_competitors_output.md` for market definition
#### Competitors Identified
- Reference: `competitor_list.md` for full details
## Last Updated
- Date: 2024-01-15
- From conversation about: Initial competitive analysis run
Updated job.yml version to 1.0.1 with changelog entry
Ran deepwork sync
Summary
Updated job instructions and created AGENTS.md with bespoke learnings. To get the updated skills, type 'exit' then run 'claude --resume'.
## Handling Edge Cases
**No job executions found**:
- Ask user which job they'd like to analyze
- Or offer to review available jobs
**Multiple jobs executed**:
- Analyze each job separately
- Create separate AGENTS.md entries or files as appropriate
**AGENTS.md already exists**:
- Read existing content
- Append new learnings to appropriate sections
- Update "Last Updated" section
**No issues found**:
- Document what worked well
- Consider if any successful patterns should be added to instructions as examples
**Sensitive information**:
- Never include secrets, credentials, or PII in AGENTS.md
- Reference config files instead of including values
### Job Context
Core commands for managing DeepWork jobs. These commands help you define new multi-step
workflows and learn from running them.
The `define` command guides you through an interactive process to create a new job by
asking structured questions about your workflow, understanding each step's inputs and outputs,
and generating all necessary files.
The `learn` command reflects on conversations where DeepWork jobs were run, identifies
confusion or inefficiencies, and improves job instructions. It also captures bespoke
learnings specific to the current run into AGENTS.md files in the working folder.
## Required Inputs
**User Parameters** - Gather from user before starting:
- **job_name**: Name of the job that was run (optional - will auto-detect from conversation)
## Work Branch
Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD`
- If on a matching work branch: continue using it
- If on main/master: create new branch with `git checkout -b deepwork/deepwork_jobs-[instance]-$(date +%Y%m%d)`
## Outputs
**Required outputs**:
- `AGENTS.md`
## Guardrails
- Do NOT skip prerequisite verification if this step has dependencies
- Do NOT produce partial outputs; complete all required outputs before finishing
- Do NOT proceed without required inputs; ask the user if any are missing
- Do NOT modify files outside the scope of this step's defined outputs
## Quality Validation
Stop hooks will automatically validate your work. The loop continues until all criteria pass.
**Criteria (all must be satisfied)**:
1. **Conversation Analyzed**: Did the agent review the conversation for DeepWork job executions?
2. **Confusion Identified**: Did the agent identify points of confusion, errors, or inefficiencies?
3. **Instructions Improved**: Were job instructions updated to address identified issues?
4. **Instructions Concise**: Are instructions free of redundancy and unnecessary verbosity?
5. **Shared Content Extracted**: Is lengthy/duplicated content extracted into referenced files?
6. **doc spec Reviewed (if applicable)**: For jobs with doc spec outputs, were doc spec-related learnings identified?
7. **doc spec Updated (if applicable)**: Were doc spec files updated with improved quality criteria or structure?
8. **Bespoke Learnings Captured**: Were run-specific learnings added to AGENTS.md?
9. **File References Used**: Do AGENTS.md entries reference other files where appropriate?
10. **Working Folder Correct**: Is AGENTS.md in the correct working folder for the job?
11. **Generalizable Separated**: Are generalizable improvements in instructions, not AGENTS.md?
12. **Sync Complete**: Has `deepwork sync` been run if instructions were modified?
**To complete**: Include `<promise>✓ Quality Criteria Met</promise>` in your final response only after verifying ALL criteria are satisfied.
## On Completion
1. Verify outputs are created
2. Inform user: "learn complete, outputs: AGENTS.md"
This standalone skill can be re-run anytime.
---
**Reference files**: `.deepwork/jobs/deepwork_jobs/job.yml`, `.deepwork/jobs/deepwork_jobs/steps/learn.md`