Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to workspace/learnings.jsonl. Don't use for analyzing source code or writing patches.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionmantis-reflectExecute the skills CLI command in your project's root directory to begin installation:
Fetches mantis-reflect from google/mantis and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate mantis-reflect. Access via /mantis-reflect in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
307
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
307
stars
| name | mantis-reflect |
| description | >- Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to workspace/learnings.jsonl. Don't use for analyzing source code or writing patches. |
Execution Trajectory Analyst. Analyzes the sequence of thoughts, tool calls, and observations (the "trajectory" or "conversation") of the other Mantis agents. Extracts valuable insights to prevent future agents from making the same mistakes.
/mantis-reflectworkspace/learnings.jsonl.workspace/.mantis_state.json (to track current loop pass).transcript.jsonl or conversation.jsonl (execution logs from the
current round's subagents).workspace/learnings.jsonl.workspace/learnings.jsonl. It should check existing lines
in workspace/learnings.jsonl to ensure it doesn't duplicate the same
insight if retried.Analyze the execution trajectories of the mantis-researcher, mantis-critic,
and mantis-patch agents from the current round to distill what went right and
what went wrong.
Execute the reflection stage as follows:
Extract Trajectories (Token Optimization):
transcript.jsonl or
conversation.jsonl files natively with read_file, as they can be
massive and blow out your context window.jq/grep to
extract key events: tool error messages, final agent summaries,
instances where an agent "gave up", or messages indicating a trust
boundary assumption was incorrect.Synthesize Insights: Review the extracted events. Look for:
Append to the Inbox (workspace/learnings.jsonl): For each distinct
insight, append a structured JSON object to workspace/learnings.jsonl.
workspace/learnings.jsonl){"type": "trajectory_insight", "action": "add | update | remove", "target_entity": "[e.g., auth_module.py or sandbox_env]", "insight": "The researcher assumed input was unsanitized, but it is actually cleansed by the middleware. Do not attempt XSS on this parameter.", "source_stage": "mantis-researcher"}
Ensure the file is appended to, not overwritten. When complete, notify the user.
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
Registry listing for mantis-reflect matched our evaluation — installs cleanly and behaves as described in the markdown.
mantis-reflect fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Keeps context tight: mantis-reflect is the kind of skill you can hand to a new teammate without a long onboarding doc.
mantis-reflect reduced setup friction for our internal harness; good balance of opinion and flexibility.
mantis-reflect has been reliable in day-to-day use. Documentation quality is above average for community skills.
mantis-reflect is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
mantis-reflect reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend mantis-reflect for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
mantis-reflect has been reliable in day-to-day use. Documentation quality is above average for community skills.
Useful defaults in mantis-reflect — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
showing 1-10 of 69