Diagnose Superpowers Session Failures
Coding-agent sessions can waste time without showing where behavior diverged. This skill analyzes transcripts and produces cited reports for review or issue filing.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "diagnosing-superpowers" from https://skillstore.io/skills/obra-diagnosing-superpowers.md and its manifest at https://skillstore.io/api/skills/obra-diagnosing-superpowers/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "diagnosing-superpowers". Why did session abc123 repeat the same file reads?
Expected outcome:
A repeated-work report listing grouped reads, intervening changes, turn ranges, evidence lines, and confidence for each finding.
Using "diagnosing-superpowers". Why was this session expensive and slow?
Expected outcome:
A cost summary covering supported token totals, longest turns, idle gaps, large tool results, compactions, and associated sessions.
Using "diagnosing-superpowers". Prepare a report for the Superpowers maintainers.
Expected outcome:
A cited diagnosis, related-issue results, an approved issue draft, and an optional scrubbed bundle with privacy limitations.
All 44 static alerts are false positives caused by Markdown, templates, defensive redaction guidance, or bounded GitHub documentation. No prompt injection, credential access, arbitrary command execution, or unauthorized network destination was found. The workflow protects sensitive transcripts through read-only source handling, approval gates, redaction, and user review before sharing.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/obra-diagnosing-superpowers/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/obra-diagnosing-superpowers?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/obra-diagnosing-superpowers?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/obra-diagnosing-superpowers/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/obra-diagnosing-superpowers.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>obra. (2026). diagnosing-superpowers security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/obra-diagnosing-superpowers/audits/1@techreport{obra-obra-diagnosing-superpowers-2026,
author = {obra},
title = {diagnosing-superpowers security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/obra-diagnosing-superpowers/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "diagnosing-superpowers security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "obra"
date-released: "2026-09-24"
url: "https://skillstore.io/skills/obra-diagnosing-superpowers/audits/1"
identifiers:
- type: other
value: "skillstore:obra-diagnosing-superpowers:audit:1"
description: "Skillstore immutable audit report identifier"
Trace repeated commands, plan drift, errors, and unsupported completion claims in one coding session.
Measure supported token use, long turns, idle gaps, large tool results, and subagent activity.
Create a cited report, search related issues, and prepare a scrubbed bundle after approval.
Diagnose this session: [session ID or path]. I expected [result], but observed [problem]. Focus on [observable].
Review [session] for repeated reads, edits, commands, searches, or decisions. Explain what changed between repetitions and cite every finding.
Analyze [session] for supported token use, longest turns, idle gaps, large tool results, compactions, and associated-session costs.
Prepare a Superpowers bug report for [session]. Search related issues, draft exact text, and offer a redacted evidence bundle for approval.
Author
obraLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
2aa351cb09c29b7287d263bd8ea81e9bee3b2a61
Maintenance freshness
9/30/2026
Usage
0 downloads · 0 views
Create Detailed Implementation Plans
Complex work is risky when requirements are not broken into clear steps. This skill turns specs into test-focused implementation plans for Claude, Codex, and Claude Code.
Build Tested AI Skills
AI skills can fail when instructions are vague or untested. This skill guides test-driven skill writing with pressure scenarios and verification loops.
Execute Implementation Plans with Checkpoints
Implementation plans can lose focus when work moves into a separate AI session. This skill guides Claude, Codex, and Claude Code through batch execution, verification, and review checkpoints.
Evaluate Code Review Feedback
Code review feedback can be unclear, incorrect, or incomplete. This skill helps Claude, Codex, and Claude Code verify suggestions, ask precise questions, and implement reviewed changes carefully.
Plan Features Through Guided Brainstorming
Feature ideas often move to implementation before goals and constraints are clear. This skill guides Claude, Codex, and Claude Code through questions, trade-offs, and validated design notes.
Execute Plans with Subagent Reviews
Complex implementation plans lose quality when one context handles every task. This skill coordinates fresh subagents for implementation, spec checks, and code quality reviews.
Debug Errors and Root Causes
by 89jobrien
Errors and incidents are hard to triage when evidence is spread across logs, stack traces, and services. This skill structures diagnosis, parses logs, identifies patterns, and guides minimal fixes.
Find Code Context Faster
by 89jobrien
Developers often lose time tracing why code exists and what depends on it. This skill prompts Claude, Codex, or Claude Code to gather related graph knowledge, callers, imports, and tests before changes.
Debug Technical Failures Systematically
by Asmayaseen
Quick fixes often hide the real cause and create regressions. This skill structures investigation, hypothesis testing, implementation, and verification around collected evidence.
Diagnose Context Degradation in AI Agents
by ChakshuGautam
Long conversations and large prompts can make AI agents lose important information or follow conflicting context. This skill helps Claude, Codex, and Claude Code identify degradation patterns and choose mitigation strategies.
Teach Code by Building Apps
by Emz1998
Learning code can feel abstract when examples are disconnected from real projects. This skill teaches concepts while building working applications step by step.
Diagnose Deep Learning Failures Safely
by lllllllama
Deep learning failures can invite risky, premature changes. This skill classifies concrete errors and prepares conservative guidance before any code modification.