Skip to content

hoavdc/CodexKit / skills/codexkit-report-summarizer

codexkit-report-summarizer

Verified

Condense long reports, documents, or data exports into structured summaries with key findings, implications, and recommended actions. Use when the work is distilling dense content for busy readers. Do not use for original analysis, strategy formulation, or when the source material needs expert interpretation beyond summarization.

FileKindSize
SKILL.mdskill md3.9 KB
agents/openai.yamlconfig174 B
examples/common-mistakes.mdmarkdown894 B
examples/good-output.mdmarkdown1.5 KB
verification/checklist.mdmarkdown1.4 KB

verification/checklist.md

View on GitHub
# 4C Verification Checklist - Report Summarizer

Use this checklist after producing a report summary.

## Correctness - Is it right?

- [ ] Key findings, numbers, dates, names, and recommendations match the source.
- [ ] No claim is added unless clearly labeled as inference.
- [ ] The source's confidence level, caveats, and limitations are preserved.
- [ ] Technical terms are not simplified into something inaccurate.

## Completeness - Is it done?

- [ ] The source purpose, thesis, findings, implications, and actions are covered.
- [ ] Major sections are represented or explicitly marked as omitted.
- [ ] Decisions requested from the reader are captured.
- [ ] Follow-up questions or missing information are listed.

## Context-fit - Does it match?

- [ ] Summary length matches the user's requested format.
- [ ] Detail level matches the reader's role.
- [ ] The summary leads with what the reader needs to know first.
- [ ] The output preserves enough context to prevent misleading shortcuts.

## Consequence - Is it safe to use?

- [ ] What could go wrong if the reader acts without opening the source?
- [ ] Are compliance, legal, financial, or safety-sensitive sections flagged for review?
- [ ] Are omitted sections low-risk enough to omit?
- [ ] Could the summary overstate certainty or hide uncertainty?

Final check: list one point the reader should verify in the original report.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall