Skills remembering-conversations
๐Ÿ“ฆ

remembering-conversations

Content revision r1 Medium Risk ๐Ÿ“ Filesystem accessโš™๏ธ External commands

Recall Past Development Decisions

Teams lose time when prior decisions and fixes are buried in old chats. This skill searches archived conversations and returns concise, sourced guidance.

Supports: Claude Codex Code(CC)
๐Ÿ“Š 70 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "remembering-conversations" from https://skillstore.io/skills/remembering-conversations.md and its manifest at https://skillstore.io/api/skills/remembering-conversations/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.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "remembering-conversations". Search for prior discussion about React Router authentication errors.

Expected outcome:

Found two relevant conversations. The earlier fix moved auth checks into the loader and kept redirect logic close to route ownership.

Using "remembering-conversations". What did we decide about the database migration strategy last time?

Expected outcome:

The prior decision favored a staged migration with compatibility writes first. The main risk was inconsistent reads during rollout.

Using "remembering-conversations". Find lessons from the last deployment failure.

Expected outcome:

The strongest lesson was to verify environment variables before release. The conversation also recommended adding a preflight check.

Security Audit

Medium Risk
v4 โ€ข 7/5/2026 Open versioned report

Most Ruby shell and reconnaissance detections are false positives from Markdown backticks and ordinary prose. I confirmed medium privacy risk from accessing hidden conversation archives and added a semantic finding for possible exposure of prior conversation content. No prompt injection attempt was found.

2
Files scanned
204
Lines analyzed
2
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
Conversation History Exposure
The skill requires a search agent for historical searches and directs it to read top results and synthesize sources. MCP documentation shows full conversation reads by path, so prior conversations may be exposed in new contexts.
The stated purpose and tool reference both confirm retrieval of archived conversations. The risk depends on deployment scope and consent controls, so confidence is high but not absolute.
Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
Hidden file access
path: "/Users/name/.config/superpowers/conversation-archive/project/uuid.jsonl"
The documented read path targets a hidden conversation archive under .config, which can contain private project and user data. It is a legitimate memory feature, but it is still privacy-sensitive local file access.
Medium
Hidden file access
path: "/Users/name/.config/superpowers/conversation-archive/project/uuid.jsonl",
The range-read example uses the same hidden conversation archive path and encourages reading selected lines. Scope is bounded to examples, but archived conversations can contain secrets or confidential context.
Audited by: codex View Audit History โ†’
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/remembering-conversations/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/remembering-conversations/security.svg)](https://skillstore.io/skills/remembering-conversations?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/remembering-conversations?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/remembering-conversations/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/remembering-conversations.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA ยท BibTeX ยท CFF)

APA citation

obra. (2026). remembering-conversations security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/remembering-conversations/audits/4

BibTeX citation

@techreport{obra-remembering-conversations-2026, author = {obra}, title = {remembering-conversations security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/remembering-conversations/audits/4}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "remembering-conversations security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "obra" date-released: "2026-07-05" url: "https://skillstore.io/skills/remembering-conversations/audits/4" identifiers: - type: other value: "skillstore:remembering-conversations:audit:4" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
obra Recommended Current

remembering-conversations

Skillstore Score 70
Evidence Confidence High
Skillstore usage 16
Updated

2026-08-21

obra-remembering-conversations

Skillstore Score 69
Evidence Confidence High
Skillstore usage 13
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
91
Spec Compliance

What You Can Build

Recover Prior Rationale

Find why a feature, architecture, or workaround was chosen in an earlier conversation.

Resume Complex Work

Locate previous investigation notes before continuing a migration, bug fix, or refactor.

Standardize Team Practice

Reuse known patterns and avoid repeating mistakes from past project conversations.

Try These Prompts

Find A Past Decision
Search past conversations for why we chose the current authentication approach. Summarize the decision, tradeoffs, and source conversations.
Resume A Prior Fix
Search memory for the last time we fixed this error. Return the root cause, files discussed, and the recommended next step.
Compare Similar Work
Search archived conversations for similar migrations. Compare patterns, risks, and lessons that apply to this repository.
Build A Sourced Plan
After reviewing this codebase, search memory for prior billing event migrations. Produce a plan with cited decisions, risks, and open questions.

Best Practices

  • Inspect the current repository before searching old conversations.
  • Use narrow queries that name the feature, error, or decision.
  • Read only the result ranges needed for the current task.

Avoid

  • Searching memory before understanding the current user request.
  • Reading entire archived conversations when summaries are enough.
  • Using historical decisions as authority without checking current code.

Frequently Asked Questions

What does this skill search?
It searches archived Claude Code conversations through the episodic-memory MCP plugin.
Does it read my current repository?
No. It is for past conversations, not live codebase structure.
When should I use it?
Use it after understanding the task when past decisions or similar work may help.
Can it expose sensitive information?
Yes. Archived conversations may contain secrets, private plans, or customer details.
Does it work without MCP tools?
No. It depends on the episodic-memory MCP tools and indexed conversation archives.
How should results be used?
Treat results as context. Verify them against current files, requirements, and user intent.

Developer Details

Author

obra

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Ref

62e2a730c5cd74eab4c7164309d810de660fcea3

Maintenance freshness

7/18/2026

Usage

13 downloads ยท 166 views

File structure

๐Ÿ“„ MCP-TOOLS.md

๐Ÿ“„ SKILL.md