Recall Past Conversations
Past decisions and fixes can be hard to find during active work. This skill searches conversation history so Claude, Codex, or Claude Code can reuse prior context.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "remembering-conversations" from https://skillstore.io/skills/obra-remembering-conversations.md and its manifest at https://skillstore.io/api/skills/obra-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.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "remembering-conversations". How should we handle auth redirects? We discussed this before.
Expected outcome:
The skill searches memory for the prior auth redirect discussion, then returns the earlier decision, tradeoffs, and source conversations.
Using "remembering-conversations". I am stuck on the release workflow. Check whether we solved this before.
Expected outcome:
The skill looks for matching release workflow conversations and summarizes previous blockers, successful steps, and remaining cautions.
Using "remembering-conversations". Before changing the caching layer, find our past reasoning about it.
Expected outcome:
The skill retrieves relevant caching discussions and separates confirmed historical decisions from items that need current verification.
The shell execution and system reconnaissance alerts are false positives from Markdown formatting and normal workflow prose. The documented read API can access archived conversation JSONL files under a hidden configuration directory, so the filesystem and privacy risk is real. No prompt injection attempt was found in the reviewed files.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
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-remembering-conversations/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/obra-remembering-conversations?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/obra-remembering-conversations?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/obra-remembering-conversations/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/obra-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>obra. (2026). remembering-conversations security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/obra-remembering-conversations/audits/4@techreport{obra-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/obra-remembering-conversations/audits/4},
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: "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/obra-remembering-conversations/audits/4"
identifiers:
- type: other
value: "skillstore:obra-remembering-conversations:audit:4"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
remembering-conversations
2026-08-21
obra-remembering-conversations
2026-08-21
Find earlier reasoning about a project choice before changing related code.
Locate previous implementation notes, blockers, and next steps for an interrupted task.
Search for similar past failures and reuse confirmed fixes when the current issue matches.
Search past conversations for why we chose [approach] in [project]. Summarize the decision, tradeoffs, and sources.
Search memory for prior work on [error or symptom]. Focus on confirmed fixes, failed attempts, and relevant source references.
Search past conversations for [pattern A] and [pattern B]. Compare where each worked, where each failed, and what applies now.
After inspecting the current code, search memory for related architecture discussions. Produce a plan that separates historical facts from current assumptions.
Author
obraLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
11 downloads · 109 views
File structure
📄 SKILL.md
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.
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.
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.
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.
Choose Claude Code Web or CLI
by DNYoussef
Teams lose time when they pick the wrong Claude Code interface for a task. This skill recommends Web, CLI, or a hybrid handoff workflow.
Organize Conductor Tracks
by sickn33
Track work can become unclear when specs, plans, status, and metadata drift apart. This skill gives Claude, Codex, and Claude Code structured guidance for Conductor track workflows.
Generate Lark Standup Reports
by larksuite
Daily planning is slow when meetings and tasks live in separate Lark apps. This skill combines calendar agenda and unfinished tasks into one standup-ready summary.
Coordinate Parallel AI Agents
by ZhanlinCui
Independent failures waste time when one agent investigates them sequentially. This skill helps Claude, Codex, and Claude Code split work safely and merge results.
Scan Conductor Project Plans
by 89jobrien
Project context is often scattered across planning files. This skill guides Claude, Codex, and Claude Code to read conductor files before work begins.
Adapt AI Responses with Behavioral Modes
by sickn33
General-purpose assistants can use the wrong approach for a task. This skill selects structured modes for ideation, implementation, debugging, review, teaching, release, and collaboration.