Automated summary

This skill manages the handoff between research and discussion workflows by saving session state and constructing a structured handoff message.

Strengths

Structured transitions between workflows
Supports multiple source types (research, continue, fresh, bridge)
Saves session state for later resumption

Limitations

Requires specific file paths
Only works with Claude CLI hooks
Assumes a predefined workflow

When to use it

When moving from a research session to a structured discussion session within a predefined workflow.

When not to use it

For ad-hoc conversations without a predefined workflow or when not using the Claude CLI infrastructure.

Security analysis

Safe

Quality score75/100

The skill instructs the AI to output a code block containing a shell command, not to execute it. The command writes session state, which is a benign local operation. There is no instruction to run destructive actions, exfiltrate data, or disable safety mechanisms. The only potential risk would be if the user later manually runs the command with unsanitized topic input, but that is outside the skill's execution context.

No concerns found

How this analysis is made

Examples

Start discussion from research

Start a discussion about the new authentication system based on the research we just did.

Continue existing discussion

Continue the discussion we had yesterday about the database migration plan.

Fresh discussion with work type

Begin a fresh discussion on optimizing the CI pipeline. Work type: implementation.

Invoke the Skill

Name: Invoke the Discussion Skill
Author: Skills Guide Bot

Reference for start-discussion

Before invoking the processing skill, save a session bookmark.

Output the next fenced block as a code block:

Saving session state so Claude can pick up where it left off if the conversation is compacted.

.claude/hooks/workflows/write-session-state.sh \
  "{topic}" \
  "skills/technical-discussion/SKILL.md" \
  ".workflows/discussion/{topic}.md"

This skill's purpose is now fulfilled.

Invoke the technical-discussion skill for your next instructions. Do not act on the gathered information until the skill is loaded - it contains the instructions for how to proceed.

Handoff

Construct the handoff based on how this discussion was initiated.

If source is "research"

If work_type is available (from Step 2), add the Work type line:

Discussion session for: {topic}
Work type: {work_type}
Output: .workflows/discussion/{topic}.md

Research reference:
Source: .workflows/research/{filename}.md (lines {start}-{end})
Summary: {the 1-2 sentence summary from the research analysis}

Invoke the technical-discussion skill.

If source is "research-bridge"

Discussion session for: {topic}
Work type: {work_type}
Research source: .workflows/research/{topic}.md
Output: .workflows/discussion/{topic}.md

Research reference:
Source: .workflows/research/{topic}.md
Summary: {the discussion-ready summary from the research file}

Invoke the technical-discussion skill.

If source is "continue"

Read work_type from the existing discussion frontmatter.

Discussion session for: {topic}
Work type: {work_type}
Source: existing discussion
Output: .workflows/discussion/{topic}.md

Invoke the technical-discussion skill.

If source is "fresh"

If work_type is available (from Step 2), add the Work type line:

Discussion session for: {topic}
Work type: {work_type}
Source: fresh
Output: .workflows/discussion/{topic}.md

Invoke the technical-discussion skill.

If source is "bridge"

Discussion session for: {topic}
Work type: {work_type}
Source: fresh
Output: .workflows/discussion/{topic}.md

Invoke the technical-discussion skill.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/invoke-the-discussion-skill-mm8o5155/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/invoke-the-discussion-skill-mm8o5155' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/invoke-the-discussion-skill-mm8o5155/download' --output '.skill-downloads/invoke-the-discussion-skill-mm8o5155/SKILL.md.part' && mv '.skill-downloads/invoke-the-discussion-skill-mm8o5155/SKILL.md.part' '.skill-downloads/invoke-the-discussion-skill-mm8o5155/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/invoke-the-discussion-skill-mm8o5155/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

PDF Reader

Productivity

Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.

Claude CodeCursorCodexbeginnerSafe 20,122

Skills Guide Bot