Automated summary

Helps the team lead review and respond to pending asks from agents using GitHub and a local tracking file.

Strengths

Clear structure for processing each ask one by one
Automates gathering and updating GitHub tasks
Maintains a local history (asks/human.md) for traceability
Prioritizes tasks by urgency

Limitations

Requires access to GitHub CLI and a local repository
Does not make decisions for the human
Relies on correct labeling of issues/PRs with 'needs-human' tags

When to use it

Use this skill when you need to process a batch of agent requests awaiting human validation.

When not to use it

Do not use this if you prefer to interact directly with agents without GitHub or a local file.

Security analysis

Safe

Quality score75/100

The skill uses standard bash commands (cat, gh, git) to read a local file and list GitHub issues/PRs. No destructive, exfiltrating, or obfuscated operations are present. The actions are legitimate for processing human feedback.

No concerns found

How this analysis is made

Examples

Process pending human asks

I have agent asks pending. Please walk me through them and help me respond.

Review needs-human issues

Check GitHub for issues labeled needs-human and help me decide on each one.

Merge PRs awaiting human approval

List PRs labeled needs-human-merge and guide me through approving or rejecting them.

name: human description: Help the human team lead review and respond to pending asks from agents. Use when processing human feedback, agent requests, or needs-human issues.

Human Feedback Assistant

Name: Human Feedback Assistant
Author: Skills Guide Bot

Help the human team lead review and respond to pending asks from agents.

Instructions

You are helping the human team lead process feedback requests from the autonomous agent team. Walk through each pending ask one at a time.

Step 1: Gather Pending Asks

First, read the human asks dashboard and find GitHub issues needing human input:

cat asks/human.md
gh issue list --label "needs-human" --state open

Also check for PRs awaiting human merge approval:

gh pr list --label "needs-human-merge" --state open

Step 2: Walk Through Each Ask

For each pending item:

Summarize the ask in plain language (what decision is needed, who's asking, what's blocked)
Present options if the agent provided them, or suggest reasonable options
Ask the human for their decision
Record the response appropriately:
- For GitHub issues: Add a comment with the decision, then close if resolved
- For PRs needing merge: Add approved:human label if approved
- Update asks/human.md to move resolved items to the Resolved section

Step 3: Commit Updates

After processing asks, commit any changes to asks/human.md:

git add asks/human.md
git commit -m "Human: Process feedback asks"
git push origin main

Response Format

When presenting each ask, use this format:

## Ask #[number]: [Brief Title]

**From:** [Agent role]
**Blocked:** [What work is waiting on this]
**Question:** [The actual decision needed]

**Options:**
1. [Option A]
2. [Option B]
...

What's your decision?

Important

Process asks in priority order (high priority first)
If an ask is unclear, help the human understand what the agent is really asking
Keep responses concise - agents just need a clear decision
Don't make decisions for the human - present information and let them choose

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/human-feedback-assistant-mma3js6e/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/human-feedback-assistant-mma3js6e' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/human-feedback-assistant-mma3js6e/download' --output '.skill-downloads/human-feedback-assistant-mma3js6e/SKILL.md.part' && mv '.skill-downloads/human-feedback-assistant-mma3js6e/SKILL.md.part' '.skill-downloads/human-feedback-assistant-mma3js6e/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

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/human-feedback-assistant-mma3js6e/SKILL.md' && test -s '.skill-downloads/human-feedback-assistant-mma3js6e/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/human' && cp -R '.skill-downloads/human-feedback-assistant-mma3js6e' '.claude/skills/human'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/human-feedback-assistant-mma3js6e'

openskills read 'human-feedback-assistant-mma3js6e'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

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/human-feedback-assistant-mma3js6e/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