Run any Skill in Manus with one click

Get Started

assess-completeness

Stars0

Forks6

UpdatedJuly 1, 2026 at 19:47

Check if an issue has all required information for action

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

fullsend-ai

fullsend-ai/experiments

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	assess-completeness
description	Check if an issue has all required information for action
allowed-tools	Bash(curl *), WebFetch

Read the issue via the GitHub REST server:

curl -s http://host.docker.internal:8081/repos/$OWNER/$REPO_NAME/issues/$ISSUE_NUMBER

Evaluate whether the issue contains sufficient information.

For bugs: steps to reproduce, expected vs actual behavior, environment info.
For features: use case description, acceptance criteria.
For questions: enough context to provide a useful answer.
If the issue references external links (logs, pastebins, docs), fetch them to verify the information is actually there.

Respond ONLY with a JSON object:

{
  "issue_type": "bug" | "enhancement" | "question" | "other",
  "complete": true | false,
  "missing": ["<missing item 1>", "<missing item 2>"],
  "external_context": "<summary of relevant information gathered from external links, or null if none>"
}

More from this repository

same repository

detect-duplicates

fullsend-ai/experiments

Search for and identify duplicate issues in a repository

2026-07-010

triage-coordination

fullsend-ai/experiments

Coordinate triage of a GitHub issue by orchestrating sandboxed analysis subagents and applying labels

2026-07-010

verify-reproducibility

fullsend-ai/experiments

Verify whether a reported bug is reproducible by inspecting the codebase

2026-07-010

code-implementation

fullsend-ai/experiments

Step-by-step procedure for implementing a GitHub issue. Gathers context, discovers repo conventions, plans the change, implements, verifies with tests and linters, and commits to a feature branch.

2026-07-010

baked-instructions-builder

fullsend-ai/experiments

Hardcoded endpoint documentation for the container builder API.

2026-07-010

baked-instructions-provisioner

fullsend-ai/experiments

Hardcoded endpoint documentation for the repo provisioner API.

2026-07-010

name	assess-completeness
description	Check if an issue has all required information for action
allowed-tools	Bash(curl *), WebFetch

Read the issue via the GitHub REST server:

curl -s http://host.docker.internal:8081/repos/$OWNER/$REPO_NAME/issues/$ISSUE_NUMBER

Evaluate whether the issue contains sufficient information.

For bugs: steps to reproduce, expected vs actual behavior, environment info.
For features: use case description, acceptance criteria.
For questions: enough context to provide a useful answer.
If the issue references external links (logs, pastebins, docs), fetch them to verify the information is actually there.

Respond ONLY with a JSON object:

{
  "issue_type": "bug" | "enhancement" | "question" | "other",
  "complete": true | false,
  "missing": ["<missing item 1>", "<missing item 2>"],
  "external_context": "<summary of relevant information gathered from external links, or null if none>"
}