Skip to content
Back to skills

Work Status Reporting

ASecurity

Use when preparing, reviewing, or correcting weekly, daily, periodic, or client-facing work status reports where finished work, moderation, diagnosis-only progress, unverified repairs, automation/system activity, and in-progress items must not be double-counted or overstated.

  • 1,531 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agents

Works with

  • cli

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add hashgraph-online/awesome-codex-plugins --skill work-status-reporting --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Work Status Reporting?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Work Status Reporting
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hashgraph-online-work-status-reporting/badge)](https://www.skillsdirectory.com/skills/hashgraph-online-work-status-reporting)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: work-status-reporting
description: Use when preparing, reviewing, or correcting weekly, daily, periodic, or client-facing work status reports where finished work, moderation, diagnosis-only progress, unverified repairs, automation/system activity, and in-progress items must not be double-counted or overstated.
---

# Work Status Reporting

Use this skill for weekly or periodic status reports, especially when the user
needs a truthful summary of many operational tasks, campaigns, automations, or
client deliverables.

## Status Separation

Before writing the report, classify each item by evidence-backed state:

- `finished`: the requested user-visible result was completed and verified;
- `waiting_external`: submitted, sent, or in moderation, but not yet accepted or
  live;
- `diagnosis_only`: investigation or root-cause work happened without a verified
  repair;
- `repair_unverified`: a fix was applied but the user-visible path was not
  proven end to end;
- `in_progress`: active work remains inside the requested scope;
- `blocked`: a concrete blocker prevents completion.

Do not call a campaign launched when the evidence shows only draft, moderation,
or another pre-launch state. Do not call a repair complete when only logs,
transport success, code inspection, or a partial internal check exists.

## Counting Rules

- Count deliverables once at the user-facing unit of work, not once per
  automation, reviewer, subtask, retry, or internal artifact.
- Separate automation/system maintenance from client-visible deliverables unless
  the report intentionally has an internal operations section.
- Keep diagnosis, implementation, review, and publication as separate phases
  when they are not all complete.
- If the same event appears in multiple notes, merge it and retain the most
  conservative current status.

## Review Checklist

Before finalizing:

1. Compare the report against source evidence for premature completion claims.
2. Check for duplicated counts caused by automation runs, subagents, review
   passes, dry-runs, or repeated summaries.
3. Preserve reviewer corrections about unfinished states, moderation, missing
   end-to-end proof, or ambiguous metrics.
4. State remaining work plainly instead of hiding it in a positive summary.

Files in this skill

  • SKILL.md2.2 KB
  • agents/openai.yaml271 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.