Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Status

ASecurity

Show a read-only rollup of the definition of done — every exit condition with its state, properties, and open reason — without running any auditor.

7 stars
0 votes
0 copies
1 views
Added 9/20/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add akka/ai-marketplace --skill status --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Status?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Status
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/akka-status/badge)](https://www.skillsdirectory.com/skills/akka-status)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: status
description: "Show a read-only rollup of the definition of done — every exit condition with its state, properties, and open reason — without running any auditor."
---

## User Input

You **MUST** consider the user input before proceeding (if not empty).

## Purpose

`/akka:status` prints the current definition-of-done manifest: every exit
condition grouped by Definition-of-Done type, with its state (`open`, `green`,
or `red`), its properties (provenance, waiver, applicability), and any `open`
reason. The two locked process-integrity gates, `PROC-AUDITOR-COVERAGE` and
`PROC-ADEQUACY-REVIEWED`, appear among the conditions like any other.

The manifest reflects the project's own state — waived, struck, and signed-off
conditions appear as such — so it agrees with `/akka:conform`.

**Status never runs an auditor.** It does not build, test, lint, or probe. That
is the whole difference from `/akka:conform`: machine-checkable conditions stay
`open` here until conform evaluates them. Once conform has run, the two agree.

Because it changes nothing and costs nothing, status is the command to reach
for during an autonomous build — it shows progress without interrupting the
machine.

## Outline

1. **Render the manifest.** Call `akka_ec_status` for the project directory.
   This resolves the exit-condition library against the org governance floor
   and the project's own strikes, waivers, and sign-offs, then renders the
   manifest. It is read-only and runs no auditors.

2. **Get the counts.** Call `akka_ec_rollup` for the same directory. It returns
   the status counts by tier and by Definition-of-Done type as JSON. Use this
   as the headline so the user sees the shape of the build before the detail.

3. **Report plainly.** Lead with the rollup: how many conditions are settled,
   how many are waiting on the user, how many are blocked outside the project.
   Then surface the conditions that are `open` or `red`, each with its
   user-facing reason — the reason field is the action.

   State plainly that the auditors were not run, and that the machine-checkable
   conditions are therefore still `open` rather than failing. Do not present an
   unevaluated condition as a problem. Offer `/akka:conform` as the way to
   resolve them.

   Do not restate internal condition ids, check keys, or the words "auditor" /
   "coverage gate" / "adequacy review" in the summary. Offer *"say 'show
   details' for the full checklist"* and show the raw manifest only if asked.

## Key rules

- Read-only, always. Never run a build, a test, or a probe from this command,
  and never call `akka_ec_conform` or `akka_ec_summary` — both run the
  auditors, which is precisely what status must not do.
- Never characterize an unevaluated condition as passing or failing. It is
  `open` because nothing has looked at it yet, and saying otherwise is the one
  way this command can mislead.
- Do not change the project. No sign-offs, no strikes, no waivers, no mode
  changes as a side effect of showing status.

## Done When

- [ ] `akka_ec_status` was called and the manifest was resolved without running
      any auditor.
- [ ] `akka_ec_rollup` was called and its counts led the report.
- [ ] Conditions that are `open` or `red` were surfaced with their user-facing
      reasons (no internal ids, no machinery words).
- [ ] The report stated that the auditors did not run, and did not present
      unevaluated machine-checkable conditions as failures.
- [ ] Nothing in the project was modified.

Attribution

akkaakka
View sourceMore from akka →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

694381 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →