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

Superstack Value

ASecurity

An outcome claim shipping — "this should increase signups", "this saves the team time" — recorded as a dated, falsifiable prediction; settled when the SessionStart line says due. Skip for work with no outcome claim.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add debabsah/superstack --skill superstack-value --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Superstack Value?

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

Security grade badge for Superstack Value
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/debabsah-superstack-value/badge)](https://www.skillsdirectory.com/skills/debabsah-superstack-value)

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

Download with Pro
Files
SKILL.md
---
name: superstack-value
description: An outcome claim shipping — "this should increase signups", "this saves the team time" — recorded as a dated, falsifiable prediction; settled when the SessionStart line says due. Skip for work with no outcome claim.
---

# superstack-value

"Worth building" is a claim. It ships every day unlabeled, undated, and never falsified — the last claim class without a ledger. This module gives it one, exactly as `claims-log` gives one to "done".

## Recording (at ship, and from inception)

When the work's justification is an expected outcome, append one bullet to `.superstack/value-log`:

```
- V<n> (<date>) expected: <observable change> — check by <YYYY-MM-DD> — from: <task/premise>
```

- **The expectation is an observable, not a vibe** — a number, a behavior, an event that either happens or doesn't. "Users will like it" is not checkable; "the weekly report takes <10 min" is.
- **The horizon is honest** — check-by is when the observable could realistically have moved, not next week by default.
- Inception's demand premises become predictions when the build ships — the premise ledger already wrote the observable; date it and log it.
- One line per shipped outcome-claim; work with no outcome claim gets no entry (do not manufacture predictions to look instrumented).

## Settling (when the session-start line says due)

For each due entry: check the observable — the real number, the real behavior, asking the user when the evidence is theirs — and append the verdict to the line:

```
[HELD <date> — <evidence>]   or   [MISSED <date> — <what actually happened>]
```

- **A MISSED is calibration data, not a failure.** Settle it honestly and move on; the log's value is the base rate.
- **A run of MISSED on a theme is a gotcha about product sense** — log it to the overlay (`Gotcha: predictions about <theme> keep missing → …`) so the next inception's demand battery pushes harder there.
- Never delete or rewrite entries; the log is append-only like every calibration record. When evidence can't be had, settle as `[MISSED <date> — unmeasurable as written]` — that too is a lesson: the next prediction gets a measurable observable.

The human owns what "held" means when the observable is ambiguous — ask, don't adjudicate.

Attribution

debabsahdebabsah
View sourceMore from debabsah →
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".

1066601 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', ...

686011 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.

651 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 →