Skip to content
Agentmart
Submit a tool

hypothesis-ledger

Maintain and validate the Learn hypothesis ledger (specs/learn/hypotheses.md): add Open hypotheses, list reviews and feature deletions that are due, compute a…

Skill by ALTEN-group

IndexedMIT★ 5
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/alten-group-hypothesis-ledger

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Maintain and validate the Learn hypothesis ledger (specs/learn/hypotheses.md): add Open hypotheses, list reviews and feature deletions that are due, compute a deterministic proposed verdict from the observed metric, and report the validation and deletion rates. Use when preparing the weekly Outcome review, when a Triage issue names an outcome metric, or when CI validates the ledger. AI proposes; the Product Owner decides every verdict.

Use cases: documents, devops

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/hypothesis-ledger

What's inside

Skill name
hypothesis-ledger
Description
Maintain and validate the Learn hypothesis ledger (specs/learn/hypotheses.md): add Open hypotheses, list reviews and feature deletions that are due, compute a deterministic proposed verdict from the observed metric, and report the validation and deletion rates. Use when preparing the weekly Outcome review, when a Triage issue names an outcome metric, or when CI validates the ledger. AI proposes; the Product Owner decides every verdict.
License
MIT
Instructions
53 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • SKILL.md
  • hypothesis-ledger-contract.md · references/
  • ledger-fixture.mjs · scripts/
  • ledger.mjs · scripts/
  • ledger.test.mjs · scripts/

SKILL.md (first lines)

# Hypothesis Ledger

Keep a ledger of every outcome bet and review it after its watch window. The script computes a proposed verdict with its maths. It never writes a verdict: **the Product Owner decides**, and an invalidated feature is deleted.

## When to Use This Skill

- A backlog issue names an outcome metric and the work item ships: add an `Open` row.
- The weekly Outcome review needs the hypotheses due for a verdict and the invalidated features still waiting for deletion.
- Someone has the observed metric and wants the proposed verdict with its maths before the review.
- CI validates `specs/learn/hypotheses.md` on a pull request.
- The monthly retrospective needs the hypothesis validation rate and the feature deletion rate.

## Path resolution

Resolve `references/` and `scripts/` relative to **this skill's install directory** (the folder that contains this `SKILL.md`), not the consumer repository root or the current shell cwd. If the skill was installed under `.agents/skills/hypothesis-ledger/` or `.claude/skills/hypothesis-ledger/`, use that base path.

## Workflow

1. **Read `references/hypothesis-ledger-contract.md` now.** It is the authoritative source for columns, verdicts, actions, and the proposal maths.
2. Register a hypothesis when the work item ships (the row starts `Open`):

```bash
node scripts/ledger.mjs add --file specs/learn/hypotheses.md --issue 42 \
  --hypothesis "Order templates shorten order entry" --metric "Minutes per order" \
  --baseline 6 --target 3 --direction down --watch-ends 2026-11-30
```

3. Before the Outcome review, list what is due and propose verdicts from the observed numbers:

```bash
node scripts/ledger.mjs due --file specs/learn/hypotheses.md --today 2026-12-01
node scripts/ledger.mjs propose --file specs/learn/hypotheses.md --issue 42 --observed 3.4
node scripts/ledger.mjs stats --file specs/learn/hypotheses.md
```

4. Present each proposed verdict with its maths and suggested actions. **Do not edit the `Verdict`, `Action`, or `Decided` cells.** The Product Owner records them, as `<name> (Product Owner) on YYYY-MM-DD`, in a pull request.
5. Validate the ledger after every human edit and in CI:

```bash
node scripts/ledger.mjs validate --file specs/learn/hypotheses.md
```

6. Hand invalidated, not-yet-deleted features and other Learn outputs to the `learn-signals` skill so they become Triage backlog issues.

Treat a nonzero exit as an invalid ledger and fix the file or the command. The script is the enforcement gate.

## Done When

- `ledger.mjs validate` exits 0 on `specs/learn/hypotheses.md`.
- Every proposed verdict was presented with its maths and none was written by AI.
- Every `Invalidated` row is either deleted (`Delete feature (Deleted <date>)`) or listed by `due` and emitted as a Triage issue.

From ALTEN-group/coding-pal, MIT.

More from ALTEN-group/coding-pal

Signals

Stars
5
Forks
0
Open issues
0
Last commit (this folder)
Oct 13, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ALTEN-group

Cite this page

hypothesis-ledger skill. Agent Mart. https://agentmart.dev/skills/alten-group-hypothesis-ledger (last updated 2026-10-24)