---
name: Accint Commitments
slug: commitments-triage
category: Automation
description: Triages open commitments from acc and closes them with honest, real-world verdicts using acc_act. Use when you need to verify promises against reality and maintain a clean state of commitments.
github: "https://github.com/sickn33/agentic-awesome-skills/tree/main/plugins/agentic-awesome-skills-claude/skills/accint-commitments"
language: Python
stars: 44097
forks: 6502
install: "git clone https://github.com/sickn33/agentic-awesome-skills"
added: 2026-07-19T06:53:17.921Z
last_synced: 2026-07-29T06:36:06.705Z
canonical_url: "https://dirskills.com/skills/commitments-triage"
---

# Accint Commitments

Triages open commitments from acc and closes them with honest, real-world verdicts using acc_act. Use when you need to verify promises against reality and maintain a clean state of commitments.

**Install:** `git clone https://github.com/sickn33/agentic-awesome-skills`

## README

# commitments
## When to Use

Use this skill when you need triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").


Routing sugar over the two MCP verbs — no logic lives here.

1. List open promises: `acc commitments` (CLI, read-only observation).
2. For each closeable one: `acc_act(runtime="outcome", input={"ref": "<id>", "good": true|false, "note": "..."})`.
3. Provenance discipline: the default `self_graded` is a WEAK prior (credits at 0.25×).
   Pass `owner` only when the owner validated, `external`/`runtime` only when reality did
   (a real reply, a passing test, a world result). Never tag your own grade as reality.
4. Leave genuinely-waiting commitments open — `waiting` is a first-class clean state.

## Limitations

- Use this skill only when the task clearly matches its upstream source and local project context.
- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.