/accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
One skill from agentic-awesome-skills.
shell
$ npx -y skills add sickn33/agentic-awesome-skills --skill accint-commitments --agent claude-codeInstalls just this skill. Get the whole plugin for auto-invocation.
How it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/accint-commitments
Context preview
The summary Claude sees to decide when to auto-load this skill.
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
Stats
Stars43,758
Forks6,464
LanguagePython
LicenseMIT
Ships with agentic-awesome-skills
SKILL.md
accint-commitments.SKILL.md
--- name: accint-commitments description: Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome"). risk: unknown source: https://github.com/maxbaluev/accreted-intelligence/tree/main/plugins/claude/skills/commitments source_repo: maxbaluev/accreted-intelligence source_type: community date_added: 2026-07-01 license: Apache-2.0 license_source: https://github.com/maxbaluev/accreted-intelligence/blob/main/LICENSE --- # 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.
