Start a fresh conversation. Replace the highlighted placeholders.
Use accint-commitments to triage open promises in [acc workspace], identify which have real supporting outcomes, leave genuinely waiting items open, and present proposed honest verdicts for my confirmation before recording any closure.
Required inputs
[acc workspace]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: accint-commitmentsdescription: Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").risk: criticalsource: https://github.com/maxbaluev/accreted-intelligence/tree/main/plugins/claude/skills/commitmentssource_repo: maxbaluev/accreted-intelligencesource_type: communitydate_added: 2026-07-01license: Apache-2.0license_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.
List open promises: acc commitments (CLI, read-only observation).
For each closeable one: acc_act(runtime="outcome", input={"ref": "<id>", "good": true|false, "note": "..."}).
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.
Leave genuinely-waiting commitments open — waiting is a first-class clean state.
Example
User request:
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
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.