Skill
agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Development
Skill
/dataset-verify
Verify a dataset plan or run receipt, checkpoint continuity, provenance completeness, and derived-artifact freshness.
Install
$ npx -y skills add jmagly/aiwg --skill dataset-verify --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/dataset-verify
Context preview
The summary Claude sees to decide when to auto-load this skill.
Verify a dataset plan or run receipt, checkpoint continuity, provenance completeness, and derived-artifact freshness.
SKILL.md
dataset-verify.SKILL.mdnamespace: aiwg name: dataset-verify description: Verify a dataset plan or run receipt, checkpoint continuity, provenance completeness, and derived-artifact freshness. version: 1.0.0 platforms: [all] aliases: [dataset health, verify ingest, check dataset freshness] triggers: [verify this dataset, did ingestion succeed, is this index fresh, validate the run receipt, check checkpoint continuity]
Dataset Verification
Delegate to `aiwg dataset verify <dataset-or-run-ref> --json`. Verify plan and receipt digests, committed outcome, checkpoint continuity, counts/rejections, schema bindings, evidence completeness, derived-artifact freshness, and stated degradation. Searchability alone is not proof of success or canonical-source availability.
Return a verification reference with explicit `verified`, `degraded`, `unverifiable`, or `failed` state. Preserve diagnostics and route evidence questions to Dataset Provenance Reviewer.
Ships withaiwg
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Get the whole plugin
Stats
211
Stars
32
Forks
Active
Maintenance
TypeScript
Language
MIT
License
1d ago
Last commit
1y ago
Created
Repo: jmagly/aiwg
Other skills on aiwg.
Skill
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Skill
auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Skill
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
Skill
debug-memory
Query and manage the executable feedback debug memory
Skill
execute-feedback
Execute tests on generated code and iterate until passing