Workflow Audit

SkillDev tools

Use when manual work, prior sessions, or an operator interview must be audited for repeatable skill, automation, or bounded-loop candidates.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Workflow Audit skill

What this skill tells your AI

The instructions your AI receives, as published by mark393295827/third-brain-v7-skills in skills/workflow-audit/SKILL.md and read by ahel’s review.

<skill_contract> Bounded manual notes, prior-session evidence, or interview answers describing work, repetition, decisions, and constraints. A deterministic audit with mode, evidence-bounded candidates, skill/automation/loop decisions, permissions, and a typed handoff. Every recommendation points to supplied evidence, remains within the input bound, and has an explicit supervised promotion decision. <non_goals>Editing skills, changing schedules, mutating Vault state, inventing metrics, or executing an unapproved external action.</non_goals>

Usage Template

Provide: objective, evidence source, mode (manual, session, or interview), size bound, candidate limit, operator/approval owner, and desired handoff.

Workflow

<unknowns_gate> Separate observed repetition from a proposed improvement. Missing frequency, owner, verifier, permission, or stop condition makes a candidate review-only; it does not justify a schedule or autonomous loop. </unknowns_gate>

  • SKILL_CANDIDATE when the work has a reusable procedure or multiple steps; otherwise KEEP_MANUAL.
  • AUTOMATION_CANDIDATE only when repetition or a clear trigger is evidenced; otherwise HOST_REQUIRED_REVIEW.
  • LOOP_CANDIDATE only when retry, monitoring, polling, follow-up, or a repeat-until condition is evidenced; otherwise NO_LOOP.

Record the evidence snippet, approval owner, verifier, stop condition, and side-effect expectation. Promotion is a separate supervised action with a receipt and rollback path.

Failure Protocol

Return NEEDS_INPUT for missing evidence or a required authority decision, INSUFFICIENT_EVIDENCE when repetition cannot be supported, and VERIFY_FAILED when a recommendation cannot be traced to the supplied source. Preserve the audit receipt and do not promote.

Output Contract

Return status, result, evidence, unknowns, and next_action. The result includes mode, source hash, bounded candidates, skill/automation/loop decisions, approval, verifier, stop condition, and side-effect count.

Edge Cases

  • A quiet prior session is not proof that a workflow is eligible for automation; record INSUFFICIENT_EVIDENCE or request a frequency probe.
  • A recurring task that writes to a shared Vault remains a supervised staged-write candidate even when the extraction itself is deterministic.

Success Metrics

  • Source provenance and candidate bounds are preserved.
  • Every decision is evidence-linked and independently checkable.
  • No skill, schedule, external service, or Vault file is changed by the audit.

Quality Gates

  • Mode is explicit or conservatively inferred.
  • Unknown permissions, verifiers, and stop conditions are surfaced.
  • Promotion is supervised and receipt-backed.
  • side_effect_count is zero.

</skill_contract>

Signals

GitHub stars
138
Forks
20
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
workflow-audit
Source
github.com/mark393295827/third-brain-v7-skills