Workflow Audit
SkillDev toolsUse 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.
No other account needed.
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_CANDIDATEwhen the work has a reusable procedure or multiple steps; otherwiseKEEP_MANUAL.AUTOMATION_CANDIDATEonly when repetition or a clear trigger is evidenced; otherwiseHOST_REQUIRED_REVIEW.LOOP_CANDIDATEonly when retry, monitoring, polling, follow-up, or a repeat-until condition is evidenced; otherwiseNO_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_EVIDENCEor 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_countis 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