Askit Build Workflow
Creates and improves workflows (an ordered multi-skill arc) for a plugin to the Advanced Skill Library Standard. Use when a recurring sequence of skills is worth formalizing as a workflow, when you need to author a _workflows file with steps and exit criteria, or to resolve S5 workflow findings.
Install
$ agentstack add skill-product-on-purpose-agent-skills-toolkit-askit-build-workflow ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-product-on-purpose-agent-skills-toolkit-askit-build-workflow) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
askit-build-workflow
Purpose
Author a plugin's workflows: ordered arcs that chain multiple skills toward an outcome (Standard sec 3.4). Two modes: create authors _workflows/.md (steps, inputs/outputs handed between steps, exit criteria); improve resolves findings. Authoring depth is in [references/authoring-workflows.md](references/authoring-workflows.md). Follows the shared builder contract ([../../docs/reference/builder-pattern.md](../../docs/reference/builder-pattern.md)).
When to use
When the user asks to author, scaffold, or improve a workflow, or to formalize a recurring multi-skill sequence into an ordered arc.
create mode
- Identify the recurring arc: the ordered skills, what is handed between steps, and the exit criteria. Skip the interview if in context.
- Author
_workflows/.md(copytemplates/workflow.md): frontmattersteps(each naming the skill it invokes) plus a body describing the handoffs and exit criteria. - Every referenced skill MUST exist (S5). Every chaining step MUST be permitted by the chain contract (sec 3.4); use
askit-build-chain-contractto add the permission if needed. - A workflow SHOULD declare which agent targets it supports.
- Evaluate (
node scripts/evaluate.mjs . --json) until S5 is clean.
improve mode
- Run evaluate and read findings.
- For an S5 finding (a step references a skill not on disk), fix the skill name or create the skill. Tighten the handoffs and exit criteria.
- Re-run to confirm.
Scope
A workflow is _workflows/.md with ordered steps and exit criteria (sec 3.4). Referenced skills must exist (S5) and chaining steps must be chain-permitted (sec 3.6). The deterministic workflow-step chain-permission check (step orphans) is a planned enhancement; today S5 enforces step skill-existence and the chain contract governs component-to-component invocation.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: product-on-purpose
- Source: product-on-purpose/agent-skills-toolkit
- License: Apache-2.0
- Homepage: https://product-on-purpose.github.io/agent-skills-toolkit
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.