Askit Build Command
Creates and improves Claude slash commands (commands/<name>.md) that map to a skill, to the Advanced Skill Library Standard. Use when you need to give a skill an explicit /command entry point or raise an existing command's conformance.
Install
$ agentstack add skill-product-on-purpose-agent-skills-toolkit-askit-build-command ✓ 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-command) 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-command
Purpose
Author conformant commands. Two modes: create scaffolds a new commands/.md that maps to an existing skill; improve raises an existing command toward the quality bar. On Codex a command is realized as its backing skill (Standard sec 3.2 parity), so this skill emits no Codex artifact. Follows the shared [builder pattern](../../docs/reference/builder-pattern.md). Authoring depth is in [references/authoring-commands.md](references/authoring-commands.md).
When to use
When the user asks to create, scaffold, or improve a slash command for a skill.
create mode
- Brief interview: the command name (kebab-case, becomes
/name), the skill (or workflow) it maps to, optional args, and a description mirroring the backing skill's intent. Skip if provided in context. - Copy
templates/command.mdintocommands/.md. - Fill the frontmatter:
description(what AND when; Standard sec 8.1);maps-toequal to the backing skill or workflow name; optionalargument-hint/allowed-tools/model;metadata.version. The filename is the command name (nonamekey). Write a body that invokes the backing skill, passing$ARGUMENTS. - Verify the
maps-totarget exists (a skill inskills/or a workflow in_workflows/). - Register the command in
library.jsoncomponents.commandsas{ name, path, version, tier, status }. - Assess with
node scripts/evaluate.mjs . --jsonand iterate until 0 errors (S3 components index + S7 command-contract must be clean).
improve mode
- Run
node scripts/evaluate.mjs . --jsonand read the report. - For each finding: an S3 error -> declare/undeclare the command in
components.commandsto match disk; an S7 error -> add the missingmaps-to, fix amaps-tothat does not resolve, or add a missingdescription. For any other finding, read its message and apply the fix it states. - Re-run evaluate to confirm.
Scope
Claude-native: a command is commands/.md. Codex realizes a command as its backing skill (Standard sec 3.2), so there is no Codex artifact to generate; the backing skill is the invocable form on Codex. A command MUST map to exactly one skill or workflow.
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.