arckit-build is a skill in tractorjuice/arc-kit, last changed 19 Nov 2026. It can install more skills, run shell commands, name web addresses and pre-approve tools — read the findings before installing.
Bulk-builds a project's ArcKit artefacts in parallel from a YAML recipe: computes the artefact dependency DAG, dispatches one subagent per target per wave, validates each output, commits the wave and persists progress to .arckit/state.json so a build can resume. Manual only: run /arckit:arckit-build with --plan, --resume, --target, --refresh or --recipe. Not needed for a single artefact; run that /arckit:* command directly.
At a glance
What it can touch
How much a skill can do, not whether it is risky.
Pattern check
Nothing flagged
That isn't proof the skill is harmless.
Commit 98167b9 · 20 Nov 2026
How the check worksPattern check: nothing flagged
That isn't proof the skill is harmless.
QAI Index
We rate every listed skill the same way, from 0 to 100.
A guide to compare by, not a verdict on the skill.
How it's scoredGet an email when its check changes.
Keep it with the other skills you use, installed with one command.
Install
Sign in to see how to install it
Free with Google or an email link, no password needed. Then pick your agent and copy its steps.
What it can touch
Sign in to see the file and line behind each one
The summary at the top stays open to everyone. Signing in is free, with Google or an email link.
Pattern check
Pattern check: nothing flagged · commit 98167b9 · 20 Nov 2026
We checked every text file in this skill, at commit 98167b9 on 20 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Outside links we did not follow
- https://github.com/tractorjuice/arc-kit/blob/469e0b7d/docs/superpowers/specs/2026-05-19-uk-nhs-overlay-design.md
- https://github.com/tractorjuice/arc-kit/issues/424
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specPasses with warnings
The format our Agent Skills docs set out, held to the strictest version of each rule among the agents we check.
- Warning
Fields outside the spec: disable-model-invocation (read by Claude Code and VS Code). Uploads to the Claude apps and API, and strict validators, reject the file; most agents ignore these fields. O1
Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Warning
allowed-tools is a list; the spec defines a space-separated string. gh skill publish rejects a list, though Claude Code accepts one. O5
Fix: Write it on one line: allowed-tools: Read(/${CLAUDE_PLUGIN_ROOT}/**)
- Warning
The body is about 9,868 tokens (approx.); the spec suggests under 5,000. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
The description doesn't say when to use the skill. D6
Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.
- Note
The first sentence of the description is 262 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
There is no license field, so readers can't tell whether they may reuse the skill. O2
Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Warning
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
The first sentence of the description is 262 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
The body is about 9,868 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
Upload and packaging fail on fields outside the spec: disable-model-invocation. O1
Fix: Delete them, and keep your own data under metadata as text values.
- Note
The description is 427 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
allowed-tools is a list; the spec defines a space-separated string. O5
Fix: Write it on one line: allowed-tools: Read(/${CLAUDE_PLUGIN_ROOT}/**)
- Note
The body is about 9,868 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Error
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
Fields outside the spec: disable-model-invocation. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
Fix: Delete them, or move your own data under metadata as text values.
- Note
The first sentence of the description is 262 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
allowed-tools is a list; the spec defines a space-separated string. O5
Fix: Write it on one line: allowed-tools: Read(/${CLAUDE_PLUGIN_ROOT}/**)
- Warning
VS Code & CopilotPasses
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Note
allowed-tools is a list; the spec defines a space-separated string. O5
Fix: Write it on one line: allowed-tools: Read(/${CLAUDE_PLUGIN_ROOT}/**)
- Note
SKILL.md
We only show SKILL.md text here when its licence clearly allows it.
Read SKILL.md on GitHub (opens in a new tab)Files
Changelog
Newest first: each commit that changed its folder on GitHub, and each change to its listing here.
- Listed on QAI
- Updated: fix: what the review of the closed-question change found (7cbde5a (opens in a new tab))
- Updated: feat(build): a recipe target can set min_lines, the fewest lines its … (6339a5f (opens in a new tab))
- Updated: feat(uk-food): a build recipe that writes the drafts and confirms not… (275076c (opens in a new tab))
- Updated: docs: stop describing /arckit:research as build-vs-buy analysis (e108f80 (opens in a new tab))
- Updated: fix(arc42): make Phase 2 build state, Spec Kit guidance and Q42 licen… (c42a130 (opens in a new tab))
- Updated: feat(arc42): Phase 2 quality, concepts, debt and SDD handover (#1053) (9035586 (opens in a new tab))
- Updated: Merge branch 'fix/982-togaf' into fix/982-au (8b9b13d (opens in a new tab))
- Updated: fix(arckit-au, arckit-au-energy): ISM guidelines, AI/PSPF template fi… (f5e7b65 (opens in a new tab))
- Updated: fix(arckit-uk-nhs): follow DTAC form 2.0, pin the SAFETY.md spec, fix… (87ce75b (opens in a new tab))
- Updated: fix: recipes run requirements after stakeholders; sobc order wording (eaed97d (opens in a new tab))
QAI Index badge
Show this skill's QAI Index in a README or on a website. It links back to this page and changes when we refresh the catalog.
[](https://qai.io/skills/tractorjuice/arc-kit/arckit-build)More from tractorjuice/arc-kit
Other Agent tooling skills
Same category, most repo stars first.