autoprompt is a skill in Spielewoy/autoprompt-skill, last changed 7 Sept 2026. It can run shell commands and name web addresses.

From the author
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

1 item to review

Name copied from another skill

R38 · High · SKILL.md:2

Commit fe1ded6 · 29 Oct 2026

How the check works

Pattern check:1 item to reviewSee it

Install

Each tab says whether it installs commit fe1ded6, the one we checked, or the latest version.

Read this before installing: Name copied from another skill — SKILL.md:2

Read SKILL.md first
MIT
Licence
1.2k
Repo stars
Publisher

What it can touch

From the files and frontmatter at commit fe1ded6. This is how much a skill can do, not whether it is risky.

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

    Outside links we did not follow

Pattern check

Pattern check: 1 item to review · commit fe1ded6 · 29 Oct 2026

We checked every text file in this skill, at commit fe1ded6 on 29 Oct 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

  • https://github.com/deepseek-ai/deepseek-harness/blob/master/packages/subagent/tool-subagent/src/index.ts
  • https://json-schema.org/draft/2020-12/schema
  • https://autoprompt.local/schemas/deepseek-role-policy-v2.json

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 specFails

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Error

      The name "autoprompt" doesn't match its folder "deepseek". The spec requires them to match. N4

      Fix: Set name: deepseek, or rename the folder to autoprompt.

    • 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

      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.

    • Note

      Reference files that SKILL.md doesn't link: agents/ap-arbiter.md, agents/ap-depth-prober.md, agents/ap-execharness-resolver.md, agents/ap-feature-coordinator.md, agents/ap-framework-generator.md and 44 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: GATES.md (429 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • 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 name "autoprompt" doesn't match its folder "deepseek". Claude Code shows the skill as /autoprompt, and the folder name also invokes it. N4

      Fix: Set name: deepseek, or rename the folder to autoprompt.

    • Note

      Reference files that SKILL.md doesn't link: agents/ap-arbiter.md, agents/ap-depth-prober.md, agents/ap-execharness-resolver.md, agents/ap-feature-coordinator.md, agents/ap-framework-generator.md and 44 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: GATES.md (429 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • 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

      The name "autoprompt" doesn't match its folder "deepseek". claude.ai refuses an upload whose folder name doesn't match the skill name. N4

      Fix: Set name: deepseek, or rename the folder to autoprompt.

    • Note

      Reference files that SKILL.md doesn't link: agents/ap-arbiter.md, agents/ap-depth-prober.md, agents/ap-execharness-resolver.md, agents/ap-feature-coordinator.md, agents/ap-framework-generator.md and 44 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: GATES.md (429 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • 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

      The name "autoprompt" doesn't match its folder "deepseek". OpenAI's own upload example uses a differently named folder, but the spec it follows says they must match. N4

      Fix: Set name: deepseek, or rename the folder to autoprompt.

  • VS Code & CopilotPasses with warnings

    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.

    • Warning

      The name "autoprompt" doesn't match its folder "deepseek". VS Code uses the folder name, deepseek, instead. N4

      Fix: Set name: deepseek, or rename the folder to autoprompt.

SKILL.md

Files

62 files

PathSize
GATES.md (opens in a new tab)25.8 KB
MODES.md (opens in a new tab)657 B
PLAYBOOKS.md (opens in a new tab)4.3 KB
README.md (opens in a new tab)2.3 KB
SKILL.md (opens in a new tab)7.1 KB
VERSION (opens in a new tab)6 B
agent-preset/agent.cordis.yml (opens in a new tab)71.1 KB
agent-preset/preset.yml (opens in a new tab)109 B
agents/ap-arbiter.md (opens in a new tab)1.8 KB
agents/ap-depth-prober.md (opens in a new tab)1.8 KB
agents/ap-execharness-resolver.md (opens in a new tab)1.8 KB
agents/ap-feature-coordinator.md (opens in a new tab)1.8 KB
agents/ap-framework-generator.md (opens in a new tab)1.8 KB
agents/ap-framework-validator.md (opens in a new tab)1.8 KB
agents/ap-fresh-verifier.md (opens in a new tab)1.8 KB
agents/ap-goal-checker.md (opens in a new tab)1.8 KB
agents/ap-implementer.md (opens in a new tab)1.8 KB
agents/ap-independent-checker.md (opens in a new tab)3.4 KB
agents/ap-intake.md (opens in a new tab)1.7 KB
agents/ap-janitor.md (opens in a new tab)1.8 KB
Show 42 more
PathSize
agents/ap-juror.md (opens in a new tab)1.8 KB
agents/ap-manager.md (opens in a new tab)1.8 KB
agents/ap-planner.md (opens in a new tab)1.8 KB
agents/ap-preflight-probe.md (opens in a new tab)1.7 KB
agents/ap-re-anchor.md (opens in a new tab)1.7 KB
agents/ap-researcher.md (opens in a new tab)1.7 KB
agents/ap-reviewer.md (opens in a new tab)1.8 KB
agents/ap-roadmap-author.md (opens in a new tab)2.5 KB
agents/ap-roadmap-scout.md (opens in a new tab)2.2 KB
agents/ap-route-analyst.md (opens in a new tab)3.6 KB
agents/ap-run-coordinator.md (opens in a new tab)2.8 KB
agents/ap-scope-coordinator.md (opens in a new tab)1.8 KB
agents/ap-scoper.md (opens in a new tab)1.8 KB
agents/ap-scribe.md (opens in a new tab)1.7 KB
agents/ap-sweep-coordinator.md (opens in a new tab)1.8 KB
agents/ap-sweeper.md (opens in a new tab)1.8 KB
agents/ap-synthesizer.md (opens in a new tab)1.8 KB
agents/ap-verifier.md (opens in a new tab)1.8 KB
agents/ap-work-group-manager.md (opens in a new tab)2.4 KB
agents/ap-worker.md (opens in a new tab)3.5 KB
frameworks/QUICKSTART.md (opens in a new tab)3 KB
frameworks/README.md (opens in a new tab)6.7 KB
frameworks/apply.md (opens in a new tab)2.5 KB
frameworks/backend-build.md (opens in a new tab)5.2 KB
frameworks/backend-fix.md (opens in a new tab)6.1 KB
frameworks/backend-implement.md (opens in a new tab)5.7 KB
frameworks/composition.md (opens in a new tab)4.3 KB
frameworks/docs.md (opens in a new tab)4.5 KB
frameworks/frontend-build.md (opens in a new tab)5.2 KB
frameworks/frontend-fix.md (opens in a new tab)5.9 KB
frameworks/frontend-implement.md (opens in a new tab)5.7 KB
frameworks/frontend-review.md (opens in a new tab)4.2 KB
frameworks/generation.md (opens in a new tab)4.5 KB
frameworks/plan-design.md (opens in a new tab)5.2 KB
frameworks/plan-research.md (opens in a new tab)5.7 KB
frameworks/plan-scope.md (opens in a new tab)4.7 KB
frameworks/polish.md (opens in a new tab)5.7 KB
frameworks/refactor.md (opens in a new tab)5.8 KB
headless.patch.yml (opens in a new tab)72.5 KB
native-projection.json (opens in a new tab)39.3 KB
role-policy.json (opens in a new tab)92.6 KB
role-policy.schema.json (opens in a new tab)18.8 KB

Copies

More from Spielewoy/autoprompt-skill

SkillWhat it can touchPattern checkLicenceUpdated
ap-arbiterReport the compatibility redirect to `ap-independent-checker`; this retired role cannot perform new work.
  • Runs shell commands
  • +1 more

Pattern check: 1 item to reviewMITUpdated 7 Sept 2026

  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT7 Sept 2026
ap-depth-proberReport the compatibility redirect to `ap-worker`; this retired role cannot perform new work.
  • Runs shell commands
  • +1 more

Pattern check: 1 item to reviewMITUpdated 7 Sept 2026

  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT7 Sept 2026
ap-execharness-resolverReport the compatibility redirect to `ap-worker`; this retired role cannot perform new work.
  • Runs shell commands
  • +1 more

Pattern check: 1 item to reviewMITUpdated 7 Sept 2026

  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT7 Sept 2026
ap-feature-coordinatorReport the compatibility redirect to `ap-run-coordinator`; this retired role cannot perform new work.
  • Runs shell commands
  • +1 more

Pattern check: 1 item to reviewMITUpdated 7 Sept 2026

  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT7 Sept 2026
ap-framework-generatorReport the compatibility redirect to `ap-worker`; this retired role cannot perform new work.
  • Runs shell commands
  • +1 more

Pattern check: 1 item to reviewMITUpdated 7 Sept 2026

  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT7 Sept 2026
  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT7 Sept 2026
All skills in Spielewoy/autoprompt-skill

Other Coding & code review skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work

obra/superpowers

  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 12 Aug 2026

  • Runs shell commands
  • Reaches the network
Pattern check: Nothing flaggedMIT12 Aug 2026
  • Reaches the network
Pattern check: Nothing flaggedMIT23 Jul 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedMIT16 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedMIT8 Oct 2026