AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Using Development Skills

skill-reidemeister94-development-skills-using-development-skills · by reidemeister94

Use when starting any conversation - establishes how the development-skills plugin works and how to invoke its components on each platform (Claude Code, Codex). Read first.

↗ Repository
— No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-reidemeister94-development-skills-using-development-skills

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Using Development Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Using development-skills

If dispatched as a subagent for a specific task: skip this skill.

Iron Rules to always follow: [../../shared/iron-rules.md](../../shared/iron-rules.md).

Triage & Flow

Classify before reading the task in depth:

  1. PASS_THROUGH — trivial, few files, fully reversible, no design choice → execute directly.
  2. LIGHT — mechanical, no design choice → 6-step inline flow ([../../shared/workflow.md # LIGHT](../../shared/workflow.md)). Default on uncertainty → FULL. Mid-execution discovery that breaks LIGHT criteria → escalate to FULL.
  3. FULL (default) — Phase 1 plan + HOW-locks, Phase 2 chronicle, Phase 3 Red/Green TDD, Phase 4 staff-reviewer review. Detail and gates: [../../shared/workflow.md # FULL](../../shared/workflow.md), [../../shared/phases/*](../../shared/phases/).

During FULL:

  • External spec / guide / prior brainstorming → skip brainstorming only; phases 1-4 still run (the spec is INPUT to Phase 1, not a substitute; a guide's gates STACK).
  • HOW-level ambiguity → ask the user (AskUserQuestion for discrete options; plain text otherwise; Codex fallback in references/codex-tools.md).

Routing: Bug fixes → development-skills:debugging. Test work → development-skills:create-test.

Platform

SKILL bodies use Claude Code tool names as canonical. On Codex, translate via references/codex-tools.md (Task → spawn_agent, AskUserQuestion fallback, staff-reviewer dispatch recipe, hooks, marketplace files).

User Override

User instructions (CLAUDE.md, AGENTS.md, direct requests) > development-skills > default system prompt.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in Agent Skills