About

Imported from terminalskills/skills (skills/using-agent-skills/SKILL.md). Install upstream with npx skills add terminalskills/skills --skill using-agent-skills. Copyright stays with the author (MIT).

Using Agent Skills

Name: using-agent-skills
Author: terminalskills

Overview

Agent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.

Instructions

Skill Discovery

When a task arrives, identify the development phase and apply the corresponding skill:

Task arrives
    ├── Vague idea/need refinement? ──→ idea-refine
    ├── New project/feature/change? ──→ spec-driven-development
    ├── Have a spec, need tasks? ──────→ planning-and-task-breakdown
    ├── Implementing code? ────────────→ incremental-implementation
    │   ├── UI work? ─────────────────→ frontend-ui-engineering
    │   ├── API work? ────────────────→ api-and-interface-design
    │   └── Need better context? ─────→ context-engineering
    ├── Writing/running tests? ────────→ test-driven-development
    ├── Something broke? ──────────────→ debugging-and-error-recovery
    ├── Reviewing code? ───────────────→ code-review-and-quality
    ├── Committing/branching? ─────────→ git-workflow-and-versioning
    ├── Writing docs/ADRs? ───────────→ documentation-and-adrs
    └── Deploying/launching? ─────────→ shipping-and-launch

Core Operating Behaviors

1. Surface Assumptions — Before implementing anything non-trivial:

ASSUMPTIONS I'M MAKING:
1. [assumption about requirements]
2. [assumption about architecture]
→ Correct me now or I'll proceed with these.

2. Manage Confusion Actively — When encountering inconsistencies:

STOP — don't proceed with a guess
Name the specific confusion
Present the tradeoff or ask the clarifying question
Wait for resolution

3. Push Back When Warranted — Point out issues directly, explain concrete downsides, propose alternatives. Sycophancy is a failure mode.

4. Enforce Simplicity — Before finishing any implementation, ask:

Can this be done in fewer lines?
Are these abstractions earning their complexity?
Would a staff engineer say "why didn't you just..."?

5. Maintain Scope Discipline — Touch only what you're asked to touch. Don't "clean up" adjacent code, remove comments you don't understand, or add unspecified features.

6. Verify, Don't Assume — A task is not complete until verification passes. "Seems right" is never sufficient — there must be evidence.

Skill Rules

Check for an applicable skill before starting work. Skills encode processes that prevent common mistakes.
Skills are workflows, not suggestions. Follow the steps in order.
Multiple skills can apply. Chain them in sequence.
When in doubt, start with a spec.

Lifecycle Sequence

For a complete feature, the typical sequence:

1. idea-refine                 → Refine vague ideas
2. spec-driven-development     → Define what we're building
3. planning-and-task-breakdown → Break into verifiable chunks
4. context-engineering         → Load the right context
5. incremental-implementation  → Build slice by slice
6. test-driven-development     → Prove each slice works
7. code-review-and-quality     → Review before merge
8. documentation-and-adrs      → Document decisions
9. shipping-and-launch         → Deploy safely

Not every task needs every skill. A bug fix might only need: debugging → testing → review.

Examples

Quick Reference

Phase	Skill	Summary
Define	idea-refine	Divergent and convergent thinking
Define	spec-driven-development	Requirements before code
Plan	planning-and-task-breakdown	Small, verifiable tasks
Build	incremental-implementation	Thin vertical slices
Build	context-engineering	Right context at right time
Verify	test-driven-development	Failing test first
Review	code-review-and-quality	Five-axis quality review
Ship	git-workflow-and-versioning	Atomic commits, clean history
Ship	documentation-and-adrs	Document the why

Guidelines

Failure Modes to Avoid

Making wrong assumptions without checking
Plowing ahead when confused
Not surfacing inconsistencies you notice
Being sycophantic to approaches with clear problems
Overcomplicating code and APIs
Modifying code orthogonal to the task
Removing things you don't fully understand
Building without a spec because "it's obvious"
Skipping verification because "it looks right"

Red Flags

Starting implementation without checking for applicable skills
Skipping verification steps within a skill
Silently guessing when requirements are ambiguous
No spec exists for non-trivial work
Agent output doesn't match project conventions

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/terminalskills-skills-using-agent-skills/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

terminalskills-skills-using-agent-skills.ocm.jsonjson

{
  "ocm": "1",
  "id": "terminalskills-skills-using-agent-skills",
  "kind": "skill",
  "name": "using-agent-skills",
  "description": "Meta-skill for discovering and invoking the right agent skill for any task. Use when starting a session, when unsure which skill applies, or when you need to understand the development lifecycle and how skills chain together. Covers skill discovery, core operating behaviors, and failure modes to avoid.",
  "publisher": "terminalskills",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "agent-skills",
      "meta",
      "workflow",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Meta-skill for discovering and invoking the right agent skill for any task. Use when starting a session, when unsure which skill applies, or when you need to understand the development lifecycle and how skills chain together. Covers skill discovery, core operating behaviors, and failure modes to avoid."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/terminalskills/skills",
      "path": "skills/using-agent-skills/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/terminalskills/skills/blob/HEAD/skills/using-agent-skills/SKILL.md",
      "key": "terminalskills/skills/skills/using-agent-skills/SKILL.md"
    },
    "compatibility": "Any AI coding agent",
    "license": "MIT"
  },
  "instructions": "# Using Agent Skills\n\n## Overview\n\nAgent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.\n\n## Instructions\n\n### Skill Discovery\n\nWhen a task arrives, identify the development phase and apply the corresponding skill:\n\n```\nTask arrives\n    ├── Vague idea/need refinement? ──→ idea-refine\n    ├── New project/feature/change? ──→ spec-driven-development\n    ├── Have a spec, need tasks? ──────→ planning-and-task-br",
  "cost": {
    "context_tokens": 1179
  }
}

Fetch it by URL: GET /api/v1/registry/terminalskills-skills-using-agent-skills/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.