AGENT SKILL

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

License 许可
MIT
最近更新
2026-06-06
Stars
★ 0
Forks
0

01 前言 Front Matter

name
write-a-skill
license
MIT
metadata
{ "voice": "Matt Pocock — direct, concrete, imperative, example-driven", "version": "1.0.0", "derived_from": "https://github.com/mattpocock/skills/tree/main/skills/productivity/write-a-skill", "original_author": "Matt Pocock (@mattpocock)", "original_license": "MIT" }
description
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

02 资源文件 7

03 SKILL.md 正文

Writing Skills

Derived from Matt Pocock's write-a-skill (MIT). Matt's voice and 3-phase workflow preserved verbatim. Additions: validation tools + references + cs-* wrapper (see Tooling + Companions below).

Process

  1. Gather requirements - ask user about:

    • What task/domain does the skill cover?
    • What specific use cases should it handle?
    • Does it need executable scripts or just instructions?
    • Any reference materials to include?
  2. Draft the skill - create:

    • SKILL.md with concise instructions
    • Additional reference files if content exceeds 500 lines
    • Utility scripts if deterministic operations needed
  3. Review with user - present draft and ask:

    • Does this cover your use cases?
    • Anything missing or unclear?
    • Should any section be more/less detailed?

Skill Structure

skill-name/
├── SKILL.md           # Main instructions (required)
├── REFERENCE.md       # Detailed docs (if needed)
├── EXAMPLES.md        # Usage examples (if needed)
└── scripts/           # Utility scripts (if needed)
    └── helper.js

SKILL.md Template

---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---

# Skill Name

## Quick start

[Minimal working example]

## Workflows

[Step-by-step processes with checklists for complex tasks]

## Advanced features

[Link to separate files: See [REFERENCE.md](REFERENCE.md)]

Description Requirements

The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.

Goal: Give your agent just enough info to know:

  1. What capability this skill provides
  2. When/why to trigger it (specific keywords, contexts, file types)

Format:

  • Max 1024 chars
  • Write in third person
  • First sentence: what it does
  • Second sentence: "Use when [specific triggers]"

Good example:

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.

Bad example:

Helps with documents.

The bad example gives your agent no way to distinguish this from other document skills.

When to Add Scripts

Add utility scripts when:

  • Operation is deterministic (validation, formatting)
  • Same code would be generated repeatedly
  • Errors need explicit handling

Scripts save tokens and improve reliability vs generated code.

When to Split Files

Split into separate files when:

  • SKILL.md exceeds 100 lines
  • Content has distinct domains (finance vs sales schemas)
  • Advanced features are rarely needed

Review Checklist

After drafting, verify:

  • [ ] Description includes triggers ("Use when...")
  • [ ] SKILL.md under 100 lines
  • [ ] No time-sensitive info
  • [ ] Consistent terminology
  • [ ] Concrete examples included
  • [ ] References one level deep

Tooling + Companions

Validation tools + cs-* wrapper sit alongside this skill. Run all 6 review-checklist items programmatically:

python scripts/skill_review_checklist_runner.py path/to/skill-folder

See references/companion_tooling.md for the tool catalogue, cs-skill-author persona agent, and /cs:write-a-skill slash command.


Version: 1.0.0 Derived: Matt Pocock (MIT) + this repo's wrapper

04 同仓库更多 Skills

AdmiralGallade
AdmiralGallade/harness-repository

verify-sign

Add an Artifact Verification (SscaArtifactVerification) step to an existing Harness pipeline to verify Cosign signatures on container or local-stage artifacts. Supports CI, Security, and CD Deploy (containerized step group). Supports Third-Party registries (Docker, ECR, GCR, GAR, ACR), Harness Artifact Registry (HAR), and Harness Local Stage artifacts. Only works with existing pipelines. Use when asked to verify signed artifacts, verify artifact signature, verify-sign, validate Cosign signature, or configure SscaArtifactVerification. Trigger phrases: verify sign, verify artifact, artifact verification, verify signature, verify-sign, SscaArtifactVerification, verify signed image, verify Cosign, HAR verification.

★ 0
AdmiralGallade
AdmiralGallade/harness-repository

template-usage

Track Harness template dependencies, usage, and adoption via MCP v2 tools. Find which pipelines or other templates reference a given template, analyze update impact, identify unused templates, and compare version adoption. Use when asked about template usage, template references, template dependencies, impact analysis before updating a template, finding unused templates, or tracking template adoption across projects. Trigger phrases: template usage, who uses template, template references, template dependencies, template impact, unused templates, template adoption. Do NOT use for creating or updating templates (use create-template instead).

★ 0
AdmiralGallade
AdmiralGallade/harness-repository

sign-artifact

Add an Artifact Signing (SscaArtifactSigning) step to an existing Harness pipeline to Cosign-sign container or local-stage artifacts with keyless, key-based, or Vault signing. Supports Third-Party registries (Docker, ECR, GCR, GAR, ACR), Harness Artifact Registry (HAR), and Harness Local Stage artifacts. Place after image build/push; optionally upload .sig to the registry. Only works with existing pipelines. Use when asked to sign artifacts, add artifact signing, Cosign sign image, attach signature to registry, or configure SscaArtifactSigning. Trigger phrases: sign artifact, artifact signing, sign image, Cosign sign, add signing step, SscaArtifactSigning, attach signature, sign container image, HAR signing.

★ 0
AdmiralGallade
AdmiralGallade/harness-repository

sei-analytics

Advanced engineering analytics via Harness Software Engineering Insights (SEI) MCP. Configure sprint velocity and estimation accuracy tracking, engineering investment allocation breakdowns, sprint planning with capacity forecasts, and release readiness assessments. Use when asked about sprint analytics, investment allocation, sprint planning, capacity forecasting, or release readiness. Do NOT use for DORA metrics (use dora-metrics instead). Trigger phrases: sprint velocity, sprint analytics, investment allocation, capacity planning, sprint forecast, release readiness, engineering productivity, estimation accuracy, sprint planning, scope creep, code quality trends.

★ 0
AdmiralGallade
AdmiralGallade/harness-repository

security-report

Generate security compliance reports using Harness SCS and STO via MCP. Analyze vulnerabilities, SBOMs, and manage exemptions. Use when user says "security report", "vulnerabilities", "SBOM", "security scan", "compliance check", or asks about application security.

★ 0
AdmiralGallade
AdmiralGallade/harness-repository

scorecard-review

Review service maturity scorecards and compliance using Harness IDP via MCP. Check production readiness, security, and documentation scores. Use when user says "scorecard", "service maturity", "production readiness", "compliance score", or asks about service health scores.

★ 0