All skills
getsentry avatar

/skill-writer

@5a64b36 official
by Sentrygetsentry/skills1k stars
53

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source capture, precision passes, authoring, registration, and validation.

Use this Skill: https://skilld.dev/gh/getsentry/skills/skill-writer

This session only. Nothing lands on disk.

referencesreference-architecture.md

≈635 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Reference Architecture

Use this guide before adding bundled files or long sections to SKILL.md.

Router Rule

  • SKILL.md is the router.
  • References are flat lookup leaves under references/.
  • SPEC.md is the maintenance contract.
  • SOURCES.md stores provenance and decisions.

Lookup Test

Before creating a reference, finish this sentence:

  • "I need to decide X, so read ...."
  • "I need to do Y, so read ...."
  • "I need to diagnose Z, so read ...."

If the sentence sounds like "I need context" or "I need patterns", the file is too vague.

Placement Table

Put it in... When it belongs there
SKILL.md every run needs it
references/ only some branches need it; keep runtime references as direct children
SPEC.md it explains maintenance, scope, or evidence policy
SOURCES.md it is provenance, a decision record, or a gap

Reference Types

Need Shape
choose a path decision guide
execute a procedure task guide
look up exact facts reference table
diagnose a failure troubleshooting matrix
imitate quality example set
judge completeness validation checklist

Naming Rules

  • Name files for the question or action they answer.
  • Good: mode-selection.md, output-contracts.md, routing-workflows.md
  • Bad: notes.md, context.md, patterns.md, research.md
  • Prefer flat filenames over nested reference folders.
  • When related references cover parallel variants of one lookup need, keep them as sibling files with a shared prefix plus an explicit differentiator.
  • List every runtime reference directly in SKILL.md.

Split Rules

Create a new reference when:

  • the content is only needed after a branch decision
  • the content has one dominant type
  • the section would make SKILL.md harder to scan
  • the file is approaching 100 lines and contains multiple lookup needs
  • the resulting file can be named as a direct child of references/ with a clear lookup reason

Keep content in SKILL.md when:

  • every invocation needs it
  • it is short
  • moving it would force unnecessary file loads

Final Checks

  1. Every runtime reference has a direct "open when..." reason in SKILL.md.
  2. The filename tells the agent why to open it.
  3. No required instruction is hidden only in an optional reference.
  4. No reference has become a second SKILL.md.
  5. No nested reference folder is introduced unless the content is non-runtime evidence or static assets.

Source: SKILL.md on GitHub

No alerts17d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    The skill is a comprehensive meta-router and workflow guide for creating, updating, and evaluating agent skills. It includes a helper python script for structural validation and standard markdown templates, presenting no security risks.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    5/19 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 5a64b36. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 months ago
  • Documentation
  • skill-authoring
  • workflow
  • specification
  • synthesis
  • iteration
  • validation
  • prompt-engineering
  • agent-skills

README badge

README badge for getsentry/skills/skill-writer

Guides AI agents through a structured workflow for creating, updating, and iterating on agent skills—instruction files that extend AI coding capabilities. Includes reference files for synthesis, authoring, validation, and skill registration following the Agent Skills specification.

Generated from the current SKILL.md.

Does this skill help me write skills for Claude, or does it help Claude write skills?
This skill is loaded into Claude or another AI coding agent. It provides the agent with a standardized workflow, reference files, and decision trees for creating, updating, and iterating on skills that other agents can use.
What's the difference between create, update, synthesize, and iterate modes?
Create starts from scratch. Update modifies an existing skill. Synthesize gathers and structures source material before authoring. Iterate improves a skill based on positive, negative, or fix examples.
Do I need to read all the reference files?
No. The skill uses a step-by-step workflow that loads only the specific reference files needed for your operation. Start with mode-selection.md to determine your path, then load only the files it directs you to.
Can I use this skill to write skills for other AI providers, or only Claude?
The skill supports both provider-agnostic skills and Claude-specific mechanics. Provider-specific references are optional; the core workflow and execution shapes are portable across agents.
What does a completed skill output look like?
A skill consists of a SKILL.md file (the runtime router), optional focused reference files under references/, a SPEC.md for the maintenance contract, and optional scripts or templates. The skill-writer guides you through all artifact types and decides what belongs in each.

Generated from the current SKILL.md. These answers refresh after source changes.