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.

referencessource-discovery.md

≈658 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Source Discovery

Use this guide during synthesis when obvious docs are shallow, stale, incomplete, or too polished to reveal real behavior.

Source Priority

Prefer sources in this order:

  1. Local repository authority: AGENTS.md, README.md, CONTRIBUTING.md, manifests, validators, scripts, tests, and existing neighboring skills.
  2. Primary upstream material: official specifications, product docs, API references, release notes, changelogs, and source code.
  3. Operational evidence: issue threads, PR discussions, CI failures, incident notes, support patterns, and migration notes.
  4. Historical evidence: commit logs, blame, reverted changes, and changelog diffs.
  5. Secondary summaries: blog posts, tutorials, and community examples.

Treat secondary and generated content as leads, not authority.

High-Signal Retrieval Passes

Run the passes that match the skill's risk:

  • Core behavior: official docs, source exports, public interfaces, happy-path examples.
  • Edge behavior: tests, fixtures, error handling, retries, permissions, validation, and cleanup paths.
  • Negative behavior: bug fixes, reverted commits, issue reports, support threads, review comments, and skipped tests.
  • Usage behavior: in-repo callers, downstream examples, configuration samples, and migration guides.
  • Maintenance behavior: changelog entries, release notes, deprecations, and commits touching the same files repeatedly.

Commit Log Mining

Use commit history when the task depends on lived behavior rather than only intended behavior.

Good candidates:

  • Security, access-control, CI, deployment, or migration skills.
  • Skills for internal systems with sparse public docs.
  • Skills being improved after repeated failures.
  • Areas with many regressions, reversions, or subtle edge cases.

Useful commands:

git log --oneline -- <path>
git log --stat -- <path>
git log -G '<behavior|symbol|error>' -- <path>
git blame <path>

Capture findings as source records with commit SHA, date, affected path, observed behavior, and whether the finding is adopted, rejected, or deferred.

Do not copy large commit messages or diffs into SKILL.md. Summarize the behavior and keep provenance in SOURCES.md or an evidence file.

Stop Conditions

Stop collecting when:

  • Required coverage dimensions are complete or have explicit next retrieval actions.
  • New retrieval mostly repeats known facts.
  • Remaining unknowns are low impact or require access the agent does not have.
  • The source mix includes both intended behavior and observed behavior for high-risk workflows.

Record the stopping rationale in SOURCES.md.

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.