[research@ai4se] : ~ $
cd ../
[tools] | | 14 min

# The Nine Types of Claude Code Skills: From Personal Prompts to Org-Level Agent Capability

Anthropic's internal experience with hundreds of skills shows: a skill is not a Markdown prompt, it's an explorable capability package — verification skills should come before code-generation skills.

[claude-code][skills][tools]

In June 2026, Anthropic summarized the Claude Code team’s experience scaling to hundreds of skills. The key insight isn’t “how to write better Markdown” — it’s that skills are a combination of org-facing knowledge, executable scripts, verification workflows, context distribution, and governance mechanisms for agents.

In one sentence: Skills are the critical middle layer between “personal prompting tricks” and “org-level Agent Enablement.”

What a Skill Really Is: A Capability Package, Not a Single File

In Claude Code, a skill is a directory:

ComponentRole
SKILL.mdEntry point, trigger conditions, execution steps
references/API docs, internal conventions, edge cases
scripts/Validators, data fetchers, generators
assets/Templates, report skeletons
config.jsonTeam/environment configuration
hooksSafety constraints enabled on demand

The design focus isn’t “write a complete description” — it’s exposing context on demand. SKILL.md handles navigation; details unfold via filesystem-based progressive disclosure.

Anthropic’s Nine Types

#TypeProblem it solvesAI4SE meaning
1Library & API referenceInternal library/CLI/SDK usage and pitfallsCaptures senior engineers’ tacit API knowledge
2Product verificationHow to verify code actually worksTop priority; improves acceptance trustworthiness
3Data fetching & analysisConnecting to monitoring/analytics stacksMoves the agent from writing code into a “look at the facts” loop
4Business process automationStandups, tickets, weekly reportsOne-click team processes
5Code scaffoldingGenerating framework code per org conventionScaffolding for cases natural-language conditions + templates can’t cover
6Code quality & reviewOrg-level review rulesMoves review standards upstream into agent execution
7CI/CD & deploymentBuild, release, PR babysittingBridges the Inner Loop and the Outer Loop
8RunbooksMulti-tool troubleshooting from symptomsStructures operational experience
9Infrastructure opsRoutine infra and high-risk maintenancePairs with hooks to handle destructive operations

The most important observation: verification-type skills have the most measurable impact on output quality. What organizations care about isn’t “how much code the AI wrote,” but whether the code actually runs, whether state is consistent, and whether the agent can prove — in a repeatable way — that it completed the task.

Design Principles

Gotchas Are the Highest-Signal Content

Don’t write down what Claude already knows. High-value skills focus on:

  • Special conventions of internal systems
  • Fields, state machines, and permission boundaries that are easy to get wrong
  • Workflows that can only be verified with a specific tool/environment

Example: some table is append-only, so you can’t grab the “latest” row by created_at; a 200 in staging doesn’t mean the webhook was actually processed.

Description Is a Trigger, Not a Summary

Claude Code scans skill descriptions at startup to decide whether to invoke one. It should include: explicit trigger words, applicable task types, boundaries where it doesn’t apply, and natural-language phrasings a user might actually use.

Provide Constraints, but Also Flexibility

Avoid railroading: clearly state when it should/shouldn’t trigger, success criteria, optional paths, and fallbacks — don’t bake the context of a single task into a permanent rule.

On-Demand Hooks Fit High-Constraint Scenarios

Blocking DROP TABLE or force-push in production; enforcing smoke tests during a release window — temporarily raising the safety bar within a specific workflow, rather than a global hard constraint.

Distribution and Governance

ApproachFitsProsRisks
./.claude/skills (in-repo)Small teams, tightly project-boundFast to adopt, versioned with codeContext noise grows as it scales
Internal plugin marketplaceMulti-team, multi-repoInstall on demand, governableNeeds admission and lifecycle management

Recommended path: pilot in-repo first, then build a marketplace once skill count and reuse scope grow.

Anthropic’s lightweight governance: sandbox → Slack trial → traction → PR into marketplace — organic discovery rather than a centralized approval bottleneck.

Where Skills Sit in AI4SE

Skills fit best in the Middle Loop (review, verification, collaboration, process):

  • Turn team working methods into agent-executable steps
  • Move verification and review standards earlier in the development process
  • Migrate gotchas from individual heads into organizational assets

Relationship to Harness Engineering: Harness defines the five-dimension control over the agent’s operating environment; Skills are the reusable, distributable, measurable implementation of the Context dimension.

Pilot Priority Order

Don’t start by building an “all-purpose dev skill.” Suggested order:

  1. Verification skills for key business processes
  2. Reference skills for internal libraries/APIs
  3. Code review / testing practices skills
  4. CI/CD babysitting or deployment skills
  5. Business process automation skills

The skill library should be driven by real failures: collect AI failure samples → extract recurring gotchas → script the verification → pilot a small skill → observe trigger rate → then expand.

Measurable Metrics

MetricMeaning
Skill trigger countWhich processes have been agentified
Share of verification-skill usageWhether the shift is from “generation-first” to “verification-first”
Growth in gotchasWhether org knowledge keeps accumulating
Skill-related rework rateWhether review/QA rework is actually reduced

References