AgentSkillsCN

patterns

当您识别工作中或数据中的反复出现的主题、发掘其中的规律，或在提及“模式”“反复”“重复”时，可运用此技能。有关具体实施方法，请参阅“编码技能”。

SKILL.md
--- frontmatter
name: patterns
description: This skill should be used when recognizing recurring themes, identifying patterns in work or data, or when "pattern", "recurring", or "repeated" are mentioned. For implementation, see codify skill.
metadata:
  version: "1.1.0"
  related-skills:
    - codify
    - codebase-recon
    - report-findings

Pattern Identification

Observe signals → classify patterns → validate with evidence → document findings.

Steps

  1. •Collect signals from conversation, code, or data
  2. •Classify pattern type (workflow, orchestration, heuristic, anti-pattern)
  3. •Validate against evidence threshold (3+ instances, multiple contexts)
  4. •Document pattern with constraints and examples
  5. •If implementation needed, delegate by loading the outfitter:codify skill

<when_to_use>

  • •Recognizing recurring themes in work or data
  • •Codifying best practices from experience
  • •Extracting workflows from repeated success
  • •Identifying anti-patterns from repeated failures
  • •Building decision frameworks from observations

NOT for: single occurrences, unvalidated hunches, premature abstraction

</when_to_use>

<signal_identification>

Watch for these signal categories:

CategoryWatch ForIndicates
SuccessCompletion, positive feedback, repetition, efficiencyPattern worth codifying
FrustrationBacktracking, clarification loops, rework, confusionAnti-pattern to document
WorkflowSequence consistency, decision points, quality gatesProcess pattern
OrchestrationMulti-component coordination, state management, routingCoordination pattern

See signal-types.md for detailed taxonomy.

</signal_identification>

<pattern_classification>

Four primary pattern types:

TypeCharacteristicsUse When
WorkflowSequential stages, clear transitions, quality gatesProcess has ordered steps
OrchestrationCoordinates components, manages state, routes workMultiple actors involved
HeuristicCondition → action mapping, context-sensitiveRepeated decisions
Anti-PatternCommon mistake, causes rework, has better alternativePreventing failures

See pattern-types.md for templates and examples.

</pattern_classification>

<evidence_thresholds>

Codification Criteria

Don't codify after first occurrence. Require:

  • •3+ instances — minimum repetition to establish pattern
  • •Multiple contexts — works across different scenarios
  • •Clear boundaries — know when to apply vs not apply
  • •Measurable benefit — improves outcome compared to ad-hoc approach

Quality Indicators

Strong PatternWeak Pattern
Consistent structureVaries each use
Transferable to othersRequires specific expertise
Handles edge casesBreaks on deviation
Saves time/effortOverhead exceeds value

</evidence_thresholds>

<progressive_formalization>

Observation (1-2 instances):

  • •Note for future reference
  • •"This worked well, watch for recurrence"

Hypothesis (3+ instances):

  • •Draft informal guideline
  • •Test consciously in next case

Codification (validated pattern):

  • •Create formal documentation
  • •Include examples and constraints

Refinement (ongoing):

  • •Update based on usage
  • •Add edge cases

</progressive_formalization>

<workflow>

Loop: Observe → Classify → Validate → Document

  1. •Collect signals — note successes, failures, recurring behaviors
  2. •Classify pattern type — workflow, orchestration, heuristic, anti-pattern
  3. •Check evidence threshold — 3+ instances? Multiple contexts?
  4. •Extract quality criteria — what makes it work?
  5. •Document pattern — name, when, what, why
  6. •Test deliberately — apply consciously, track variance
  7. •Refine — adjust based on feedback
</workflow> <rules>

ALWAYS:

  • •Require 3+ instances before codifying
  • •Validate across multiple contexts
  • •Document both when to use AND when not to
  • •Include concrete examples
  • •Track pattern effectiveness over time

NEVER:

  • •Codify after single occurrence
  • •Abstract without evidence
  • •Ignore context-sensitivity
  • •Skip validation step
  • •Assume transferability without testing
</rules> <references>

Identification vs Implementation:

  • •This skill (patterns) identifies and documents patterns
  • •codify skill implements patterns as Claude Code components (skills, commands, hooks, agents)

Use patterns to answer "what patterns exist?" Use codify to answer "how do I turn this into a reusable component?"

</references>