[H1][OUTPUT-STYLE-BUILDER]
Dictum: Parsing clarity requires structured serialization.
Build agent response formats. Configure scope-based style.
[DELEGATE] Voice, formatting, constraint rules → style-standards skill.
Tasks:
- Read index.md — Reference file listing for navigation
- Select domain — FORMATS (structured data) or CONFIGURATION (response style scope)
- (formats) Read formats.md — Selection metrics, embedding, validation scoring
- (configuration) Read configuration.md — Scope hierarchy, embedding patterns
- (schema) Read schema.md — Delimiter syntax, canonical examples
- (structure) Read structure.md — Ordering patterns, composition
- (prose) Load
style-standards skill — Voice, formatting, constraints
- Execute per domain — Apply Guidance and Best-Practices
- Validate — Quality gate; see §VALIDATION
Scope:
- Formats: Structured data serialization (JSON, YAML, Markdown-KV, XML) for agent output.
- Configuration: Response style scope hierarchy (global → project → skill → command).
Domain Navigation:
- [FORMATS] — Structured data output. Load for: agent schemas, API responses, validation scoring.
- [CONFIGURATION] — Scope hierarchy. Load for: CLAUDE.md output sections, precedence rules.
- [SCHEMA] — Delimiters, examples. Load for: syntax reference, canonical patterns.
- [STRUCTURE] — Ordering, composition. Load for: section sequencing, chaining.
[REFERENCE]: index.md — Complete reference file listing
[1][FORMATS]
Dictum: Format optimization requires accuracy-token tradeoff analysis.
[IMPORTANT] Format choice impacts accuracy (16pp variance) and tokens (6.75x variance).
Guidance:
Selection — Markdown-KV: 60.7% accuracy, 2.7x tokens. JSON: 52.3% accuracy, 0.85x tokens.Embedding — Inline for single use. Reference (@.claude/styles/) for 3+ consumers.Validation — 100-point scoring. Deployment requires score >= 80.
Best-Practices:
- Single format per output type.
- Max 5 variables per format; every optional has default.
- Constrained decoding guarantees 97-100% schema compliance.
References:
[2][CONFIGURATION]
Dictum: Narrow context requires specialized output rules.
[IMPORTANT] Higher precedence overrides lower (command level 5 > global level 1).
Guidance:
Global — CLAUDE.md [OUTPUT] section. 50-100 LOC optimal.Project — PROJECT.md overrides. Document divergence reason.Skill/Agent — Inline or reference pattern. Match reuse requirements.Command — Narrowest scope. Specialized output for single invocation.
Best-Practices:
- Global rules in CLAUDE.md; overrides minimal (max 30 LOC).
- Reference
style-standards for voice/formatting rules—no duplication.
- Place weight-10 constraints first in all scopes.
References:
[3][SCHEMA]
Dictum: Performance consistency requires delimiter standardization.
[IMPORTANT] Maintain delimiter consistency throughout output.
Guidance:
Delimiters — Code fence (```), separator (---), soft break (<br>).Consistency — Prohibit mixed delimiter styles within single output.
References:
[4][STRUCTURE]
Dictum: Attention decay requires priority-first placement.
[IMPORTANT] Primacy effect assigns 5.79x weight to early items.
Guidance:
Ordering — Action-first, Priority-first, or Context-first patterns.Hierarchy — Maximum 3 levels. 2-7 items per container.Composition — Base-override inheritance. Shallow or deep merge.
References:
[5][TEMPLATES]
Dictum: Structural consistency requires scaffold reuse.
FORMATS Domain:
CONFIGURATION Domain:
[6][VALIDATION]
Dictum: Gates prevent incomplete artifacts.
[VERIFY] Completion:
[REFERENCE] Operational checklist: →validation.md
1---2name: output-style-builder3description: Creates structured output formats (JSON, YAML, Markdown-KV, XML) and response style configurations for Claude. Use when: (1) defining agent output schemas (.json, .yaml, .xml), (2) configuring response style scope hierarchy, (3) embedding formats in agents/commands, (4) building CLAUDE.md output sections, (5) creating format definitions in .claude/styles/, or (6) standardizing structured data serialization.4---5
6# [H1][OUTPUT-STYLE-BUILDER]
7>**Dictum:** *Parsing clarity requires structured serialization.*
8
9<br>
10
11Build agent response formats. Configure scope-based style.
12
13[DELEGATE] Voice, formatting, constraint rules → `style-standards` skill.
14
15**Tasks:**
161. Read [index.md](./index.md) — Reference file listing for navigation
172. Select domain — FORMATS (structured data) or CONFIGURATION (response style scope)
183. (formats) Read [formats.md](./references/formats.md) — Selection metrics, embedding, validation scoring
194. (configuration) Read [configuration.md](./references/configuration.md) — Scope hierarchy, embedding patterns
205. (schema) Read [schema.md](./references/schema.md) — Delimiter syntax, canonical examples
216. (structure) Read [structure.md](./references/structure.md) — Ordering patterns, composition
227. (prose) Load `style-standards` skill — Voice, formatting, constraints
238. Execute per domain — Apply Guidance and Best-Practices
249. Validate — Quality gate; see §VALIDATION
25
26**Scope:**
27- *Formats:* Structured data serialization (JSON, YAML, Markdown-KV, XML) for agent output.
28- *Configuration:* Response style scope hierarchy (global → project → skill → command).
29
30**Domain Navigation:**
31- *[FORMATS]* — Structured data output. Load for: agent schemas, API responses, validation scoring.
32- *[CONFIGURATION]* — Scope hierarchy. Load for: CLAUDE.md output sections, precedence rules.
33- *[SCHEMA]* — Delimiters, examples. Load for: syntax reference, canonical patterns.
34- *[STRUCTURE]* — Ordering, composition. Load for: section sequencing, chaining.
35
36[REFERENCE]: [index.md](./index.md) — Complete reference file listing
37
38---
39## [1][FORMATS]
40>**Dictum:** *Format optimization requires accuracy-token tradeoff analysis.*
41
42<br>
43
44[IMPORTANT] Format choice impacts accuracy (16pp variance) and tokens (6.75x variance).
45
46**Guidance:**
47- `Selection` — Markdown-KV: 60.7% accuracy, 2.7x tokens. JSON: 52.3% accuracy, 0.85x tokens.
48- `Embedding` — Inline for single use. Reference (`@.claude/styles/`) for 3+ consumers.
49- `Validation` — 100-point scoring. Deployment requires score >= 80.
50
51**Best-Practices:**<br>
52- Single format per output type.
53- Max 5 variables per format; every optional has default.
54- Constrained decoding guarantees 97-100% schema compliance.
55
56**References:**<br>
57- [→formats.md](./references/formats.md): Selection, embedding, validation.
58- [→format.template.md](./templates/format.template.md): Format scaffold.
59
60---
61## [2][CONFIGURATION]
62>**Dictum:** *Narrow context requires specialized output rules.*
63
64<br>
65
66[IMPORTANT] Higher precedence overrides lower (command level 5 > global level 1).
67
68**Guidance:**
69- `Global` — CLAUDE.md `[OUTPUT]` section. 50-100 LOC optimal.
70- `Project` — PROJECT.md overrides. Document divergence reason.
71- `Skill/Agent` — Inline or reference pattern. Match reuse requirements.
72- `Command` — Narrowest scope. Specialized output for single invocation.
73
74**Best-Practices:**<br>
75- Global rules in CLAUDE.md; overrides minimal (max 30 LOC).
76- Reference `style-standards` for voice/formatting rules—no duplication.
77- Place weight-10 constraints first in all scopes.
78
79**References:**<br>
80- [→configuration.md](./references/configuration.md): Scope hierarchy, embedding.
81- [→style.template.md](./templates/style.template.md): Style scaffold.
82- [DELEGATE] `style-standards` skill: Voice, formatting, constraints.
83
84---
85## [3][SCHEMA]
86>**Dictum:** *Performance consistency requires delimiter standardization.*
87
88<br>
89
90[IMPORTANT] Maintain delimiter consistency throughout output.
91
92**Guidance:**
93- `Delimiters` — Code fence (` ``` `), separator (`---`), soft break (`<br>`).
94- `Consistency` — Prohibit mixed delimiter styles within single output.
95
96**References:**<br>
97- [→schema.md](./references/schema.md): Syntax reference.
98
99---
100## [4][STRUCTURE]
101>**Dictum:** *Attention decay requires priority-first placement.*
102
103<br>
104
105[IMPORTANT] Primacy effect assigns 5.79x weight to early items.
106
107**Guidance:**
108- `Ordering` — Action-first, Priority-first, or Context-first patterns.
109- `Hierarchy` — Maximum 3 levels. 2-7 items per container.
110- `Composition` — Base-override inheritance. Shallow or deep merge.
111
112**References:**<br>
113- [→structure.md](./references/structure.md): Sequencing, composability.
114
115---
116## [5][TEMPLATES]
117>**Dictum:** *Structural consistency requires scaffold reuse.*
118
119<br>
120
121**FORMATS Domain:**<br>
122- [→format.template.md](./templates/format.template.md): Structured data format scaffold.
123
124**CONFIGURATION Domain:**<br>
125- [→style.template.md](./templates/style.template.md): Response style scaffold.
126
127---
128## [6][VALIDATION]
129>**Dictum:** *Gates prevent incomplete artifacts.*
130
131<br>
132
133[VERIFY] Completion:
134- [ ] Domain: Selected FORMATS or CONFIGURATION scope.
135- [ ] References: Required domain files loaded per Tasks.
136- [ ] Style: `style-standards` delegation applied—zero duplication.
137- [ ] Format: Validation score >= 80 (formats domain).
138- [ ] Quality: LOC within limits, weight-10 constraints first.
139
140[REFERENCE] Operational checklist: [→validation.md](./references/validation.md)
majiayu000