GravionLabs/elysion / .agents/skills/implementation
implementation
VerifiedRules for code changes: every change ships with tests, dispatches to <lang>-implementation. Use for implement, write code, add feature, test requests.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.3 KB |
| references/format.md | markdown | 9.6 KB |
| references/lint.md | markdown | 1.8 KB |
| references/runner-contract.md | markdown | 2.3 KB |
| references/specs.md | markdown | 1.2 KB |
| references/test-quality.md | markdown | 1.4 KB |
| schema/config.schema.json | config | 6.3 KB |
| schema/implementer.schema.json | config | 949 B |
| scripts/Format-Changed.ps1 | script | 18.8 KB |
| templates/spec.md | markdown | 607 B |
schema/config.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/GravionLabs/skills/main/skills/shared/implementation/schema/config.schema.json",
"title": "GravionLabs skills project config (.agents/config.json)",
"type": "object",
"additionalProperties": false,
"properties": {
"$schema": { "type": "string" },
"format": {
"description": "false disables every format and check call; a map replaces the built-in commands per language.",
"oneOf": [
{ "const": false },
{
"type": "object",
"additionalProperties": { "$ref": "#/$defs/formatEntry" }
}
]
},
"lint": {
"description": "false disables every lint call; a map replaces the built-in lint command per language.",
"oneOf": [
{ "const": false },
{
"type": "object",
"additionalProperties": { "$ref": "#/$defs/lintEntry" }
}
]
},
"governance": {
"description": "Architecture decisions and specs; read by adr, github-issue, planner, implementation, code-review, deliver, detect-techstack and the CI checks adr and spec of GravionLabs/ci.",
"type": "object",
"additionalProperties": false,
"properties": {
"adrDir": { "type": "string", "minLength": 1, "default": "docs/adr" },
"adrPaths": {
"description": "Globs of paths whose change needs an ADR.",
"type": "array",
"items": { "type": "string", "minLength": 1 },
"default": []
},
"specDir": { "type": "string", "minLength": 1, "default": "docs/specs" },
"specMap": {
"description": "Glob of source paths -> spec file.",
"type": "object",
"additionalProperties": { "type": "string", "minLength": 1 }
},
"specMode": { "enum": ["warn", "require"], "default": "warn" },
"skipLabels": {
"type": "array",
"items": { "type": "string", "minLength": 1 },
"default": ["skip-adr"]
}
}
},
"release": {
"description": "Release candidate and RC test; read by deliver (step 9) and github-release finish.",
"type": "object",
"additionalProperties": false,
"properties": {
"prerelease": {
"description": "Command that cuts a release candidate, e.g. gh workflow run release.yml --ref release/next -f prerelease=true.",
"type": "string",
"minLength": 1
},
"test": {
"type": "object",
"additionalProperties": false,
"properties": {
"platforms": {
"description": "Platforms of the RC test, e.g. [\"macOS\", \"Linux\", \"Windows\"]; with template, github-milestone create/insert makes the release-test issue.",
"type": "array",
"items": { "type": "string", "minLength": 1 },
"minItems": 1
},
"template": {
"description": "Body template of the release-test issue ({milestone}, {platforms}), e.g. docs/manual-acceptance.md or .github/release-test.md.",
"type": "string",
"minLength": 1
},
"gate": {
"description": "true: no release PR while the release-test issue is open (default false).",
"type": "boolean",
"default": false
}
}
}
}
},
"deliver": {
"description": "Settings of the deliver workflow.",
"type": "object",
"additionalProperties": false,
"properties": {
"loopThreshold": {
"description": "An interactive /deliver run with more PBIs than this starts the loop and stays a control session (default 3).",
"type": "integer",
"minimum": 1
},
"controlContextTokens": {
"description": "Context size at which the control session prints the status block and the resume command and stops (default 200000).",
"type": "integer",
"minimum": 1000
},
"roles": {
"description": "Model and effort per role; unset keys keep the defaults.",
"type": "object",
"additionalProperties": false,
"properties": {
"select": { "$ref": "#/$defs/role" },
"plan": { "$ref": "#/$defs/role" },
"create": { "$ref": "#/$defs/role" },
"implement": { "$ref": "#/$defs/tieredRole" },
"fix": { "$ref": "#/$defs/tieredRole" },
"gate": { "$ref": "#/$defs/role" },
"review": { "$ref": "#/$defs/role" },
"release-review": { "$ref": "#/$defs/role" },
"pr": { "$ref": "#/$defs/role" },
"ci": { "$ref": "#/$defs/role" }
}
}
}
}
},
"$defs": {
"role": {
"type": "object",
"additionalProperties": false,
"properties": {
"model": { "type": "string", "minLength": 1 },
"effort": { "enum": ["low", "medium", "high", "xhigh", "max"] }
}
},
"tieredRole": {
"type": "object",
"additionalProperties": false,
"properties": {
"model": { "type": "string", "minLength": 1 },
"effort": { "enum": ["low", "medium", "high", "xhigh", "max"] },
"tiers": {
"type": "object",
"additionalProperties": false,
"properties": {
"fast": { "$ref": "#/$defs/role" },
"standard": { "$ref": "#/$defs/role" },
"strong": { "$ref": "#/$defs/role" }
}
}
}
},
"commands": {
"oneOf": [
{ "type": "string", "minLength": 1 },
{ "type": "array", "minItems": 1, "items": { "type": "string", "minLength": 1 } }
]
},
"lintEntry": {
"type": "object",
"required": ["command"],
"additionalProperties": false,
"properties": {
"extensions": { "type": "array", "items": { "type": "string", "minLength": 1 } },
"command": { "$ref": "#/$defs/commands" }
}
},
"formatEntry": {
"type": "object",
"required": ["format"],
"additionalProperties": false,
"properties": {
"extensions": { "type": "array", "items": { "type": "string", "minLength": 1 } },
"format": { "$ref": "#/$defs/commands" },
"check": { "$ref": "#/$defs/commands" }
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |