infer-scope-from-code

Infer the v1 scope.yaml (selected / deferred / rejected capabilities plus depth caps, within-domain coverage gaps, and constraint trace) by scoring KB capabilities against scan-index.json signals during /codify. Bounds the selection to the domains already chosen in the domain-selection proposal and the profile posture from the project-profile proposal. Used exclusively by product-keeper in the /codify play.

跳到安装

仓库: kapilvirenahuja/garura
最近来源活动: 2026年7月3日 06:46
检测到的 SKILL.md 语言: 英语
星标: 3
分支: 0

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/kapilvirenahuja/garura --skill infer-scope-from-code

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

install-garura

Install Garura into a target project or repository so its skills, agents, and plays become discoverable by a host coding tool — Claude Code or the OpenAI Codex CLI. Reads this garura checkout's core/components and runs a per-tool ADAPTER that lays them down in the host's native shape: for claude, .claude/ skills + agents with model tiers resolved to Claude models; for codex, .agents/skills Agent Skills plus AGENTS.md and ~/.codex model/sandbox/approval profiles. Always writes a .garura/ tooling tree (config + STM scaffold) and copies shared memory to the machine-global ~/.garura, and records an install manifest so uninstall-garura can reverse exactly what was placed. Use when the user wants to install, set up, bootstrap, add, or enable Garura in another folder or repo for claude or codex — "install garura into X", "set up garura in this repo for codex", "bootstrap garura", "make codex see the garura skills". Takes the target path, an optional --tool, and an optional --scope (full = everything, the default; ha

2026-07-21

play-creator

Compile a deterministic "play" (a multi-step, gated workflow recipe) from an intent. Interviews for the intent triple, generates the expectation, identifies the skills, scripts, and agents the play needs, selects a workflow structure, generates evals, and emits a compiled play (a SKILL.md plus bundled scripts for its mechanical work). Use this whenever the user wants to create, build, compile, or review a play — or says "create a play", "new play", "compile this into a play", "play-creator", "turn this intent into a play", or "review my play for gaps" — even if they don't say the word "play" explicitly but are describing a repeatable, multi-step, checkpoint-gated workflow they want captured as a runnable recipe.

2026-07-21

play-editor

Modify an existing compiled play — change its goal, a constraint, a failure condition, a success scenario, a step, the workflow shape, or the agents/skills it uses — by editing the play's ICE source and recompiling, never by hand-patching the output into disagreement with its intent. This is the companion to play-creator (which makes new plays). Use this whenever the user wants to edit, change, modify, update, tweak, extend, or fix an existing play — or says "edit the play", "change this play", "add a constraint to the play", "the play needs a new failure condition / step / scenario", "play-editor", or "recompile the play after I changed its intent" — even if they don't say "play" outright but are clearly reshaping a workflow recipe that already exists.

2026-07-21

查看这个仓库的全部 Skills

name	infer-scope-from-code
description	Infer the v1 scope.yaml (selected / deferred / rejected capabilities plus depth caps, within-domain coverage gaps, and constraint trace) by scoring KB capabilities against scan-index.json signals during /codify. Bounds the selection to the domains already chosen in the domain-selection proposal and the profile posture from the project-profile proposal. Used exclusively by product-keeper in the /codify play.
version	0.1.0
user-invocable	false
model	sonnet
allowed-tools	Read, Write, Grep, Glob
deprecated	true
deprecated_note	#434 ProductOS realignment — superseded by the command model; retained for Phase E reference, not installed

infer-scope-from-code

Called by product-keeper during /codify after infer-domain-selection-from-code and infer-project-profile-from-code complete. Produces scope/scope.yaml at {stm_base}/{issue}/evidence/codify/proposals/scope/scope.yaml.

Purpose

During /codify (brownfield bootstrap), the scope artifact that /specify normally produces via configure-capabilities (KB walk + user decisions on optional capabilities) must instead be reverse-engineered from the existing codebase. This skill consumes scan-index.json plus the two prior proposals (domain-selection, project-profile) and emits a scope proposal grounded entirely in scan-index signals. It never invents evidence, never selects a capability outside the already-chosen domains, and always surfaces low-evidence items rather than silently rejecting them.

The capability universe is bounded by the intersection of:

selected_domains from the domain-selection proposal (narrows the KB walk)
KB capability listings under {kb_domain_dir}/{domain}.md (enumerated as ## Features blocks with IDs and Inclusion rules)

For every KB capability inside a selected domain, this skill scores scan-index evidence and classifies the capability as selected (high/medium evidence), deferred (low evidence, scaffolds only), or rejected (zero evidence). Capabilities whose KB Inclusion rule fires on profile posture but have no scan evidence go into within_domain_coverage_gaps — the code is silent on them, not absent.

Input

Receive from product-keeper via JSON contract.

scan_index_path (path, required) — scan-index.json produced by scan-codebase.
related_proposal_paths (list, required) — must contain the absolute paths to the already-emitted domain-selection.yaml and project-profile.yaml proposals. Validation halts if either is missing.
kb_domain_dir (path, required) — core/components/memory/knowledge/domain/. Drives the capability walk.
stm_base (path, required) — STM root resolved from .garura/core/config.yaml stm.base-path.
issue (str, required) — issue number driving /codify.

Signal (scan-index path)	Evidence rule
`patterns.framework_idioms[]`	Idiom match to the capability's KB "Signals" block (e.g. `auth-middleware` idiom → auth capability) → high. Indirect match (e.g. `orm` idiom → data-layer capability) → medium.
`patterns.naming_suffix_counts`	`Repository`/`Service`/`Controller`/`Handler` suffix counts inside a top-level module matching the capability's conceptual name → medium when count >= 3, low when 1-2.
`trees[].children` under `src/` or `app/`	Top-level module name matches capability slug or a synonym from the KB "Search patterns" line → medium (structural presence). No match → contributes nothing.
`git.churn_top[]`	A module already matched by `trees` appears in churn_top → upgrade match to high (active capability, not dormant). Absent from churn → match stays where it was (do not downgrade).
`manifests[].dependencies`	Specialized library declared (e.g. `stripe` → payments, `opensearch`/`elasticsearch` → search, `passport`/`next-auth` → auth, `socket.io` → realtime) → high for the unlocked capability.
`entry_points[]` and `config_files.ci`	Dedicated entry point or CI job for a capability's surface (e.g. `worker`, `migrate`, `seed`) → medium operational-presence signal.
`frontend_detection`	Presence of a frontend for UI-bearing capabilities (e.g. catalog, cart) — without it, those capabilities drop from high to medium.
`docs.readme_preview` / `docs.adrs`	Capability keyword hits in README or ADRs → medium documentation-presence signal (never alone sufficient for high).

infer-scope-from-code

安装方式

检查来源文件

infer-scope-from-code

Purpose

Input

infer-scope-from-code

Purpose

Input

Process

Output

Failure Modes

Boundaries

infer-scope-from-code

来源信息

安装方式

检查来源文件

同仓库更多 Skills

同仓库更多 Skills

infer-scope-from-code

Purpose

Input

infer-scope-from-code

Purpose

Input

Process

Output

Failure Modes

Boundaries