원클릭으로 Manus에서 모든 스킬 실행

ai-spec

스타1

포크0

업데이트2026년 7월 12일 17:22

Render a topic's surviving findings into an AI-ready, agent-executable architecture spec. A genre-shaping of the artifact -> Markdown pipeline (not a new mechanism) — finding_refs become grounded evidence sections, the goal's completion checks become EARS acceptance criteria, and the artifact sections become the document structure. Use to turn research into a buildable spec a downstream coding agent executes.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

modeled-information-format

modeled-information-format/research-harness-template

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Channel: AI-Ready Spec

Delivery adapter (SPEC §6d, §10). Turns a topic's research into a buildable spec for a downstream AI coding agent. The channel owns delivery (artifact -> document); a spec-genre skill (ai-architecture-doc / feature-spec / kiro-requirements / kiro-design / kiro-tasks, each an external mif-docs-plugin skill per ADR-0018) owns shape. Build on the existing artifact.json -> Markdown pipeline; this is a genre-shaping of that path, not a parallel one.

Inputs

reports/<topic>/findings/*.json — surviving findings (verdict != falsified).
reports/<topic>/goal.json — completion_condition.checks[] become the acceptance criteria.
reports/<topic>/ontology-map.json — per-finding resolved type, for the entity-catalog grounding.
The selected spec genre (default ai-architecture-doc).

Procedure

Select — gather surviving and weakened findings for the topic; resolve their ontology types so entity-catalog rows carry their grounding.
Synthesize — run scripts/synthesize-artifact.sh <findings-dir> <genre> <artifact.json> with the chosen genre, so artifact.json carries genre, finding_refs[] for every cited finding, and sections[] for the taxonomy.
Shape (genre) — apply the genre skill's section taxonomy and frontmatter contract:
- finding_refs[] → grounded evidence sections (every design claim carries a finding_ref or a named external standard).
- goal completion_condition.checks[] → EARS acceptance criteria (WHEN … SHALL … + the check's verify command as the executable test).
- artifact.sections[] → the document structure.
- when an ontology pack is bound, render its entity inventory as a grounded entity-catalog section and its inter-type relationships as a relationship-model section, each row naming its source vocabulary.
Render — deterministically write the spec to the <out.md> path passed to render-artifact.sh (same findings -> byte-identical Markdown). Default output paths, so switching --genre never overwrites a sibling spec:
- ai-architecture-doc (default): reports/<topic>/<topic>-build-spec.md
- feature-spec: reports/<topic>/<topic>-feature-build-spec.md
- kiro-requirements: reports/<topic>/<topic>-kiro-requirements.md
- kiro-design: reports/<topic>/<topic>-kiro-design.md
- kiro-tasks: reports/<topic>/<topic>-kiro-tasks.md
Carry MIF frontmatter + the genre markers (genre, audience: implementer, status, evidence_base).
Gate — the spec must pass markdownlint-cli2 with zero errors; every evidence row must carry a citation; the body carries no internal urn:mif: identity.

Greenfield vs brownfield

status: proposed for a greenfield build (work not yet done). To document/affirm an existing build, use the worked-specimen framing ("these artifacts already exist") — same genre, same taxonomy, status and the objective framing differ.

The Kiro three-document set

kiro-requirements, kiro-design, and kiro-tasks are three independently selectable genres (matching how mif-docs-plugin ships them), not one combined genre — a caller wanting the full Kiro spec set for one feature runs this channel three times, once per genre, against the same findings. This replaced a single bundled kiro-spec pack (research-harness-template#409); see that story and ADR-0018 for the rationale.

Output

The agent-consumable spec, written to the <out.md> path given to render-artifact.sh, at the default path named for its genre above unless overridden. A companion worked specimen (the genre rendered end-to-end for a concrete subject) proves the genre is real output, not just described.

Dependencies

scripts/synthesize-artifact.sh, scripts/render-artifact.sh, an enabled mif-docs-plugin spec-genre skill (harness.config.json packs[], marketplace-ref against the mif-docs marketplace), schemas/artifact.schema.json, reports/<topic>/goal.json.

이 저장소의 다른 Skills

같은 저장소

continuous-monitor

modeled-information-format/research-harness-template

Unattended, scheduled monitoring of external sources (arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed, bioRxiv/medRxiv, GDELT, Hacker News) for operator-selected current-events DOMAINS (monitoringDomains[], weighted, momentum-ranked, digest output) or for a research topic (the topic-bound special case), gated end to end through a mandatory human Editorial Gate before anything publishes. An OPTIONAL methodology pack (enable the `continuous-monitor` pack AND configure a domain or a topic's continuousMonitoring block). Use this skill when the user wants to enable, inspect, or manually run continuous monitoring for a domain or topic, review a run's digest or candidate recommendations, or check the Continuity Log for a skipped/failed source. Triggers on 'continuous monitoring', 'monitor this domain', 'monitor this topic', 'monitoring digest', 'schedule research monitoring', 'check for new sources', 'run the monitoring pipeline', 'review monitoring recommendations'.

2026-07-213

publish-blog

modeled-information-format/research-harness-template

Render surviving research findings into a publishable blog post through the typed findings-to-artifact contract. A first-class harness output (not a pack). Use this skill when the user wants to turn research into a blog post, publish findings, draft an article from the corpus, or write up what the research found. Triggers on 'publish blog', 'blog post from research', 'write up these findings', 'draft an article', 'turn this into a post'.

2026-07-203

book-author

modeled-information-format/research-harness-template

Render surviving research findings into a book chapter through the typed findings-to-artifact contract. An OPTIONAL channel pack (enable the `book` pack to use it), supporting the full genre range. Use this skill when the user wants to author a book, write a chapter from the research, turn the corpus into long-form, or build a manuscript. Triggers on 'write a book', 'author a chapter', 'book from research', 'turn this into a chapter', 'long-form from the corpus', 'manuscript'.

2026-07-203

ontology-manager

modeled-information-format/research-harness-template

Create, validate, inspect, and convert MIF ontology definition files. Use when the user asks to: create a new ontology, scaffold an ontology, validate an ontology YAML, inspect ontology contents (entities, traits, relationships, namespaces, discovery patterns), convert between YAML and JSON formats, convert to JSON-LD, or get guidance on MIF ontology structure. Triggers on: "ontology", "create ontology", "validate ontology", "inspect ontology", "convert ontology", "ontology schema", "entity types", "traits", "discovery patterns", "namespace hierarchy".

2026-07-143

diataxis-docs

modeled-information-format/research-harness-template

Render a research topic's entire surviving findings corpus into a COMPLETE Diátaxis documentation set — a reference page per finding, a per-dimension explanation, how-to, and guided tutorial, plus landing/index pages — every page carrying MIF Level-1 frontmatter and a diataxis_type marker. An OPTIONAL channel pack (enable the `diataxis` pack). Use this skill when the user wants documentation for a research topic, a full docs set from the findings, or to publish the corpus as Diátaxis docs. Triggers on 'diataxis docs', 'documentation channel', 'render docs from research', 'document the findings', 'reference and explanation docs', 'generate the docs site'.

2026-07-143

modeled-information-format/research-harness-template

Search the MIF research index — find findings by free-text query or by structured filters over the index fields (dimension, tags, namespace, verdict). Use this skill when the user wants to find research findings, look up what is known about a subject, query findings, or asks 'what do I have on X', 'find findings about Y', 'search research for Z', 'what research', 'what findings'. Reads the projected index, not raw tag files.

2026-07-053

name	ai-spec
description	Render a topic's surviving findings into an AI-ready, agent-executable architecture spec. A genre-shaping of the artifact -> Markdown pipeline (not a new mechanism) — finding_refs become grounded evidence sections, the goal's completion checks become EARS acceptance criteria, and the artifact sections become the document structure. Use to turn research into a buildable spec a downstream coding agent executes.
version	0.13.0
argument-hint	<topic> [--genre ai-architecture-doc\|feature-spec\|kiro-requirements\|kiro-design\|kiro-tasks] [-o <out.md>]
allowed-tools	Read, Write, Bash, Glob, Grep

Channel: AI-Ready Spec

Inputs

reports/<topic>/findings/*.json — surviving findings (verdict != falsified).
reports/<topic>/goal.json — completion_condition.checks[] become the acceptance criteria.
reports/<topic>/ontology-map.json — per-finding resolved type, for the entity-catalog grounding.
The selected spec genre (default ai-architecture-doc).

Procedure

Select — gather surviving and weakened findings for the topic; resolve their ontology types so entity-catalog rows carry their grounding.
Synthesize — run scripts/synthesize-artifact.sh <findings-dir> <genre> <artifact.json> with the chosen genre, so artifact.json carries genre, finding_refs[] for every cited finding, and sections[] for the taxonomy.
Shape (genre) — apply the genre skill's section taxonomy and frontmatter contract:
- finding_refs[] → grounded evidence sections (every design claim carries a finding_ref or a named external standard).
- goal completion_condition.checks[] → EARS acceptance criteria (WHEN … SHALL … + the check's verify command as the executable test).
- artifact.sections[] → the document structure.
- when an ontology pack is bound, render its entity inventory as a grounded entity-catalog section and its inter-type relationships as a relationship-model section, each row naming its source vocabulary.
Render — deterministically write the spec to the <out.md> path passed to render-artifact.sh (same findings -> byte-identical Markdown). Default output paths, so switching --genre never overwrites a sibling spec:
- ai-architecture-doc (default): reports/<topic>/<topic>-build-spec.md
- feature-spec: reports/<topic>/<topic>-feature-build-spec.md
- kiro-requirements: reports/<topic>/<topic>-kiro-requirements.md
- kiro-design: reports/<topic>/<topic>-kiro-design.md
- kiro-tasks: reports/<topic>/<topic>-kiro-tasks.md
Carry MIF frontmatter + the genre markers (genre, audience: implementer, status, evidence_base).
Gate — the spec must pass markdownlint-cli2 with zero errors; every evidence row must carry a citation; the body carries no internal urn:mif: identity.