Agent skill

Cabloy Spec Generation

by cabloy in cabloy/cabloy

A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.

MITAuto-check: notesDevelopment

Install Cabloy Spec Generation

skills CLI
$ npx skills add cabloy/cabloy --skill cabloy-spec-generation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cabloy/cabloy cabloy-spec-generation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cabloy/cabloy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cabloy-spec-generation .claude/skills/cabloy-spec-generation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cabloy-spec-generation
GitHub stars
982
Token cost
~3.2k tokens
SKILL.md length
1,398 words
Files
8 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.

  • Works in 10 steps: Discover the active repository → Choose one planning mode → Resolve identity without changing the… → …
  • Maintain Cabloy suite specifications under repo-specs
  • SKILL.md covers 1. Discover the active…, 2. Choose one planning mode, 3. Resolve identity without… and 4. Resolve only missing site…, plus 6 more sections
  • Calls npm

What it does

Cabloy Spec Generation is an agent skill from cabloy/cabloy. Use this skill to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs. It supports a complete new baseline, incremental maintenance, and explicitly lightweight planning. Route unresolved naming through cabloy-domain-planning and return here; hand approved bounded implementation to cabloy-spec-execution, not directly to broad scaffolding.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `evals/evals.json`, `evals/files/scenarios.json` and `evals/protocol.md`).

It sits in Development, covering Architecture decision records, Project scaffolding and PRD writing. It works with npm. The repository describes itself as: Cabloy is a Node.js fullstack framework for AI vibe coding, with AI Spec-Driven Development guiding work from confirmed specs to verifiable delivery. The licence is MIT.

When your agent uses it

  • Maintain Cabloy suite specifications under repo-specs
  • Acceptance planning

Example prompts

  • “/cabloy-spec-generation”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Discover the active repository
  2. Choose one planning mode
  3. Resolve identity without changing the workflow
  4. Resolve only missing site strategy
  5. Collect the remaining inputs
  6. Confirm generation scope
  7. Write authority first
  8. Preserve Cabloy boundaries
  9. Apply three independent quality gates
  10. Finish with a bounded execution handoff

What it can do on your machine

Read from SKILL.md and the folder at commit b3d00ec. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cabloy Spec Generation loads about 3.2k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 113 tokens; SKILL.md has 1,398 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~113
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:26
    ign, and evidence. Never read or expose `.env*` contents to recommend worktree identity or ports.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cabloy/cabloy at commit b3d00ec, republished under its MIT licence (© cabloy). 1,398 words, ~3,213 tokens.

Download SKILL.mdSave it as .claude/skills/cabloy-spec-generation/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
cabloy-spec-generation
description
Use this skill to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs. It supports a complete new baseline, incremental maintenance, and explicitly lightweight planning. Route unresolved naming through cabloy-domain-planning and return here; hand approved bounded implementation to cabloy-spec-execution, not directly to broad scaffolding.

Cabloy Repository Specs

Create or maintain repository-native planning authority. Planning is not source implementation, acceptance evidence, ADR acceptance, or execution authorization.

Read before substantial generation or revision:

  • references/repo-aware-discovery.md: edition, source discovery, and observed versus new target semantics;
  • references/repo-specs-document-set.md: authority and proportionate document architecture;
  • references/canonical-spec-input.md: canonical declarations, parser compatibility, and the three quality gates;
  • references/traceability-and-status-rules.md: stable IDs, evidence, and authority-first updates.

1. Discover the active repository

Inspect the root, working tree, edition markers, root package.json, existing repo-specs/ indexes, relevant suite/module topology, and authored governance. Discover npm run vona / npm run zova command families when planning cites implementation commands.

  • Exactly __CABLOY_BASIC__: use observed Basic scripts, UI, sites, flavors, and output paths.
  • Exactly __CABLOY_START__: resolve those details from the active Start source; do not copy Basic examples.
  • Both markers: stop; the checkout is invalid or ambiguous.
  • Neither: inspect the owning package and nearby structure, then ask before edition-sensitive planning.

Cite inspected paths. Keep repository facts separate from user inputs, target design, and evidence. Never read or expose .env* contents to recommend worktree identity or ports.

2. Choose one planning mode

ModeScope and protectionQuality branch
Complete new baselineNew long-lived suite: six core Markdown records plus initial ADR; both charts after complete chart inputs exist.Full spec:check, then chart generation/freshness, then human decision/status review.
Incremental maintenanceRead the existing README/authority map; update affected upstream authority and downstream links only. Preserve IDs, accepted decisions, evidence, and unrelated statuses.Full audit when the authority set is complete; report legacy gaps separately. Charts only with complete supported inputs.
Lightweight planningExplicitly approved small demo, utility, or limited planning scope. Agree on selected records, omitted owners, limits, and no implied full-suite closure.spec:check --lightweight for available owners/references/links; manually review the limited chain. No forced full set or charts with incomplete inputs.

An existing directory is the normal incremental destination, not an automatic conflict. Ask about a conflict only for a genuine identity collision, parallel authority, or requested destructive replacement. Do not reset the directory or regenerate the whole baseline by default.

A growing business domain defaults to the complete baseline. Ask before choosing lightweight scope. Do not invent requirements to fill omitted documents.

3. Resolve identity without changing the workflow

For unresolved provider/suite/module naming, route to cabloy-domain-planning with a naming-only return to generation. Validate the returned names and resume this mode and its confirmation gate. Naming confirmation does not authorize source scaffolding.

For suite-first ownership, the short name is {providerId}-{suiteName}; suiteName uses lowercase English letters only, without another hyphen. Use capability names for modules. Reuse the stable existing suite/capability planning slug rather than creating a competing hierarchy.

4. Resolve only missing site strategy

First inspect active shared-site composition owners, extension points, independent-site conventions, and framework constraints. A capability module or an Admin audience alone does not require an independent site.

  • If both Web and Admin strategies are unresolved, evaluate them separately, recommend contextually, and present one single-select decision: shared/shared, independent/shared, shared/independent, independent/independent. Keep Other for custom/no-site/deferred choices.
  • If only one audience is in scope or unresolved, ask only about that audience.
  • If an established strategy already governs the requested change, preserve it; do not repeat the four-way question absent a material change.

Choosing strategy confirms only that input. It does not accept an ADR or approve implementation.

Classify every target as observed existing, proposed new, or explicitly approved new under the discovery reference. Shared integration requires an observed owner. A proposed independent tuple may be designed before its source exists: validate framework constraints and collisions, obtain explicit design approval, and retain its governing ADR as Proposed until separately accepted. An explicitly approved new tuple with an Accepted ADR can be created by a bounded execution task; source pre-existence is not a prerequisite.

Unknown or unchecked values stay TODO(confirm) with the exact missing design/source/conflict check. Block only dependent site/frontend implementation; keep backend, unrelated audiences, and runnable discovery tasks actionable.

5. Collect the remaining inputs

Ask only for missing inputs in a compact clarification pass:

  • identity/output path, outcomes, personas, journeys, scope, exclusions, and acceptance;
  • modules and reused persistence/identity owners; audience strategy and target classification;
  • tenant, server-authoritative identity/authorization, privacy, lifecycle, transactions, concurrency, idempotency, audit, integrations, and migration/version decisions where material;
  • dependencies, release constraints, contract-loop checkpoints, test levels, fixture cleanup, proof/redaction, and optional records;
  • durable decisions, ADR candidates, and unresolved gates.

Label recommendations as proposals. A request for comprehensiveness is not permission to invent security or business decisions.

6. Confirm generation scope

Before writing, present the edition/root, mode, identity/path, intended ownership, outcomes/scope, site strategy/target tuple classification, affected records, justified omissions/extensions, unresolved gates, and initial status/evidence policy. Include planned chart eligibility and README language.

Keep three approvals separate:

  1. Generation approval authorizes the named planning edits only.
  2. Design/ADR approval explicitly approves a durable decision; record Accepted only for the decision actually accepted. A tuple design approval is not source-existence proof.
  3. Execution approval belongs to a bounded WBS dossier in cabloy-spec-execution.

Do not treat silence, strategy selection, naming confirmation, or generation approval as another approval. Drafts retain Proposed ADRs and controlling TODO(confirm) gates.

Show full SKILL.md (565 more words)Show less

7. Write authority first

For a complete new baseline, create:

text
repo-specs/<suite>/
├── README.md
├── prd.md
├── srs.md
├── pdp-wbs.md
├── test-plan.md
├── progress.md
└── decisions/0001-<boundary>.md

With complete supported chart inputs, generate implementation-gantt.svg and implementation-burndown.svg as derived views. Use canonical declarations in references/canonical-spec-input.md for new records. Each exact PRD/SRS/WBS/ATP ID has one definition in its owner, not merely a matrix, range, or evidence mention.

For updates, change PRD/SRS/ADR first, then mappings, WBS, ATP, evidence assumptions, and progress. Preserve stable IDs and history. Legacy catalogue tables remain compatible; missing formal definitions are a reported legacy gap, not permission to invent business meaning or rewrite legacy business records to satisfy a tool.

Add presentation contracts, rollout records, runbooks, extra ADRs, or evidence only when confirmed scope justifies them. Never create empty evidence or fabricate an EVD-* record.

8. Preserve Cabloy boundaries

  • Keep suite business planning in repo-specs/, public/agent guidance in repo-docs/, and supporting maintainer rationale in repo-docs-internal/.
  • Reuse persistence and identity ownership. An independent site does not create a separate tenant, identity, authorization, persistence, or domain-rule authority.
  • Treat the active Vona instance as tenant by default. Authorization and scope are server-authoritative, not menus or browser filters.
  • Separate genuinely different Admin/Web API/DTO, server-scope, frontend state, and page contracts while retaining one domain/persistence boundary.
  • Plan forward and reverse contract-loop checkpoints; actual regeneration belongs to the specialist invoked by execution. Never hand-edit generated consumers.
  • Ask before choosing the persisted-field vonaModule.fileVersion strategy.
  • A new wrapper is a planned addition, not a currently runnable command. Validate its durable manifest destination and paired SSR/REST design; execution must create and observe it before running it.

9. Apply three independent quality gates

Use the active root scripts, verified from package.json:

bash
npm run spec:check -- <suite>
# Explicit lightweight branch:
npm run spec:check -- <suite> --lightweight
  1. Planning authority audit: spec:check validates definition roles, exact references, PRD -> SRS -> WBS -> ATP associations, and local links. Explicit Traceability belongs in declaration bodies. Review gaps and decisions manually; a static pass is not design acceptance.
  2. Chart model/freshness: only with complete supported README/WBS/ATP/progress inputs, run npm run spec:charts -- <suite> then npm run spec:charts:check -- <suite>. This proves supported model consistency and SVG freshness only. Regenerate after WBS, test-plan, progress, or README title/language changes. No complete input means an explicit chart omission/blocker, not invented definitions or status.
  3. Human approval/evidence: review ADR status, controlling TODOs, scope, and evidence-backed status. Only retained applicable ATP proof can justify verified; neither audit nor charts can approve a design or implementation.

For incremental legacy gaps, report the missing definition/owner/link and affected chain without silently changing business meaning. If correction needs a new decision, request it and report the update as incomplete at that gate. Lightweight results must state skipped owners/chain coverage; never advertise a full-suite pass.

Planning creation alone initializes delivery as not-started, deferred, or specifically blocked. planning-complete is only available to a formally opted-in documentary/design task after its own checks receive revision-scoped proof and a named-reviewer closure disposition; it is not ATP verification or permission to execute a successor. Preserve carried-forward observed evidence with its revision/authority limits. Do not run init, database reset, scaffolding, deployment/provider operations, or acceptance tests as an automatic consequence of planning.

10. Finish with a bounded execution handoff

Report edition/mode/path, files changed, omissions, unresolved decisions, approval domains, actual audit results, chart eligibility/freshness/language, and evidence limitations. Identify one candidate WBS increment or finite phase and its dependencies, acceptance proof, and controlling gates.

The next implementation entry is cabloy-spec-execution, which still requires explicit target/dossier approval. Do not jump directly from generation to broad backend/frontend scaffolding, execute an adjacent task, or claim release closure.

© cabloy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in .agents/skills/cabloy-spec-generation of cabloy/cabloy.

  • SKILL.md
  • evals/evals.json
  • evals/files/scenarios.json
  • evals/protocol.md
  • references/canonical-spec-input.md
  • references/repo-aware-discovery.md
  • references/repo-specs-document-set.md
  • references/traceability-and-status-rules.md

Open the folder on GitHubat commit b3d00ec

Compare with similar skills

Cabloy Spec Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cabloy Spec Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cabloy Spec Generation this skillcabloy/cabloy982—~3.2kAutomated safety check: NotesMIT
Vibe CodingOfficeDev/microsoft-365-agents-toolkit781—~5.5kAutomated safety check: PassCustom licence
Diag Harnessruvnet/metaharness694—~835Automated safety check: PassMIT
Bmad Architectureaj-geddes/claude-code-bmad-skills488—~1.9kAutomated safety check: NotesCustom licence
Documentation Criteriashinpr/claude-code-workflows693—~1.9kAutomated safety check: PassMIT
Ad ReviewCorridorTech/PoseCap224—~2.4kAutomated safety check: NotesApache-2.0

Similar skills

  • Vibe Coding

    OfficeDev/microsoft-365-agents-toolkit

    End-to-end workflow for agent-driven changes that add or modify behavior in the toolkit packages.

    781 GitHub stars~5.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Diag Harness

    ruvnet/metaharness

    Kernel-version skew check (ADR-027). An agent skill from ruvnet/metaharness.

    694 GitHub stars~835 tokensUpdated today
    DevelopmentAuto-check passed
  • Bmad Architecture

    aj-geddes/claude-code-bmad-skills

    Solutioning skill (Winston, the Architect). An agent skill from aj-geddes/claude-code-bmad-skills.

    488 GitHub stars~1.9k tokensUpdated 3 mo ago
    DevelopmentAuto-check: notes
  • Documentation Criteria

    shinpr/claude-code-workflows

    Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored.

    693 GitHub stars~1.9k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Ad Review

    CorridorTech/PoseCap

    Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

    224 GitHub stars~2.4k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes
  • Squid Plan

    iusztinpaul/squid

    Turn a raw feature spec into an approved Tasks Plan — grill the spec, have the Product Architect groom draft tasks (+ optional ADR and glossary additions), then run ONE human gate that decides…

    203 GitHub stars~2.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from cabloy/cabloy

All 12 skills in this repo
  • A skill your agent uses whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain.

    982 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • This skill must be used only when the user explicitly invokes /cabloy-worktree-environment or explicitly asks to perform the named Cabloy worktree-environment setup.

    982 GitHub stars~2.9k tokensUpdated today
    Auto-check: notes
  • This skill should be used when the user needs the Vona backend scaffold/extend path in this Cabloy repo, especially to choose the right npm run vona generator or CRUD command and the required…

    982 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses whenever a Cabloy task crosses the Vona-to-Zova contract boundary: backend DTO, controller, validation, entity, inferred DTO, or OpenAPI changes that should drive SDK…

    982 GitHub stars~5.1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses whenever the user wants the Zova frontend path in this Cabloy repo: create or extend pages, components, api or model beans, route/query/params work, metadata refresh…

    982 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses whenever the user wants to update a field on an existing Cabloy backend resource: add a new persisted field, refine validation, add enum-like constraints, attach or change…

    982 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

Works with

Questions about Cabloy Spec Generation

What does Cabloy Spec Generation do?

A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs. Cabloy Spec Generation is an agent skill from cabloy/cabloy. Use this skill to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.

When should I use Cabloy Spec Generation?

Cabloy Spec Generation fits situations like: maintain Cabloy suite specifications under repo-specs; acceptance planning.

How do I install Cabloy Spec Generation in Claude Code?

Run `npx skills add cabloy/cabloy --skill cabloy-spec-generation -a claude-code`. Or copy the skill folder (.agents/skills/cabloy-spec-generation in cabloy/cabloy) into .claude/skills/cabloy-spec-generation in your project. Claude Code loads it when a task matches its description.

How do I install Cabloy Spec Generation in Codex?

Run `npx skills add cabloy/cabloy --skill cabloy-spec-generation -a codex`. Or copy the skill folder (.agents/skills/cabloy-spec-generation in cabloy/cabloy) into .agents/skills/cabloy-spec-generation in your project. Codex loads it when a task matches its description.

Can I use Cabloy Spec Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cabloy/cabloy --skill cabloy-spec-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cabloy-spec-generation, .gemini/skills/cabloy-spec-generation, .github/skills/cabloy-spec-generation and .opencode/skills/cabloy-spec-generation in your project.

What does Cabloy Spec Generation need to run?

Going by SKILL.md and its folder, Cabloy Spec Generation needs the command-line tools its instructions call (npm).

Does Cabloy Spec Generation access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cabloy Spec Generation safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Cabloy Spec Generation use?

Cabloy Spec Generation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cabloy Spec Generation use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Cabloy Spec Generation?

Skills that share tags, products or a category with Cabloy Spec Generation: Vibe Coding (OfficeDev/microsoft-365-agents-toolkit, 781 stars), Diag Harness (ruvnet/metaharness, 694 stars), Bmad Architecture (aj-geddes/claude-code-bmad-skills, 488 stars) and Documentation Criteria (shinpr/claude-code-workflows, 693 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cabloy Spec Generation?

cabloy (a GitHub organization) maintains it in cabloy/cabloy, which has 982 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.

Source: cabloy/cabloy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.