Cdd Spec Writer logo

Cdd Spec Writer

Community
Oscaner
cdd-spec-writer

Independent spec-writer -- Node-anchored flow with digraph as single control-flow source of truth. Consumes the /superpowers:brainstorming(pi:/skill:brainstorming) (writing-spec) design flow inline as this session's baseline, then authors the target spec (single-spec / phase-spec / overall — one parameterized flow), commits it before the review-fix loop, and runs the loop following the engine's next face — the engine's next directive carries the pipeline continuation. Callable standalone; invoke as kairos:cdd-spec-writer(pi:/skill:cdd-spec-writer).

Overview

PublisherOscaner
Repositoryskills
Skill namecdd-spec-writer
Stars
63
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Oscaner on GitHub. Read the source before you install it.

Installation

Install the Cdd Spec Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Oscaner/skills/tree/main/packages/kairos/skills/cdd-spec-writer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Oscaner/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/packages/kairos/skills/cdd-spec-writer .claude/skills/cdd-spec-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cdd Spec Writer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cdd Spec Writer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cdd Spec Writer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Kairos CDD-Spec-Writer

Writes the target spec from the writing-spec import — single-spec / phase-spec / overall under one parameterized flow (the schema target + scope gates + authoring differ by variant; the review-fix rhythm and the Invariants are the single shared skeleton) — commits it before reviewing under the cdd spec contract; on closure the engine's next: face carries the pipeline continuation.

Invocation discipline — every engine command runs as a background dispatch: launch it in the background and await the completion notification — never poll — then read the full output (stdout/stderr). Output filtering is forbidden — no piping to tail/head, no 2>&1 |, no EXIT=$? capture. Round rhythm — one review pass per dispatch; a fix round re-enters the review while the route is not done; commit the authored spec before the first review round; ensure the working tree is clean before entering review (dirty → BLOCKED; the orchestrator writes no tree during dispatch). Failure face — cross-node failure handling lives in the Failure Modes table below (the single source); node Fail entries keep only local behavior.

Flow Digraph

Node Definitions

run-writing-spec-session

  • Do: Import /superpowers:brainstorming(pi:/skill:brainstorming) (writing-spec import); it lands the design decisions this target spec will capture. The target (single-spec / phase-spec / overall) is the session parameter: it selects the schema target, the scope gates and the handoff of the flow
  • Read: nothing before the import; the import lands the design + the target
  • Exit: Import landed → author-spec
  • Fail: Upstream superpowers plugin missing → BLOCKED (no downgrade, no skip, no inline restatement)

author-spec

  • Do: Write the target spec document from the session output — overall lands in docs/kairos/overalls/, phase-spec and single-spec in docs/kairos/specs/ — generate the canonical skeleton first for the target type (npx -y @oscaner-skills/cdd-engine@latest schema get <overall|phase-spec|single-spec> --output skeleton <target path>) and fill its slots in place; the structure stays as generated. The landed document carries its identity in the front-matter slug: key (the engine keys the workspace and the board on it, never on the file name); a phase-spec additionally carries program: — the parent overall's slug:, the phase's attribution to its program. Per the target variant:
    • single-spec — the free-form spec form; the docs-lane doc-contract gate asserts the version-lineage on every reviewed spec
    • phase-spec — the phase scope is an increment only: when the phase scope changed vs the parent overall, sync the parent overall (Issue/Phase inventory + Dependency graph + version bump + change history) BEFORE writing (the four-table sync ordering; the sync is the registration gate, never a silent skip)
    • overall — the phase registration for a new phase is the parent's own table sync (see run-cdd-design's run-cdd-charter · sync)
  • Read: Session output + the target's structural contract (phase-spec/overall variants also read the parent overall)
  • Exit: File written → self-review
  • Fail: Session output unusable or write error → BLOCKED (missing design input)

self-review

  • Do: Review the just-written spec before committing — run five checks, substance first: (1) capture — every design decision the session landed is in the spec, every ruling recorded; (2) sufficiency — could the downstream plan author act without guessing? Name each place where a wrong guess would change what gets built; (3) consistency — doc-type / naming / cross-references agree; (4) failure modes — the design addresses the failure modes and edge conditions it implies; (5) proportion — the spec carries decisions, not a transcript of the work. Then the mechanical tail: zero leftover :::fill markers, zero angle-bracket literals outside link-anchor slots (cheap hygiene the doc-contract gate would otherwise flag). Issues found are fixed inline on the same file; this is a pre-commit self-check inside this flow, not a review round (no next: dispatch, no findings carrier).
  • Read: the written spec document + the session output it was authored from
  • Exit: Self-check clean (issues fixed inline) → commit-spec
  • Fail: Unresolvable defect needing upstream design input → BLOCKED (missing design input)

commit-spec

  • Do: git add the spec + conventional commit.
  • Read: The committed spec file path
  • Exit: Commit complete → NEXT-LOOP
  • Fail: Git error → report + fail-open (do not block user spec review)

NEXT-LOOP

  • Do: Run the review-fix rhythm for the authored spec — one review per pass. Dispatch the review round on the current ref (npx -y @oscaner-skills/cdd-engine@latest review --type spec --spec <path>); dispatch the output's next: line as written — the literal is the route: a fix dispatch consumes the findings handoff, a closure ends the flow (follow the engine's next: literal — for a phase/overall spec it routes the next pipeline entrypoint); a BLOCKED/TIMEOUT round carries no next: line — its reason rides stderr for reporting.
  • Read: the review output — its conclusion and the next: line, plus the findings handoff path
  • Exit: the next: line routes the next pipeline entrypoint (a skill ref / the pipeline terminus) → the flow ends (the engine's next: literal carries the next pipeline entrypoint when one exists); each fix pass re-enters this hub while the route is not terminal — the engine's next: literal has not yet handed the orchestrator off (the until next is terminal self-loop)
  • Fail: Re-running a review after a closure conclusion → violates Review Convergence (stop + report)

Invariants

#Invariant
I1Review Convergence (next: is the dispatch) — a review closes by its conclusion (APPROVED / CHANGES_REQUESTED / REVIEW_FIX), and the output's next: line carries the engine's default next step as a complete executable command; read the next: line and dispatch it as written — the literal is the dispatch, no kind→command mapping layer. A mid-backfill or a user adjudication that lands governs over the suggestion (current world state wins). Fixes always dispatch via the fix round, consuming the findings handoff; the orchestrator must not edit in place as a substitute; a fix commit opens a new review, never a re-run of a closed one
I2Spec commit discipline — the authored spec commits before the first review round; each fix round commits its own changes — approval closes the loop on a committed state; do not wait for dev merge
I3Mid-Flight Backfill — a user-raised backfill of overall/spec/plan docs surfaced while a dispatch is in flight lands through four ordered steps on the current call's return: (1) land immediately — hot context, no deferral; (2) commit on its own — a standalone change, never mixed with implementation commits; (3) pause the loop until clean — an uncommitted backfill trips the next review's entry gate (dirty → BLOCKED); (4) audit in-band on resume — the next review audits the backfill in-band; a backfill rewriting the current task's own plan/spec text routes through the orchestrator's plan write authority

Failure Modes

failurebehaviorreason
Upstream superpowers plugin missingBLOCKED (install superpowers — see the kairos README's installation table)Block policy: no silent fallback
review re-run after a closure conclusion (REVIEW_FIX / APPROVED)Violates I1 (Review Convergence) — stop + report to userA fix commit opens a new review, never a re-run of a closed one
Git commit errorreport + fail-openDo not block user spec review
Completed round with no next: line (not BLOCKED/TIMEOUT)HARD_ERROR — report the carried reason, re-run the same command to continueNo dispatchable next

Frequently asked questions

What does the Cdd Spec Writer AI skill do?

Independent spec-writer -- Node-anchored flow with digraph as single control-flow source of truth. Consumes the /superpowers:brainstorming(pi:/skill:brainstorming) (writing-spec) design flow inline as this session's baseline, then authors the target spec (single-spec / phase-spec / overall — one parameterized flow), commits it before the review-fix loop, and runs the loop following the engine's next face — the engine's next directive carries the pipeline continuation. Callable standalone; invoke as kairos:cdd-spec-writer(pi:/skill:cdd-spec-writer).

Why use Cdd Spec Writer on TypingMind?

Because you install it once and use it with any model. Cdd Spec Writer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cdd Spec Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Oscaner/skills/tree/main/packages/kairos/skills/cdd-spec-writer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cdd Spec Writer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cdd Spec Writer?

As many as you like. As long as a model supports skills, you can use Cdd Spec Writer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cdd Spec Writer AI skill free?

Yes. It is published on GitHub by Oscaner under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇