Agent skill

Create Spec

by Levix0501 in Levix0501/kiko-skills

Turn the design into a build-ready spec a fresh context can implement and verify.

MITAuto-check passed

Install Create Spec

skills CLI
$ npx skills add Levix0501/kiko-skills --skill create-spec -a claude-code

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

GitHub CLI
$ gh skill install Levix0501/kiko-skills create-spec --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/Levix0501/kiko-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/create-spec .claude/skills/create-spec && 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
create-spec
GitHub stars
170
Token cost
~772 tokens
SKILL.md length
437 words
Files
8 (incl. scripts, references, assets)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Turn the design into a build-ready spec a fresh context can implement and verify.

  • Works in 5 steps: Locate the spec directory → Classify the design → Draft and preflight → …
  • The user asks to create a spec
  • SKILL.md covers 1. Locate the spec directory, 2. Classify the design, 3. Draft and preflight and 4. Review with the user, plus 1 more section

What it does

Create Spec is an agent skill from Levix0501/kiko-skills. Turn the design into a build-ready spec a fresh context can implement and verify. Use when the user asks to create a spec.

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts, reference files and assets (for example `assets/spec-template.md`, `references/facts.md` and `references/self-review.md`).

The licence is MIT.

When your agent uses it

  • The user asks to create a spec

Example prompts

  • “/create-spec”

Workflow steps

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

  1. Locate the spec directory
  2. Classify the design
  3. Draft and preflight
  4. Review with the user
  5. Commit the confirmed version

What it can do on your machine

Read from SKILL.md and the folder at commit 9734a55. 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

    Ships 1 file in scripts/, which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Create Spec loads about 772 tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 437 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~772
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

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 passed

The automated check found no risky patterns in SKILL.md.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Levix0501/kiko-skills at commit 9734a55, republished under its MIT licence (© Levix0501). 437 words, ~772 tokens.

Download SKILL.mdSave it as .claude/skills/create-spec/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
create-spec
description
Turn the design into a build-ready spec a fresh context can implement and verify. Use when the user asks to create a spec.

create-spec turns the design into a build-ready spec — the delivery contract a fresh context can implement and verify.

1. Locate the spec directory

Run scripts/check-kiko with the opened project root's absolute path as its only argument, and use the returned path as KIKO_ROOT.

  • Exit 3: ask the user to run the setup-kiko skill at the project root, then retry.
  • Any other nonzero exit: report the error and stop.

Do not initialize or repair .kiko.

SPEC_DIR is the spec directory named when this skill was invoked, directly under $KIKO_ROOT/docs; ask for it when none was named. It holds decisions.md, the decisions made so far toward the outcome, and facts.md, per the facts file. The spec goes to $SPEC_DIR/spec.md; if it already exists, report that and stop.

2. Classify the design

decisions.md holds one entry per decision:

md
- DECISION<n> [user] <question, with the options as put>
  <what the user chose or said>

DECISION1 is the outcome and becomes the Goal. [user] marks the user as the decider. IDs increase and are never reused; a changed decision is a new entry that says which ID it supersedes. An entry holds what was put to the user and what they chose or said, nothing written for them. A decision the user makes while create-spec runs, whether answering a returned issue or revising the draft, is appended the same way before it is used, worded so that question and answer have one reading without the conversation.

Apply the spec rules to each entry. Run each empirical premise through the evidence gate in the spec rules before using it.

Show full SKILL.md (189 more words)Show less

3. Draft and preflight

Assemble, without writing either file, the complete draft per the template and the facts to append per the facts file.

Run the self-review and fix every failure. Write the draft to $SPEC_DIR/spec.md and append the facts to $SPEC_DIR/facts.md only after this preflight passes.

4. Review with the user

Present the written file as the exact review target, list every D or state that there are none, show the decisions entries appended since this skill started, name the entries the delivery boundary left to the user's release, and ask the user to confirm or revise the document.

Treat a revision like the first draft: classify, gate, and self-review what changed, then ask again.

5. Commit the confirmed version

Do not commit until the user explicitly confirms the current file. Any later semantic change requires another confirmation.

If the spec directory is in a Git working tree, commit it and report the commit SHA; otherwise warn the user that nothing marks the spec as confirmed.

Recommend starting /implement $SPEC_DIR in a new window or after /compact, so that implement starts from the files rather than this conversation.

© Levix0501, 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 (scripts, references, assets) in skills/create-spec of Levix0501/kiko-skills.

  • SKILL.md
  • assets/spec-template.md
  • references/facts.md
  • references/self-review.md
  • references/spec-rules.md
  • scripts/check-kiko
  • tests/run-tests
  • tests/semantic-cases.md

Open the folder on GitHubat commit 9734a55

Compare with similar skills

Create Spec 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.

Create Spec compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Spec this skillLevix0501/kiko-skills170—~772Automated safety check: PassMIT
Content Freshness Signalsthedaviddias/Front-End-Checklist74k—~741Automated safety check: PassMIT
Freshness Checkbruin-data/bruin1.8k—~1kAutomated safety check: PassApache-2.0
Checking Freshnessastronomer/agents451—~801Automated safety check: PassApache-2.0
Ripwire Fresh Eyesredhat-et/ripwire2.4k—~10kAutomated safety check: NotesApache-2.0
Doc Freshness ReviewTencentCloudBase/CloudBase-AI-Toolkit1.1k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Content Freshness Signals

    thedaviddias/Front-End-Checklist

    Audits article pages for freshness signals, covering the Last-Modified header, Article JSON-LD dateModified and a visible last-updated date, and fixes mismatches.

    74k GitHub stars~741 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Freshness Check

    bruin-data/bruin

    A skill your agent uses when data is stale, a scheduled run is missing, or freshness checks fail.

    1.8k GitHub stars~1k tokensUpdated today
    DatabasesAuto-check passed
  • Checking Freshness

    astronomer/agents

    Quick data freshness check. An agent skill from astronomer/agents.

    451 GitHub stars~801 tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Ripwire Fresh Eyes

    redhat-et/ripwire

    Maintenance risk in code you did NOT write — inheriting a module, planning a refactor, a suspected god object, 'what's gnarly / where's the rot / safe to touch?': hotspots, dead or inactive code…

    2.4k GitHub stars~10k tokensUpdated today
    DevelopmentAuto-check: notes
  • Doc Freshness Review

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses when auditing repository documentation for drift, stale statements, broken references, or README mismatches, especially across published docs under doc/ and key entry…

    1.1k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Fresh Eyes Amend

    jackfranklin/dotfiles

    Amends the previous commit with current changes, then spawns two subagents to independently review the full git diff and propose fresh commit messages.

    255 GitHub stars~899 tokensUpdated today
    DevelopmentAuto-check passed

More from Levix0501/kiko-skills

  • Implement

    Levix0501/kiko-skills

    Turn a spec into reviewed, shippable code. An agent skill from Levix0501/kiko-skills.

    170 GitHub stars~3.6k tokensUpdated 14 days ago
    Auto-check passed
  • Kick Off

    Levix0501/kiko-skills

    Cut the request into outcomes, pick what to build next, and interview until every decision about it is settled.

    170 GitHub stars~1.5k tokensUpdated 14 days ago
    Auto-check passed
  • Setup Kiko

    Levix0501/kiko-skills

    Initialize or repair the project-local .kiko workspace at the project root.

    170 GitHub stars~239 tokensUpdated 14 days ago
    Auto-check passed

Questions about Create Spec

What does Create Spec do?

Turn the design into a build-ready spec a fresh context can implement and verify. Create Spec is an agent skill from Levix0501/kiko-skills. Turn the design into a build-ready spec a fresh context can implement and verify.

When should I use Create Spec?

Create Spec fits situations like: the user asks to create a spec.

How do I install Create Spec in Claude Code?

Run `npx skills add Levix0501/kiko-skills --skill create-spec -a claude-code`. Or copy the skill folder (skills/create-spec in Levix0501/kiko-skills) into .claude/skills/create-spec in your project. Claude Code loads it when a task matches its description.

How do I install Create Spec in Codex?

Run `npx skills add Levix0501/kiko-skills --skill create-spec -a codex`. Or copy the skill folder (skills/create-spec in Levix0501/kiko-skills) into .agents/skills/create-spec in your project. Codex loads it when a task matches its description.

Can I use Create Spec 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 Levix0501/kiko-skills --skill create-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-spec, .gemini/skills/create-spec, .github/skills/create-spec and .opencode/skills/create-spec in your project.

What does Create Spec need to run?

SKILL.md names no scripts, command-line tools or credentials: Create Spec is instructions for the agent only.

Does Create Spec access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Create Spec safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Create Spec use?

Create Spec 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 Create Spec use?

About 772 tokens (SKILL.md is roughly 3.1k 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 2.6k tokens, read only when the agent opens those files.

What are the alternatives to Create Spec?

Skills that share tags, products or a category with Create Spec: Content Freshness Signals (thedaviddias/Front-End-Checklist, 74k stars), Freshness Check (bruin-data/bruin, 1.8k stars), Checking Freshness (astronomer/agents, 451 stars) and Ripwire Fresh Eyes (redhat-et/ripwire, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Spec?

Levix0501 (a GitHub user) maintains it in Levix0501/kiko-skills, which has 170 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 24, 2026.

Source: Levix0501/kiko-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.