Agent skill

Implement

by Levix0501 in Levix0501/kiko-skills

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

MITAuto-check passed

Install Implement

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

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

GitHub CLI
$ gh skill install Levix0501/kiko-skills implement --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/implement .claude/skills/implement && 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
implement
GitHub stars
170
Token cost
~3.6k tokens
SKILL.md length
1,840 words
Files
11 (incl. scripts, references, assets)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 12 steps: Check kiko workspace → Resolve spec → Prepare the implementation directory → …
  • The user asks to implement a spec
  • SKILL.md covers 1 Workflow and 2 Concepts
  • Calls openssl

What it does

Implement is an agent skill from Levix0501/kiko-skills. Turn a spec into reviewed, shippable code. Use when the user asks to implement a spec.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts, reference files and assets (for example `assets/implementation-result-template.md`, `assets/review-result-template.md` and `references/facts.md`).

The licence is MIT.

When your agent uses it

  • The user asks to implement a spec

Example prompts

  • “/implement”

Workflow steps

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

  1. Check kiko workspace
  2. Resolve spec
  3. Prepare the implementation directory
  4. Read progress file
  5. Dispatch the implementer
  6. Read the subagent result
  7. Route the implementation result
  8. Dispatch the reviewer
  9. Route the review result
  10. Handle a spec issue
  11. Handle an external blocker
  12. Handle a blocked attempt

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 2 files in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • openssl

    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

Implement loads about 3.6k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 1,840 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.9k

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). 1,840 words, ~3,583 tokens.

Download SKILL.mdSave it as .claude/skills/implement/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
implement
description
Turn a spec into reviewed, shippable code. Use when the user asks to implement a spec.
disable-model-invocation
true

Orchestrate implementation from a spec: the controller dispatches fresh roles (subagents) to implement and review. The controller never implements, reviews, or fixes anything itself.

1 Workflow

Start with Step 1.

Step 1: Check kiko workspace

Set PROJECT_ROOT to the opened project root's absolute path. Run scripts/check-kiko with $PROJECT_ROOT 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. On success, continue to Step 2.

Step 2: Resolve spec

Resolve SPEC_DIR, the absolute path of a spec directory directly under $KIKO_ROOT/docs, from the first available source:

  1. the path named when this skill was invoked;
  2. the spec directory this conversation is already working on;
  3. ask which spec to build.

Then continue to Step 3.

Step 3: Prepare the implementation directory

Run scripts/prepare-implement-dir with $KIKO_ROOT and $SPEC_DIR as its arguments, and use the returned path as IMPLEMENT_DIR, per 2.1 Implementation directory. On a nonzero exit, show the error and ask the user to fix what it names, then retry from Step 2.

On success, derive:

sh
SPEC_SLUG=$(basename "$SPEC_DIR")
SPEC_FILE="$SPEC_DIR/spec.md"
FACTS_FILE="$SPEC_DIR/facts.md"
DECISIONS_FILE="$SPEC_DIR/decisions.md"

Then check every repository at or under $PROJECT_ROOT for uncommitted content: the roles create the work branch from the current branch, so anything left uncommitted would end up in their work. If any tree is not clean, show the user what you found right away, before looking into anything else, and offer the choice:

  • the agent commits it as it stands, one commit per repository on its current branch;
  • the user commits, stashes, or discards it themselves and tells the agent when every tree is clean;
  • the run ends (Step 14).

Then show the user, for each repository, the branch the work branch will be created from, its head, and how far it is ahead of or behind its upstream: reviewers see only Base..Head, so nothing later revisits where Base came from.

Then continue to Step 4.

Step 4: Read progress file
sh
PROGRESS_FILE="$IMPLEMENT_DIR/progress.md"

$PROGRESS_FILE is the run's index, per 2.2 Progress file. Create it empty if it does not exist. If it is empty, continue to Step 5. If its last record is Complete, tell the user this spec is already built and stop. Otherwise resume: read the records and the artifacts they point to, determine which step the run reached, and continue from that step.

Step 5: Dispatch the implementer

Write $IMPLEMENT_DIR/dispatch/<name>.md — a manifest, per 2.3 Manifests:

text
Role: implementer
Branch: kiko/$SPEC_SLUG
Spec: $SPEC_FILE
Facts: $FACTS_FILE
Output: $IMPLEMENT_DIR/results/<name>.md

Branch is the spec's work branch: in every repository it modifies, the role works on this branch, creating it from the repository's current branch on first touch.

Append this record to $PROGRESS_FILE:

text
Implement — dispatch/<name>.md

Then dispatch the role per 2.4 Dispatch; its role contract is references/implementer.md and its manifest is the file just written.

When the subagent returns, continue to Step 6.

Step 6: Read the subagent result

Read the result at the manifest's Output path. If the subagent returns ERROR: or the result is incomplete, determine how to proceed from the cause and the work already done.

When a complete result is available, adopt it by appending the matching line to $PROGRESS_FILE, reusing the dispatch's <name>. A review result with a Fix section is a review+fix result.

text
Implementation result — results/<name>.md
Review result — results/<name>.md
Review+fix result — results/<name>.md

Then continue by result type: implementation → Step 7; review or review+fix → Step 9.

When a result reports both a spec issue and an external blocker, route by the spec issue.

Step 7: Route the implementation result
  • DONE → Step 8.
  • BLOCKED → spec issue: Step 10; external blocker: Step 11; otherwise Step 12.
Step 8: Dispatch the reviewer

Write $IMPLEMENT_DIR/dispatch/<name>.md — a manifest, per 2.3 Manifests:

text
Role: reviewer
Branch: kiko/$SPEC_SLUG
Spec: $SPEC_FILE
Facts: $FACTS_FILE
Output: $IMPLEMENT_DIR/results/<name>.md
Prior result: <absolute-result-path>
First finding ID: F<n>
  • Prior result is the latest adopted result, per 2.6 Results: the implementation result to review, or the review result whose fixes to verify.
  • First finding ID is one greater than the highest finding ID in any adopted review or review+fix result, or F1 if none.

Append this record to $PROGRESS_FILE:

text
Review — dispatch/<name>.md

Then dispatch the role per 2.4 Dispatch; its role contract is references/reviewer.md and its manifest is the file just written.

When the subagent returns, continue to Step 6.

Step 9: Route the review result
  • Status: clean → Step 13.
  • Status: issues without Fix → spec issue: Step 10; external blocker: Step 11.
  • Fix: DONE whose fixes changed no behavior → Step 13. The fixes changed no behavior when the behavior check returns UNCHANGED for every repository the result lists, from the Head its Prior result records for it (its Base when the prior result does not list it) to its Head.
  • Any other Fix: DONE → Step 8, so a fresh reviewer verifies the fixes; when this is the third or a later Fix: DONE result since the latest Implementation result or Spec amendment record, read and follow references/finding-gate.md instead.
  • Fix: BLOCKED → spec issue: Step 10; external blocker: Step 11; otherwise Step 12.
Step 10: Handle a spec issue

Read and follow references/spec-amendment.md: whether the spec stands or was amended, it ends by dispatching a successor through the reporting result's successor dispatch step.

Step 11: Handle an external blocker

The reporting result names something outside the repositories that blocks progress and the user action that clears it. Show the user both and ask how to proceed.

  • Cleared — dispatch a successor through the reporting result's successor dispatch step.
  • Changed — the user drops, defers, or substitutes the blocked obligation instead.
  • Not now — continue to Step 14; the next run resumes here.

For Changed, edit the spec to say what the user decided, keeping the rules the spec amendment draft follows for identifiers and A coverage; append the [user] decision per 2.5 Decisions and a Spec amendment — DECISION<n> record to $PROGRESS_FILE, and commit the spec with the decision when tracked. Give a deferred obligation a task line in $KIKO_ROOT/TODO.md. Then dispatch a successor as for Cleared.

Step 12: Handle a blocked attempt

The role stopped short with neither a spec issue nor an external blocker; its Remaining says what stopped it, what was tried, and what is needed. Dispatch one successor through the reporting result's successor dispatch step: a fresh attempt holding that record either finishes or stops short again.

If the successor also stops short, show the user its Remaining and ask how to proceed.

  • Continue — dispatch another successor, after the user acts on what is needed if they can.
  • Changed — the user drops, defers, or substitutes the obligation instead: proceed as for Changed in Step 11.
  • Not now — continue to Step 14; the next run resumes here.
Show full SKILL.md (747 more words)Show less
Step 13: Complete

Ask the user how to land the work in every repository the run touched, the ones in the latest adopted result's repository blocks:

  • the agent merges kiko/$SPEC_SLUG into the branch it was created from — its Created from, or the branch the user names where no result records it — and deletes it;
  • the agent pushes the branch for the user to open a pull request;
  • the branch stays as it is.

Do as they choose.

Append Complete to $PROGRESS_FILE.

Report Complete to the user: the key outcomes and every Concern in adopted implementation results that names a decision the user has not made, brief and to the point. The run ends here.

Step 14: Incomplete

The run stops before every obligation is proven. Revert nothing.

Report Incomplete to the user: the cause, the next action, the work branch holding the partial work, and that a later run on the same spec resumes from here — brief and to the point. The run ends here.

2 Concepts

2.1 Implementation directory

The implementation directory ($IMPLEMENT_DIR) is one spec's run state: it persists across invocations and is not committed. It contains only:

text
progress.md
dispatch/
results/

Files in the subdirectories are immutable: never edit or overwrite one — supersede it with a new file. Basenames are random, such as openssl rand -hex 4 gives; a result shares its dispatch's <name>.

2.2 Progress file

The progress file ($PROGRESS_FILE) is an append-only index in order: the last record is where the run stands, and a dispatch record stands even when no result for it is ever adopted. The file contains only these records:

text
Implement — dispatch/<name>.md
Implementation result — results/<name>.md
Review — dispatch/<name>.md
Review result — results/<name>.md
Review+fix result — results/<name>.md
Risk acceptance — DECISION<n>
Spec amendment — DECISION<n>
Complete
2.3 Manifests

A manifest is one dispatch's complete, immutable task statement — everything the role receives beyond its role contract.

Prior result
text
Prior result: <absolute-result-path>
Prior disposition: spec-issue-rejected

Prior result names the latest adopted result, the one the role starts from per 2.6 Results. Every reviewer manifest carries it; an implementer manifest carries it as a successor after a blocked attempt, an external blocker, or a spec issue, whether rejected or adopted as an amendment. Only the rejected case adds the fixed Prior disposition line.

Successor dispatch step

A successor is dispatched through the step matching the reported result's type: an implementation result through Step 5, a review or review+fix result through Step 8.

2.4 Dispatch

Dispatch every role as a fresh subagent with exactly this prompt:

text
Follow the role contract:
<absolute-role-contract-path>

Execute the manifest:
<absolute-manifest-path>

Write the result to the manifest's Output path.
Return only `RESULT: <path>`, or `ERROR: <reason>` if the manifest cannot be safely executed or a complete result cannot be written.

One exception. A successor after a spec issue or an external blocker whose role matches the subagent that wrote its Prior result continues that subagent, sending it the same prompt with the new manifest, when the harness can resume a returned subagent with its context intact — in Claude Code, a message to the agent by name. When it cannot, or that subagent no longer exists, dispatch a fresh subagent. A successor after a blocked attempt is always a fresh subagent.

2.5 Decisions

$DECISIONS_FILE holds one entry per decision made toward the outcome. The entries before this run were written while the spec was formed; during the run only the controller appends, on a spec amendment or a risk acceptance, and commits what it appended when the spec directory is tracked in Git: the write roles refuse a dirty tree. Append-only, never edited or deleted; a changed decision is a new entry that says which ID it supersedes. Numbers in DECISION<n> increase and are never reused.

md
- DECISION<n> [user] <question>
  <answer>
- DECISION<n> [controller] <question>
  <answer>

[user] records the user's decision, in their words where given; [controller] records a decision the controller made itself. The facts a decision rests on are appended to $FACTS_FILE, verified for what the controller established and user for what the user supplied, and named in the answer. Question and answer together have one reading for someone with no run history. Name the R, D, A, or O concerned, and quote a finding rather than only citing F<n>: .implement/ is not committed, so the finding cannot be looked up later. No role receives this file.

2.6 Results

Results are cumulative: a role reads only its Prior result, and the controller takes repository state from the latest adopted result. Every result carries forward the repository blocks of its Prior result — every repository on the work branch, with Base the commit the branch was created from, Created from where recorded, and Head updated to the current commit — and adds any repository this dispatch first touched. A review result also carries forward the findings its Prior result lists. Everything else in a result is that dispatch's own report.

2.7 Behavior check

Dispatch a fresh subagent with exactly this prompt, one line per repository:

text
Read the diff of each repository below between its two commits, excluding `.kiko/`, and change nothing:
<repository-path> <from-sha> <to-sha>

Decide whether any change can make something that runs behave differently: the product, or any tool the project runs on it. That depends on how the project uses the changed file; look in the repository when it decides the answer.

Return only `UNCHANGED` if you established, for every change, that nothing behaves differently. Otherwise return only `CHANGED: <path:line> <reason>`, naming the first change you could not establish that for.

© 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 10 other files (scripts, references, assets) in skills/implement of Levix0501/kiko-skills.

  • SKILL.md
  • assets/implementation-result-template.md
  • assets/review-result-template.md
  • references/facts.md
  • references/finding-gate.md
  • references/implementer.md
  • references/reviewer.md
  • references/spec-amendment.md
  • scripts/check-kiko
  • scripts/prepare-implement-dir
  • tests/run-tests

Open the folder on GitHubat commit 9734a55

Compare with similar skills

Implement 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.

Implement compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implement this skillLevix0501/kiko-skills170—~3.6kAutomated safety check: PassMIT
Review Implement Phaseprisma/orm48k—~1.7kAutomated safety check: PassApache-2.0
MCP Implementation Security Reviewgithub/awesome-copilot40k—~5.2kAutomated safety check: PassMIT
Implementation Final Reviewopenai/openai-agents-python30k—~2kAutomated safety check: PassMIT
Review Pending PR Reviewsnrwl/nx29k—~3.9kAutomated safety check: PassMIT
Reviewthedaviddias/Front-End-Checklist74k—~556Automated safety check: PassMIT

Similar skills

  • Official

    Implements triaged pull request review actions, commits focused fixes, posts status replies on GitHub and resolves the threads.

    48k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, input-schema…

    40k GitHub stars~5.2k tokensUpdated today
    SecurityAuto-check passed
  • Implementation Final Review

    openai/openai-agents-python

    Official

    Review completed implementation changes before final verification.

    30k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners).

    29k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Review

    thedaviddias/Front-End-Checklist

    A skill your agent uses when applies to product pages, local business pages, recipes, apps, books, and any page that aggregates user reviews.

    74k GitHub stars~556 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Post Implementation Review

    EpicenterHQ/epicenter

    Review cumulative implementation for structural collapse, invariant ownership, and correctness.

    4.8k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

More from Levix0501/kiko-skills

  • Create Spec

    Levix0501/kiko-skills

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

    170 GitHub stars~772 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 Implement

What does Implement do?

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

When should I use Implement?

Implement fits situations like: the user asks to implement a spec.

How do I install Implement in Claude Code?

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

How do I install Implement in Codex?

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

Can I use Implement 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 implement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implement, .gemini/skills/implement, .github/skills/implement and .opencode/skills/implement in your project.

What does Implement need to run?

Going by SKILL.md and its folder, Implement needs the command-line tools its instructions call (openssl).

Does Implement 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 Implement 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 Implement use?

Implement 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 Implement use?

About 3.6k tokens (SKILL.md is roughly 14k 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 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Implement?

Skills that share tags, products or a category with Implement: Review Implement Phase (prisma/orm, 48k stars), MCP Implementation Security Review (github/awesome-copilot, 40k stars), Implementation Final Review (openai/openai-agents-python, 30k stars) and Review Pending PR Reviews (nrwl/nx, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implement?

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.