Not in the top 1,000 by GitHub stars
Levix0501/kiko-skills
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/create-spec/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
9734a55a9d4e → 9734a55a9d4e
skills/implement/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
9734a55a9d4e → 9734a55a9d4e
skills/kick-off/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
9734a55a9d4e → 9734a55a9d4e
skills/setup-kiko/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
9734a55a9d4e → 9734a55a9d4e
Verified commit 9734a55a9d4e08d8d4d92306a9494b732c9c9e4a
git clone --filter=blob:none --no-checkout https://github.com/Levix0501/kiko-skills.git .hotskills/levix0501-kiko-skills && git -C .hotskills/levix0501-kiko-skills checkout --detach 9734a55a9d4e08d8d4d92306a9494b732c9c9e4a
# Copy each selected skill directory from .hotskills/levix0501-kiko-skills into .claude/skills/<skill-name>/Heat
2.1- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- create-spec
skills/create-spec - implement
skills/implement - kick-off
skills/kick-off - setup-kiko
skills/setup-kiko
How it works
create-spec
When your agent uses it
Turn the design into a build-ready spec a fresh context can implement and verify. Use when the user asks to create a spec.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
719 tokensWhen the skill is activated
Reference documents
12,384 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Locate the spec directory
- 2. Classify the design
- 3. Draft and preflight
- 4. Review with the user
- 5. Commit the confirmed version
Scripts executed separately
scripts/check-kikotests/run-tests../implement/scripts/check-kiko../implement/scripts/prepare-implement-dir../implement/tests/run-tests../kick-off/scripts/check-kiko../setup-kiko/scripts/init-kiko
Files
../../.claude-plugin/plugin.jsonasset376 bytesSKILL.mdcore3,087 bytesassets/spec-template.mddoc1,751 bytesreferences/facts.mddoc1,112 bytesreferences/self-review.mddoc2,772 bytesreferences/spec-rules.mddoc6,552 bytesscripts/check-kikoruns1,424 bytestests/run-testsruns4,343 bytestests/semantic-cases.mddoc2,729 bytes../implement/SKILL.mddoc14,411 bytes../implement/assets/implementation-result-template.mddoc1,893 bytes../implement/assets/review-result-template.mddoc2,128 bytes../implement/references/facts.mddoc1,364 bytes../implement/references/finding-gate.mddoc1,303 bytes../implement/references/implementer.mddoc3,472 bytes../implement/references/reviewer.mddoc4,916 bytes../implement/references/spec-amendment.mddoc2,334 bytes../implement/scripts/check-kikoruns1,424 bytes../implement/scripts/prepare-implement-dirruns2,137 bytes../implement/tests/run-testsruns16,881 bytes../kick-off/SKILL.mddoc6,153 bytes../kick-off/agents/openai.yamlasset197 bytes../kick-off/references/records.mddoc2,292 bytes../kick-off/scripts/check-kikoruns1,424 bytes../setup-kiko/SKILL.mddoc957 bytes../setup-kiko/agents/openai.yamlasset181 bytes../setup-kiko/scripts/init-kikoruns3,459 bytes
Read SKILL.md
`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`.
View the complete source on GitHubimplement
When your agent uses it
Turn a spec into reviewed, shippable code. Use when the user asks to implement a spec.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
3,374 tokensWhen the skill is activated
Reference documents
3,704 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1 Workflow
- 2 Concepts
Scripts executed separately
scripts/check-kikoscripts/prepare-implement-dirtests/run-tests
Files
SKILL.mdcore14,411 bytesSKILL.mdcore14,411 bytesSKILL.mdcore14,411 bytesassets/implementation-result-template.mddoc1,893 bytesassets/review-result-template.mddoc2,128 bytesreferences/facts.mddoc1,364 bytesreferences/finding-gate.mddoc1,303 bytesreferences/implementer.mddoc3,472 bytesreferences/reviewer.mddoc4,916 bytesreferences/spec-amendment.mddoc2,334 bytesscripts/check-kikoruns1,424 bytesscripts/prepare-implement-dirruns2,137 bytestests/run-testsruns16,881 bytes
Read SKILL.md
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 `$PROJECT_ROOT` as its only argument, and use the returned path as `KIKO_ROOT`.
- Exit 3: ask the user to run the `setup-kiko` skill at the project root, then retry.
- Any other nonzero exit: report the error and stop.
Do not initialize or repair `.kiko`. On success, continue to Step 2.View the complete source on GitHubkick-off
When your agent uses it
Cut the request into outcomes, pick what to build next, and interview until every decision about it is settled.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
1,318 tokensWhen the skill is activated
Reference documents
577 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workspace
- Cut and pick
- Interview
- Summary
- Next action
Scripts executed separately
scripts/check-kiko
Files
SKILL.mdcore6,153 bytesagents/openai.yamlasset197 bytesreferences/records.mddoc2,292 bytesscripts/check-kikoruns1,424 bytes
Read SKILL.md
## Workspace
Run `scripts/check-kiko` with the opened project root's absolute path as its only argument, and use the returned path as `KIKO_ROOT`. On exit 3, ask the user to run the `setup-kiko` skill at the project root, then retry. On any other nonzero exit, report the error and stop. Do not initialize or repair `.kiko`, and suggest no substitute for `setup-kiko`.
## Cut and pick
Take the request the user brings, which may be empty, together with what is waiting in `$KIKO_ROOT/TODO.md` as one whole, and cut it vertically into outcomes that are each verifiable on their own: a narrow but complete path through every layer it touches, never one layer of the whole. An outcome waits on the outcomes without which it cannot be delivered and accepted, and on no others; importance never overrides a dependency.
Importance is the mark an outcome carries: `[P0]` for what must ship for the work to count, `[P1]` for what must follow, `[P2]` for what can wait. An outcome inherits the highest mark among the outcomes that wait on it. Propose a mark for every outcome that has none.
Show the user the outcomes in the shape `$KIKO_ROOT/TODO.md` takes:
```md
# TODOView the complete source on GitHubsetup-kiko
When your agent uses it
Initialize or repair the project-local .kiko workspace at the project root.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
211 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
scripts/init-kiko
Files
SKILL.mdcore957 bytesagents/openai.yamlasset181 bytesscripts/init-kikoruns3,459 bytes
Read SKILL.md
Run the bundled `scripts/init-kiko <project-root>` with the opened project root and report the path it prints. The script is idempotent: it creates any missing part of `.kiko/{TODO.md,docs/,.implement/,.gitignore}` while preserving existing artifacts and custom ignore content, so rerunning it also repairs an incomplete layout.
Initialize the root the user intends to work in — not a subdirectory and not a parent that happens to contain it. If the opened directory is ambiguous, ask the user to confirm the root first.
If the script warns that the root is not inside a Git worktree, tell the user Git has not been initialized there and the kiko artifacts are local-only; never run `git init` for them.
If the script exits with an error, show its message and stop; never create or repair `.kiko` by hand.View the complete source on GitHubSkills included
- create-spec
- implement
- kick-off
- setup-kiko
Repository facts
- License
- MIT
- Created
- Aug 5, 2026
- Last pushed
- Sep 24, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
skills/implement/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/implement/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 12 dangerous shell commandsin 2 files: skills/setup-kiko/scripts/init-kiko:64 skills/implement/tests/run-tests:21
- No network access
- No hidden or obfuscated text
- No instruction overrides
- 12 executable scriptsin 7 files: skills/implement/scripts/check-kiko:1 skills/implement/scripts/prepare-implement-dir:1 skills/implement/tests/run-tests:1 and 4 more
- No access to secrets
- No requests to vote in Hot
Show all 24 signals by file
skills/create-spec/scripts/check-kiko
- Executable scriptline 1
#!/usr/bin/env bash
skills/create-spec/tests/run-tests
- Executable scriptline 1
#!/usr/bin/env bash
skills/implement/scripts/check-kiko
skills/implement/scripts/prepare-implement-dir
skills/implement/tests/run-tests
skills/kick-off/scripts/check-kiko
skills/setup-kiko/scripts/init-kiko
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 64
[ -z "$tmp_file" ] || rm -f -- "$tmp_file" || true - Dangerous shell operationline 64
[ -z "$tmp_file" ] || rm -f -- "$tmp_file" || true - Dangerous shell operationline 79
rm -f -- "$tmp_file" - Dangerous shell operationline 79
rm -f -- "$tmp_file" - Dangerous shell operationline 92
rm -f -- "$tmp_file" - Dangerous shell operationline 92
rm -f -- "$tmp_file" - Dangerous shell operationline 97
rm -f -- "$tmp_file" - Dangerous shell operationline 97
rm -f -- "$tmp_file" - Dangerous shell operationline 103
rm -f -- "$tmp_file" - Dangerous shell operationline 103
rm -f -- "$tmp_file"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 24 facts
- Executable script in code of a file that runscreate-spec/scripts/check-kiko:1High confidence
- Executable script in code of a testcreate-spec/tests/run-tests:1Low confidence
- Executable script in code of a file that runsskills/implement/scripts/check-kiko:1High confidence
- Executable script in code of a file that runsimplement/scripts/check-kiko:1High confidence
- Executable script in code of a file that runsskills/implement/scripts/prepare-implement-dir:1High confidence
- Executable script in code of a file that runsimplement/scripts/prepare-implement-dir:1High confidence
- Executable script in code of a testskills/implement/tests/run-tests:1Low confidence
- Executable script in code of a testimplement/tests/run-tests:1Low confidence
- Dangerous shell operation in code of a testskills/implement/tests/run-tests:21Low confidence
- Dangerous shell operation in code of a testimplement/tests/run-tests:21Low confidence
- Executable script in code of a file that runsskills/kick-off/scripts/check-kiko:1High confidence
- Executable script in code of a file that runskick-off/scripts/check-kiko:1High confidence
- Executable script in code of a file that runsskills/setup-kiko/scripts/init-kiko:1High confidence
- Executable script in code of a file that runssetup-kiko/scripts/init-kiko:1High confidence
- Dangerous shell operation in code of a file that runsskills/setup-kiko/scripts/init-kiko:64High confidence
- Dangerous shell operation in code of a file that runssetup-kiko/scripts/init-kiko:64High confidence
- Dangerous shell operation in code of a file that runsskills/setup-kiko/scripts/init-kiko:79High confidence
- Dangerous shell operation in code of a file that runssetup-kiko/scripts/init-kiko:79High confidence
- Dangerous shell operation in code of a file that runsskills/setup-kiko/scripts/init-kiko:92High confidence
- Dangerous shell operation in code of a file that runssetup-kiko/scripts/init-kiko:92High confidence
- Dangerous shell operation in code of a file that runsskills/setup-kiko/scripts/init-kiko:97High confidence
- Dangerous shell operation in code of a file that runssetup-kiko/scripts/init-kiko:97High confidence
- Dangerous shell operation in code of a file that runsskills/setup-kiko/scripts/init-kiko:103High confidence
- Dangerous shell operation in code of a file that runssetup-kiko/scripts/init-kiko:103High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/create-spec/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/create-spec/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/create-spec/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/create-spec/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/create-spec/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.