new-skill
Skill12 starsChanged 2 months agoMITView on GitHub
Create a new ai-kit skill end to end — ground in the repo's Archcore rules, collect the brief from the user, draft with skill-creator, apply ai-kit conventions, then hand off to review-and-release. Use when the user says "/new-skill", "давай новый скилл", "add a skill to ai-kit", or describes a capability they want packaged as a skill in this repository.
25 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- antick/skillstheir own version, first seen Nov 16, 2026
- th3r-dev/th3-skillstheir own version, first seen Nov 16, 2026
- rafapeixer/go-skillstheir own version, first seen Nov 15, 2026
- rafapeixer/db-skillstheir own version, first seen Nov 8, 2026
- genericService/claude-skillstheir own version, first seen Nov 8, 2026
- cicorias/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use review-skill, commit and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MongoDBSkillreview-skill
Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise SMEs on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.
Also in 3 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 4 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions25 projects use a version of this.
Word for word · 1
- ivklgn/bag-of-skills★ 12100% same
Edited · 1
- TheLatentSpaceLab/Qubito★ 116% same
Wrote their own version · 23
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- hyhmrright/brooks-lint★ 1.6ksame name
- remorses/kimaki★ 1.4ksame name
- MusserLab/lab-claude-skills★ 6same name
- qunyou-agent/finance-skills★ 4same name
- press-pass/journalism-skills★ 2same name
- th3r-dev/th3-skills★ 2same name
- 0xkangl/skills★ 1same name
- Andersonnn7788/claude-code-101★ 1same name
- cicorias/skills★ 1same name
13 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- review-and-releaseSkill
- 12-factor-appsSkill
- ask-meSkill
- audit-websiteSkill
- can-i-useSkill
- code-reviewerSkill
- compatibility-auditSkill
- explain-branch-changesSkill
- humanizer-ruSkill
- humanizerSkill
- jsdocSkill
- load-branch-changesSkill
- nextjs-developerSkill
- recapSkill
- reset-permissionsSkill
- review-golangSkill
- seo-auditSkill
- simplify-code-commentsSkill
- test-health-checkSkill
- update-golang-depsSkill
- update-node-depsSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run the steps in order. Step 1 is the only one that questions the user.
- Distinctive: line 18
Before asking anything, read what already binds:
- Very specific: line 25
Read two or three existing SKILL.md files closest in shape to the request.
- Distinctive: line 31
Ask the user. Batch these into one question widget where the host offers one.
- Very specific: line 44
Do not ask about a standalone README.md — the repo default is no.
- Very specific: line 72
Frontmatter: Add model: <answer 3> alongside name and description.
- Very specific: line 100
Add argument-hint: "[--flag]" to the frontmatter only when the skill takes flags — commands/reset-permissions.md is the one example.
- Very specific: line 111
If the skill's design settled a question that will bind future work — a new convention, a rejected alternative, a model chosen against the …
- Very specific: line 118
Run /review-and-release. It validates conventions, rebuilds the README ## Skills and ## Commands lists, mirrors skills/ and agents/ into …
- Distinctive: line 122
Do not hand-edit the README lists or the version — that skill owns them.
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
New Skill
A harness for adding one skill to this repository. It sequences three existing
instruments — Archcore, skill-creator, /review-and-release — and fills the gap
between them: skill-creator writes portable skills, this repo ships plugin skills,
and the two disagree on frontmatter, packaging, and file layout.
Run the steps in order. Step 1 is the only one that questions the user.
Step 0: Ground in the repo's rules
Before asking anything, read what already binds:
mcp__archcore__search_documentswithcontent: "skill command naming"— thenget_documenton.archcore/conventions/project-stack.rule.md. It fixes the file layout, the frontmatter fields, and the kebab-case naming rule.ls skills/— check no skill already covers the requested job. A near-duplicate is a reason to extend an existing skill instead, and a reason to say so before Step 1.- Read two or three existing
SKILL.mdfiles closest in shape to the request. They are the style baseline —skills/recap/SKILL.mdfor a short one,skills/compatibility-audit/SKILL.mdfor one withreferences/andscripts/.
Step 1: Collect the brief
Ask the user. Batch these into one question widget where the host offers one; otherwise one message per question, most important first. Recommend an answer for every question.
| # | Question | Recommended default |
| 1 | What does the skill do, and what are 2–3 concrete invocations of it? | — the user must supply this |
| 2 | What phrasings should trigger it? | derived from answer 1; confirm the list |
| 3 | model: haiku, sonnet, or opus? | sonnet; haiku for a mechanical skill under ~60 lines |
| 4 | A slash command in commands/? | yes when the skill is an action the user fires at a moment; no when it is domain expertise the model picks up from the description |
| 5 | Bundled scripts/, references/, or assets/? | none — 5 of 20 skills carry nothing but SKILL.md |
| 6 | Original text, or a port of something external? | original; a port switches on the license track in Step 3 |
| 7 | Output language | English, unless the skill's subject is Russian text |
Do not ask about a standalone README.md — the repo default is no. Add one only when the
user asks for the skill to be installable on its own via npx degit.
Step 2: Draft with skill-creator
Invoke the skill-creator skill and follow its craft guidance: progressive disclosure,
degrees of freedom, writing a description that carries all the triggering information,
keeping SKILL.md lean.
Two deviations from its process:
init_skill.py— runscripts/init_skill.py <name> --path skills/only when answer 5 named bundled resources. It scaffolds examplescripts/,references/, andassets/directories that then have to be deleted. For aSKILL.md-only skill, write the file directly.- Step 5, packaging — skip it.
package_skill.pybuilds a.skillarchive for standalone distribution; ai-kit ships through the plugin marketplace, and nothing in this repo consumes a.skillfile.
Step 3: Apply ai-kit conventions
This is the delta skill-creator does not know about.
- Location. The skill lives at
skills/<name>/SKILL.mdin the repo root. Never author underplugins/ai-kit/skills/— that tree is generated byrsyncat release and any edit there is overwritten. - Name. kebab-case, one string reused in four places: the directory, the frontmatter
name, the command filename, and the/ai-kit:<name>invocation. - Frontmatter. Add
model: <answer 3>alongsidenameanddescription.skill-creatorsays to include no field beyondnameanddescription; this repo overrides that —/review-and-releasefails a skill that carries neithermodelnordisable-model-invocation: true. - Do not run
quick_validate.pyorpackage_skill.py. Both reject every skill in this repository: their allowed-frontmatter list isname,description,license,allowed-tools,metadata, somodel:reads as an unexpected key./review-and-releaseis this repo's validator. Command file, when answer 4 was yes —
commands/<name>.md, exactly this shape:--- description: <one line, imperative, same subject as the skill description> --- # /ai-kit:<name> ## Arguments The user invoked this command with: $ARGUMENTS <one line on what an empty value means, and what a non-empty value selects> ## Instructions Use the skill at `skills/<name>/SKILL.md`.Add
argument-hint: "[--flag]"to the frontmatter only when the skill takes flags —commands/reset-permissions.mdis the one example.- A port, when answer 6 said so — read
.archcore/importing-external-components.rule.mdand follow it: check the upstream license, add theTHIRD-PARTY-LICENSES.mdmap row and full license text, writeskills/<name>/ATTRIBUTION.md, and add the README Credits bullet. A skill written from scratch that reuses only ideas gets the map row and the Credits bullet, and noATTRIBUTION.md.
Step 4: Record the decision, when there was one
If the skill's design settled a question that will bind future work — a new convention, a
rejected alternative, a model chosen against the default — record it with
/archcore:document as an adr under .archcore/skills/. .archcore/skills/compatibility-audit-model.adr.md
is the worked example. A routine skill that follows every existing rule needs no document.
Step 5: Release
Run /review-and-release. It validates conventions, rebuilds the README ## Skills and
## Commands lists, mirrors skills/ and agents/ into plugins/ai-kit/, bumps the
patch version in both plugin manifests, and commits.
Do not hand-edit the README lists or the version — that skill owns them.
Result
Report: the skill path, whether a command was created, the new version, the commit hash, and any Archcore document written.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

