coding
Canonical Arkira coding guidance for planning, implementation, and review of a bounded repository outcome.
Skill by jeanchastel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jeanchastel-coding
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/coding
What's inside
- Skill name
coding- Description
- Canonical Arkira coding guidance for planning, implementation, and review of a bounded repository outcome. Reuse existing solutions and finish the accepted delivery unit.
- License
- MIT
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Coding a bounded outcome Before implementation, state the requested result, observable acceptance criteria, delivery target, owned paths, and non-goals. Reuse an approved plan. Group related agent subtasks into one reviewable integration unit before creating branches. One integration owner owns final edits, evidence, and publication; delegated units return changes and evidence, not separate releases. Inspect existing components, utilities, installed packages, standard libraries, and native platform features first. Briefly assess fit, maintenance, portability, accessibility, licensing, and integration cost. Choose once sufficient evidence supports a suitable option. For suitable frontend work, prefer Base UI with Tailwind or a comparable portable solution; respect an existing suitable stack and explicit requirements. Do not migrate a working repo merely to standardize a preference. Reuse maintained accessible primitives for dialogs, menus, forms, focus management, and keyboard behavior. Verify the actual interaction, labels, focus restoration, error state, and relevant screen sizes with installed repo E2E tooling. Do not hand-roll common UI behavior or infrastructure that an existing portable solution already provides. Custom code should address a stated product-specific gap with minimal new surface. Avoid wrappers, abstractions, or dependencies without a concrete need. During development, use focused checks that can expose the changed behavior. Review the combined candidate independently once. Broader integration validation belongs at the integration boundary; consume its authoritative result later while revision, relevant configuration, dependencies, and merge context remain valid. Revalidate only what subsequent changes invalidate. Deployment checks verify the intended revision and target environment plus remaining acceptance criteria, not an automatic repeat of the full suite. Follow adjacent dependencies only when they directly block acceptance or verification. Record other findings once for later. Do not add unrelated refactors, migrations, speculative infrastructure, or new features. Once acceptance passes, finish the requested delivery target and stop. Planning and review use this same source. No extra generic approval or mechanical validation layer is required; add a mechanical check only for a demonstrated recurring violation it can detect reliably.
From jeanchastel/arkira, MIT.
More from jeanchastel/arkira
- 0.570score
click-audit
jeanchastel
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out…
SkillAFreshness: AClaude Code +9 - 0.570score
onboarding
jeanchastel
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.
SkillAFreshness: AClaude Code +9 - 0.570score
intent-layer
jeanchastel
Scaffold or audit a repo's hierarchical AGENTS.md Intent Layer.
SkillAFreshness: AClaude Code +9 - 0.570score
intake-runbook
jeanchastel
Take a client's externally-hosted project (Lovable export, a repo on another GitHub/GitLab, a dev project) and re-home it onto your own GitHub + Vercel, then…
SkillAFreshness: AClaude Code +9 - 0.567score
design-system
jeanchastel
Generate or audit a design system from Tailwind or CSS tokens, extract and check design tokens, run an AI-slop visual-consistency audit, and review…
SkillAFreshness: AClaude Code +9 - 0.565score
adr
jeanchastel
Capture architectural decisions made during Claude Code sessions as structured ADRs with context, alternatives considered, rationale, and an ADR log.
SkillAFreshness: AClaude Code +9 - 0.565score
bug-report
jeanchastel
Use when behavior looks like an Arkira harness defect in any repo, including bin/arkira, goal, gate, session state, hooks, or Arkira CI workflows.
SkillAFreshness: AClaude Code +9 - 0.565score
context-discipline
jeanchastel
Use when a task involves heavy file reading, repo-wide search, or long tool output.
SkillAFreshness: AClaude Code +9 - 0.565score
css-tokens
jeanchastel
Migrate hardcoded color, spacing, and typography values in static-site CSS to custom properties aligned with the static-web token layer and entity brand kit.
SkillAFreshness: AClaude Code +9 - 0.565score
deploy-prep
jeanchastel
Pre-flight gate before pushing a static brochure site to FTP or Netlify, composing html-audit, a11y-audit-aa, perf-budget, responsive, and deploy-specific…
SkillAFreshness: AClaude Code +9 - 0.565score
perf-budget
jeanchastel
Check a static brochure site against the static-web performance budget: Lighthouse mobile 90+, page weight under 1MB, WebP with srcset, self-hosted fonts with…
SkillAFreshness: AClaude Code +9 - 0.561score
native-scaffold
jeanchastel
Scaffold an Expo + React Native native app version of an existing Arkira web app with shared design tokens and EAS.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 7, 2026 (1 month ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jeanchastel/arkira
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jeanchastel
- 0.570score
click-audit
jeanchastel
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out…
SkillAFreshness: AClaude Code +9 - 0.570score
intake-runbook
jeanchastel
Take a client's externally-hosted project (Lovable export, a repo on another GitHub/GitLab, a dev project) and re-home it onto your own GitHub + Vercel, then…
SkillAFreshness: AClaude Code +9 - 0.570score
intent-layer
jeanchastel
Scaffold or audit a repo's hierarchical AGENTS.md Intent Layer.
SkillAFreshness: AClaude Code +9 - 0.570score
onboarding
jeanchastel
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.
SkillAFreshness: AClaude Code +9 - 0.567score
design-system
jeanchastel
Generate or audit a design system from Tailwind or CSS tokens, extract and check design tokens, run an AI-slop visual-consistency audit, and review…
SkillAFreshness: AClaude Code +9 - 0.565score
adr
jeanchastel
Capture architectural decisions made during Claude Code sessions as structured ADRs with context, alternatives considered, rationale, and an ADR log.
SkillAFreshness: AClaude Code +9
Cite this page
coding skill. Agent Mart. https://agentmart.dev/skills/jeanchastel-coding (last updated 2026-10-24)