repo-init-official
Use inside repo-init-scan to try a target-local `init` skill, Claude `/init`, or `copilot init`, normalize official init output into…
Skill by funky-eyes
Chalk Labs
Need help deploying repo-init-official?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/funky-eyes-repo-init-official
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
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/repo-init-official
What's inside
- Skill name
repo-init-official- Description
- Use inside repo-init-scan to try a target-local `init` skill, Claude `/init`, or `copilot init`, normalize official init output into `.github/instructions/project.instructions.md`, and decide whether manual fallback is still needed.
- License
- Apache-2.0
- Instructions
- 36 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- run-claude-native-init.sh · scripts/
- run-copilot-native-init.sh · scripts/
SKILL.md (first lines)
# Repo Init Official ## Immediate Execution Rule When this stage has just been loaded inside `repo-init-scan`, the next assistant action must attempt the official initializer or report `official_init_unavailable`, then emit `## Repo Init Official`. Do not stop at `Skill(...repo-init-official...) Successfully loaded`, and do not inspect business source before this stage returns. ## Contract - This is the best-copilot official-init stage. Loading `/best-copilot:repo-init-official` or `Skill(best-copilot:repo-init-official)` makes this stage's instructions available; it is not the same thing as running the runtime's built-in `/init`. - Try a target-local `init` skill first when it is discoverable and the active runtime can invoke skills non-interactively. This means `skills/init/SKILL.md` for Claude Code and Copilot plugin directories, plus `.claude/skills/init/SKILL.md` for Claude Code. For Copilot CLI, `skills/init/SKILL.md` is mechanically invokable only when the target root is a plugin directory with `plugin.json`; otherwise report `local_init_skill_status=uninvokable_missing_plugin_json` and fall back to `copilot init`. Invoke successful candidates from the target root through the bundled official helper, record `attempted=target_local_init_skill`, and treat them as successful only when a recognized init artifact is written on disk. - In Copilot CLI or other shell-capable runtimes, if no target-local `init` skill succeeds and `copilot init` exists, run `copilot init` automatically before manual fallback through `repo-init-official/scripts/run-copilot-native-init.sh`. This is the normal command fallback for Copilot. - In Claude Code, if no target-local `init` skill succeeds, attempt Claude Code's built-in `/init` command automatically through the bundled helper script before manual fallback when the helper path is discoverable from `CLAUDE_SKILL_DIR` or the active plugin directory. This is the native command shown by Claude as "Initialize a new CLAUDE.md file with codebase documentation"; it is not a best-copilot skill. The helper uses a bounded `claude --bare --permission-mode acceptEdits -p "/init"` attempt so the native Claude initializer can write the target `CLAUDE.md` without loading this plugin recursively. `BEST_COPILOT_CLAUDE_NATIVE_INIT_TIMEOUT_SECONDS` may shorten the default 45-second timeout for smoke tests. If the helper cannot be located, report `official_init_unavailable` and continue to manual fallback instead of blocking solely on helper discovery. - Prefer a directly invokable bare runtime `/init` command when the active session exposes one. This bare `/init` is distinct from best-copilot plugin skills such as `/repo-init-official` or `/best-copilot:repo-init-official`. - Normalize useful output into the target `.github/instructions/project.instructions.md` when the official initializer produces enough facts directly. Recognized helper artifacts such as target `CLAUDE.md`, `.github/copilot-instructions.md`, and `AGENTS.md` are also successful official evidence; `repo-init-manual-fallback` must then preserve and normalize their useful facts into `.github/instructions/project.instructions.md`. - Do not treat chat output alone as success. Either the facts file must exist on disk with real facts or explicit `unknown` gaps, or the helper must have written a recognized artifact that the manual fallback can normalize. - In Claude Code, do not report `official_init_unavailable` merely because the assistant cannot call a UI slash command directly. First try the helper script. If the helper succeeds and creates `.github/instructions/project.instructions.md`, `CLAUDE.md`, `AGENTS.md`, or another recognized init artifact, report `success`. - In Copilot CLI, do not report `official_init_unavailable` merely because the assistant loaded this skill text. First try the target-local `init` skill when present, then `copilot init` through the bundled helper when the shell command is available. If the helper succeeds and creates `.github/instructions/project.instructions.md`, `.github/copilot-instructions.md`, `AGENTS.md`, or another recognized init artifact, report `success`. - Report `official_init_unavailable` only when no official initializer is available or known in the current runtime, no `copilot init` command can be run, and no prior `/init` / `copilot init` output or artifacts are available to normalize. - If official init runs but only returns chat text without a verified facts file, fails, times out, or reports missing authentication, report `official_init_no_write`, `official_init_incomplete`, or `official_init_unavailable` and continue to `repo-init-manual-fallback`. Do not stop after loading this skill. - If official init is unavailable, does not write the file, or leaves those fact categories incomplete, hand off to `repo-init-manual-fallback`. - This stage does not certify scaffold completeness and does not write `best-copilot.md`; those remain owned by `repo-init-manual-fallback`. ## Output ```markdown ## Repo Init Official - status: success|official_init_unavailable|official_init_no_write|official_init_incomplete - attempted: target_local_init_skill|copilot_init|claude_native_slash_init|bare_init|none - native_command: /init when attempted=claude_native_slash_init - native_command: copilot init when attempted=copilot_init - artifacts: <files created or normalized, such as CLAUDE.md, .github/copilot-instructions.md, and .github/instructions/project.instructions.md> ``` When a target-local `init` skill is present but does not write a recognized artifact, the helper may continue to the runtime command fallback. In that case `attempted` may contain a comma-separated attempt chain such as `target_local_init_skill,claude_native_slash_init`.
From funky-eyes/best-copilot, Apache-2.0.
More from funky-eyes/best-copilot
- 0.599score
evolution-loop
funky-eyes
Use after meaningful task closeout, repeated failure, review loops, stale triggers, or user feedback that an agent/skill/workflow should improve.
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
target-instructions-bootstrap
funky-eyes
Create the target repository's local AI instruction scaffold during first-use bootstrap.
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
td-python-coding-guidelines
funky-eyes
Use when writing or reviewing Python code, fixing lint/docstring/import/naming/exception/type annotation issues, unifying team style, or migrating `.py` files…
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
structured-review
funky-eyes
Use when reviewing code diffs, implementation changes, agent/skill/instruction customization, targeted re-review, review feedback intake, review handoff…
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
td-java-coding-guidelines
funky-eyes
Use when writing or reviewing Java code involving Tongdun/Alibaba Java rules, exceptions, logging, SQL/MyBatis, security, middleware, concurrency, virtual…
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
core-workflow-contract
funky-eyes
Use when an agent needs the shared best-copilot contract for source priority, runtime adapters, init gates, work modes, dispatch packets, review…
SkillBFreshness: B★ 12Claude Code +9 - 0.596score
target-memory-bootstrap
funky-eyes
Create the target repository's local memory skeleton after repo init.
SkillBFreshness: B★ 12Claude Code +9 - 0.596score
repo-init-manual-fallback
funky-eyes
Use inside repo-init-scan after the official stage whenever scaffold verification, bounded repair, or `best-copilot.md` rewrite is still needed.
SkillBFreshness: B★ 12Claude Code +9 - 0.596score
repo-init-gate
funky-eyes
Use before repo-init-scan to cheaply decide whether a target repository already satisfies the current best-copilot init contract by reading only the root…
SkillBFreshness: B★ 12Claude Code +9 - 0.596score
target-spec-bootstrap
funky-eyes
Create the target repository's local spec skeleton and reusable requirements/design/tasks templates.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
gitnexus-guide
funky-eyes
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
security-reviewer-workflow
funky-eyes
Use when reviewing authentication, authorization, dependencies, configuration, release surfaces, sensitive data, logging, validation, CORS, secrets, or…
SkillBFreshness: B★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jun 1, 2026 (5 months ago)
- Last release
- Aug 3, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/funky-eyes/best-copilot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from funky-eyes
- 0.599score
evolution-loop
funky-eyes
Use after meaningful task closeout, repeated failure, review loops, stale triggers, or user feedback that an agent/skill/workflow should improve.
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
td-java-coding-guidelines
funky-eyes
Use when writing or reviewing Java code involving Tongdun/Alibaba Java rules, exceptions, logging, SQL/MyBatis, security, middleware, concurrency, virtual…
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
core-workflow-contract
funky-eyes
Use when an agent needs the shared best-copilot contract for source priority, runtime adapters, init gates, work modes, dispatch packets, review…
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
td-python-coding-guidelines
funky-eyes
Use when writing or reviewing Python code, fixing lint/docstring/import/naming/exception/type annotation issues, unifying team style, or migrating `.py` files…
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
target-instructions-bootstrap
funky-eyes
Create the target repository's local AI instruction scaffold during first-use bootstrap.
SkillBFreshness: B★ 12Claude Code +9 - 0.599score
structured-review
funky-eyes
Use when reviewing code diffs, implementation changes, agent/skill/instruction customization, targeted re-review, review feedback intake, review handoff…
SkillBFreshness: B★ 12Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get repo-init-official running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
repo-init-official skill. Agent Mart. https://agentmart.dev/skills/funky-eyes-repo-init-official (last updated 2026-10-24)