[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ADTNCJH4NFCFPEPNKBWBH8":3,"skill-same:01M7ADTNCJH4NFCFPEPNKBWBH8":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7ADTNCJH4NFCFPEPNKBWBH8","project-setup",null,"Use when starting work on a new or existing project that lacks a `.devin\u002F` configuration, or when the user wants to add skills, hooks, rules, and local tools to a project in a systematic, validated way.","Leostruka\u002Fdevin-bundle","Leostruka","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81370685?v=4","01M7AD8MAK63VDNAWRDRRRW04N","leandro ostruka","01M7AD8MBS65YDS1KMMV7YPM07",0,"MIT","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fproject-setup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: project-setup\ndescription: Use when starting work on a new or existing project that lacks a `.devin\u002F` configuration, or when the user wants to add skills, hooks, rules, and local tools to a project in a systematic, validated way.\nversion: 1.0.0\ntriggers: [user, model]\n---\n\n# Project Setup\n\nSet up a Devin CLI project workspace inside `.devin\u002F` only. This is a systematic, validated workflow that adapts the `continuous-improvement` 10-step loop to project onboarding.\n\n## Principle\n\nEvery project that the agent touches deserves a predictable, auditable `.devin\u002F` setup. Nothing agent-facing is written outside `.devin\u002F`. The skill does not write business code or install project dependencies unless they are required for the agent to function.\n\n## When to use\n\n- The repo has no `.devin\u002F` directory.\n- `.devin\u002F` exists but is incomplete (no rules, no hooks, no skills, no memory, no agent config).\n- The user asks to \"set up the project for the agent\", \"add skills\u002Fhooks\", or \"prepare this repo for Devin CLI\".\n\n## When NOT to use\n\n- The project already has a complete `.devin\u002F` and the user wants a specific edit - use `\u002Fself-extend` instead.\n- The task is to write application code - use `\u002Fimplement` or `\u002Ftdd`.\n- The user only wants a global config change - use `~\u002F.config\u002Fdevin\u002F` paths.\n\n## FASE 0 - Deep Research (before any change)\n\nRun these checks in order and record the evidence. Do not proceed until each step has a concrete output.\n\n1. **Inspect the repo.**\n   - `git remote -v` and `.git\u002Fconfig` - GitHub, GitLab, or none?\n   - `ls -la` (or `Get-ChildItem`) at the repo root - what files and directories already exist?\n   - Look for `package.json`, `pyproject.toml`, `requirements.txt`, `Cargo.toml`, `pnpm-workspace.yaml`, `go.mod`, `pom.xml`, or similar stack signals.\n   - Look for `src\u002F`, `packages\u002F*`, `apps\u002F*`, `tests\u002F` to detect monorepo.\n\n2. **Inspect existing `.devin\u002F` (if any).**\n   - `ls -la .devin\u002F` - what is already configured?\n   - Read `.devin\u002Fconfig.json`, `.devin\u002Fhooks.v1.json`, `.devin\u002Fmcp_config.json` if they exist.\n   - List `.devin\u002Fskills\u002F*\u002F` and `.devin\u002Frules\u002F*.md`.\n\n3. **Confirm Devin CLI conventions.**\n   - Rules: `.devin\u002Fglobal_rules.md` and `.devin\u002Frules\u002F*.md` (sources: Devin CLI docs, `self-extend` skill).\n   - Skills: `.devin\u002Fskills\u002F\u003Cname>\u002FSKILL.md`.\n   - Hooks: `.devin\u002Fhooks.v1.json`.\n   - MCP: `.devin\u002Fmcp_config.json` and `.devin\u002Fmcp_config.local.json` (gitignored).\n   - Memory: `.devin\u002Fmemory\u002F` (see `\u002Fproject-memory`).\n\n4. **List the bundle resources available.**\n   - Read the global bundle `config.json`, `manifest.json`, and `AGENTS.md` to know which skills, scripts, and hooks can be copied into the project.\n\n## LOOP DE SETUP (10 passos)\n\n### Passo 1 - OBSERVAR\n\nRecord the current state in a ledger at `.devin\u002Fledgers\u002Fproject-setup.md` (create the `ledgers\u002F` directory if it does not exist):\n\n```markdown\n# Project setup: \u003Crepo-name>\n\n## Observed\n- Stack: \u003Cdetected stack>\n- Monorepo: \u003Cyes\u002Fno>\n- Remote: \u003Cgithub\u002Fgitlab\u002Fnone>\n- Existing `.devin\u002F`: \u003Clist files>\n\n## Missing\n- \u003Crule file>\n- \u003Chook file>\n- \u003Cskill file>\n- \u003Cmemory dir>\n```\n\n### Passo 2 - CRITICAR\n\nCompare the observed state against the rule: **all agent files must live in `.devin\u002F`**. Identify every missing or mis-placed item. For each missing item, note which bundle resource should provide it.\n\n### Passo 3 - GERAR ALTERNATIVAS\n\nFor each missing component, generate at least two alternatives and record trade-offs:\n\n| Component | Alt 1 | Alt 2 | Alt 3 | Best fit |\n|---|---|---|---|---|\n| Issue tracker | GitHub (gh) | Local markdown | GitLab | depends on `git remote` |\n| Rules | `.devin\u002Fglobal_rules.md` | `.devin\u002Frules\u002F*.md` | both | both |\n| Memory | `.devin\u002Fmemory\u002F` | none | - | always enable |\n| Hooks | copy bundle hooks | create minimal set | none | copy from bundle |\n| MCP | `.devin\u002Fmcp_config.json` template | none | - | ask user |\n\n### Passo 4 - REVISAR\n\nApply the best-fit alternative for each component. This is the deterministic setup order:\n\n1. **Run the engineering-skills setup** to configure issue tracker, triage labels, and domain docs (all inside `.devin\u002F`).\n2. **Create `.devin\u002Fglobal_rules.md`** with a short `## Agent skills` block and the repo-specific rules from the engineering-skills setup.\n2.5. **Create `.devin\u002Frules\u002Fagents.md` from the project template** - copy `skills\u002Fproject-setup\u002Ftemplates\u002Fagents.md` into `.devin\u002Frules\u002Fagents.md` and replace the stack-specific placeholder with the project's concrete rules (e.g., TypeScript without `any`, linter commands, naming conventions). This is the project's per-stack agent rules file; keep it short and action-oriented.\n3. **Create `.devin\u002Frules\u002F*.md`** for optional, trigger-scoped rules.\n4. **Create `.devin\u002Fhooks.v1.json`** with the essential hooks from the bundle:\n   - `behavioral-nudge.py` on `UserPromptSubmit`\n   - `check-ai-signature.py` on `PreToolUse` for `write`\u002F`edit`\n   - `check-push-green.py` on `PreToolUse` for `exec`\n   - `destructive-gate.py` on `PreToolUse` for `exec`\n   - `context-budget.py` on `SessionStart`\n   - `memory-retrieval.py` on `UserPromptSubmit`\n   - `memory-post-edit.py` on `PostToolUse` for `write`\u002F`edit`\n   - `memory-post-exec.py` on `PostToolUse` for `exec`\n   - `memory-stop.py` on `Stop`\n5. **Create `.devin\u002Fmcp_config.json`** as an empty scaffold if the project has no MCP servers; otherwise ask the user which servers to add.\n6. **Create `.devin\u002Fskills\u002Fproject-memory\u002F`** if it does not exist, copying `note.md`, `capture-memory.py`, `query-memory.py`, and `audit-memory.py` from the bundle. Use `\u002Fproject-memory` to walk the user through the first capture.\n7. **Create a local copy of the engineering-skills setup** if the user wants the engineering flow available locally.\n8. **Create `.devin\u002Fmemory\u002F`** directory and seed `MOC.md`.\n\n### Passo 4.5 - POPULAR A BASE DE CONHECIMENTO\n\nThe `.devin\u002F` structure is not a solid base until it has content. Run the following setup skills in order, recording everything in `.devin\u002Fledgers\u002Fproject-setup.md`:\n\n1. **Run `grilling`** to capture the project's big-picture goals, constraints, and stakeholders. Save the approved design (if one emerges) to `.devin\u002Fspecs\u002F`.\n2. **Run `domain-modeling`** to build `.devin\u002FCONTEXT.md` and `.devin\u002Fadr\u002F`. Resolve ambiguous or overloaded terms before they leak into code.\n3. **Run `project-memory`** to capture a first memory entry - stack, conventions, and any decisions the user already shared.\n4. **Run `triage`** once on the existing issue tracker to show the user the triage flow and confirm label mapping.\n5. **Run `planning-pipeline`** on the most urgent item to demonstrate the spec -> tickets flow.\n\nStop after each step if the user has no content to populate yet. The goal is to leave the project with at least a populated `CONTEXT.md`, one memory entry, and a triaged issue, not to force a full spec.\n\n### Passo 5 - VALIDAR\n\nRun the project-level validation suite:\n\n- `python audit.py` in the project root if the project has one.\n- If no project audit exists, run a minimal structural check:\n  - `ls .devin\u002Fglobal_rules.md`, `.devin\u002Fhooks.v1.json`, `.devin\u002Fmcp_config.json`, `.devin\u002Fskills\u002F`, `.devin\u002Fmemory\u002F`\n  - `python -m json.tool .devin\u002Fhooks.v1.json`\n  - `python -m json.tool .devin\u002Fmcp_config.json`\n\n### Passo 6 - FUTURE PACE\n\nProject the setup against 3 hypothetical future sessions:\n\n1. **New feature request** - does the agent know where to write tickets, capture memory, and read domain docs?\n2. **Code review request** - does the agent find the standards sources and the `AGENTS.md` rule block?\n3. **Multi-session task** - does the agent have memory retrieval hooks and a local issue tracker to record progress?\n\nAt least two must be clearly helped; otherwise the setup is incomplete.\n\n### Passo 7 - ECOLOGICAL CHECK\n\nCheck for side effects:\n\n- Did the setup create any file outside `.devin\u002F`? If yes, delete or move it.\n- Did any hook conflict with an existing project hook?\n- Is the `context-budget.py` hook adding too much token cost?\n- Are there duplicate skills in `.devin\u002Fskills\u002F` and `%APPDATA%\u002Fdevin\u002Fskills\u002F`?\n\n### Passo 8 - SIMULAR\n\nRun `install.ps1 -Force` (or copy the `.devin\u002F` files) and restart a fresh Devin CLI session against the project. Verify:\n\n- `skill list --path .devin\u002Fskills` shows the local skills.\n- `python audit.py` (or the structural check) passes.\n- A test `write` to a project file triggers `check-ai-signature.py` (if configured).\n\n### Passo 9 - CLASSIFICAR\n\nClassify the setup:\n\n| Classe | Critério | Ação |\n|---|---|---|\n| **MELHOROU** | All 3 future scenarios helped, no side effects, validation passed | Mark ledger as `done` |\n| **NEUTRO** | Validation passed, no side effects, but \u003C2 scenarios helped | Revisit missing component |\n| **PIOROU** | Validation failed or side effects found | Revert the offending change and return to Passo 3 |\n| **INCONCLUSIVO** | Could not simulate (no fresh session) | Do not declare done; ask user to test |\n\n### Passo 10 - REPETIR OU CONVERGIR\n\n- If the user asks for more tools, skills, or hooks, return to **Passo 1** and update the ledger.\n- If nothing more is requested and the setup is classified **MELHOROU** or **NEUTRO**, the setup is complete.\n\n## Output format\n\nWhen finishing, report:\n\n```\nSETUP: \u003Crepo-name>\nOBSERVED: \u003Cstack> | \u003Cmonorepo> | \u003Cremote>\nFASE0: \u003Csources checked>\nCOMPONENTS: \u003Clist of .devin\u002F files created or updated>\nVALIDATION: \u003Cpass|fail>\nFUTURE_PACE: \u003Cn\u002F3 scenarios helped>\nECOLOGICAL: \u003Cside effects or none>\nCLASSIFICATION: \u003CMELHOROU|NEUTRO|PIOROU|INCONCLUSIVO>\nPENDING: \u003Cwhat the user still needs to decide or provide>\n```\n\n## Red flags - STOP and ask\n\n- The user asks to write files outside `.devin\u002F`.\n- A requested hook conflicts with the project's CI or security policy.\n- The user wants to skip the engineering-skills setup but still use `triage`, `planning-pipeline`, or `wayfinder`.\n- A proposed MCP server requires a secret that the user has not provided.\n\n## Common mistakes\n\n- Copying every global skill into the project. Only copy skills that benefit from project-specific tuning; the global bundle is still available.\n- Creating `AGENTS.md` at the project root. Always prefer `.devin\u002Fglobal_rules.md`.\n- Skipping the ledger. Without a ledger, the agent cannot prove completion.\n- Skipping simulation. A setup that is not loaded by a fresh session is not done.\n\n## Cross-references\n\n- The engineering-skills setup - issue tracker, triage labels, domain docs.\n- `\u002Fgrilling` - capture the project's goals and produce a design doc.\n- `\u002Fai-coding-dictionary` - align any AI-coding jargon before it enters the project glossary.\n- `\u002Fdomain-modeling` - build `.devin\u002FCONTEXT.md` and `.devin\u002Fadr\u002F`.\n- `\u002Fproject-memory` - capture and retrieve project knowledge.\n- `\u002Ftriage` - first triage run on the issue tracker.\n- `\u002Fplanning-pipeline` - demonstrate spec → tickets flow.\n- `\u002Fself-extend` - add individual rules, skills, hooks, or MCP servers.\n- `\u002Fcontinuous-improvement` - the 10-step loop this skill adapts.\n","# Project Setup\n\nSet up a Devin CLI project workspace inside `.devin\u002F` only. This is a systematic, validated workflow that adapts the `continuous-improvement` 10-step loop to project onboarding.\n\n## Principle\n\nEvery project that the agent touches deserves a predictable, auditable `.devin\u002F` setup. Nothing agent-facing is written outside `.devin\u002F`. The skill does not write business code or install project dependencies unless they are required for the agent to function.\n\n## When to use\n\n- The repo has no `.devin\u002F` directory.\n- `.devin\u002F` exists but is incomplete (no rules, no hooks, no skills, no memory, no agent config).\n- The user asks to \"set up the project for the agent\", \"add skills\u002Fhooks\", or \"prepare this repo for Devin CLI\".\n\n## When NOT to use\n\n- The project already has a complete `.devin\u002F` and the user wants a specific edit - use `\u002Fself-extend` instead.\n- The task is to write application code - use `\u002Fimplement` or `\u002Ftdd`.\n- The user only wants a global config change - use `~\u002F.config\u002Fdevin\u002F` paths.\n\n## FASE 0 - Deep Research (before any change)\n\nRun these checks in order and record the evidence. Do not proceed until each step has a concrete output.\n\n1. **Inspect the repo.**\n   - `git remote -v` and `.git\u002Fconfig` - GitHub, GitLab, or none?\n   - `ls -la` (or `Get-ChildItem`) at the repo root - what files and directories already exist?\n   - Look for `package.json`, `pyproject.toml`, `requirements.txt`, `Cargo.toml`, `pnpm-workspace.yaml`, `go.mod`, `pom.xml`, or similar stack signals.\n   - Look for `src\u002F`, `packages\u002F*`, `apps\u002F*`, `tests\u002F` to detect monorepo.\n\n2. **Inspect existing `.devin\u002F` (if any).**\n   - `ls -la .devin\u002F` - what is already configured?\n   - Read `.devin\u002Fconfig.json`, `.devin\u002Fhooks.v1.json`, `.devin\u002Fmcp_config.json` if they exist.\n   - List `.devin\u002Fskills\u002F*\u002F` and `.devin\u002Frules\u002F*.md`.\n\n3. **Confirm Devin CLI conventions.**\n   - Rules: `.devin\u002Fglobal_rules.md` and `.devin\u002Frules\u002F*.md` (sources: Devin CLI docs, `self-extend` skill).\n   - Skills: `.devin\u002Fskills\u002F\u003Cname>\u002FSKILL.md`.\n   - Hooks: `.devin\u002Fhooks.v1.json`.\n   - MCP: `.devin\u002Fmcp_config.json` and `.devin\u002Fmcp_config.local.json` (gitignored).\n   - Memory: `.devin\u002Fmemory\u002F` (see `\u002Fproject-memory`).\n\n4. **List the bundle resources available.**\n   - Read the global bundle `config.json`, `manifest.json`, and `AGENTS.md` to know which skills, scripts, and hooks can be copied into the project.\n\n## LOOP DE SETUP (10 passos)\n\n### Passo 1 - OBSERVAR\n\nRecord the current state in a ledger at `.devin\u002Fledgers\u002Fproject-setup.md` (create the `ledgers\u002F` directory if it does not exist):\n\n```markdown\n# Project setup: \u003Crepo-name>\n\n## Observed\n- Stack: \u003Cdetected stack>\n- Monorepo: \u003Cyes\u002Fno>\n- Remote: \u003Cgithub\u002Fgitlab\u002Fnone>\n- Existing `.devin\u002F`: \u003Clist files>\n\n## Missing\n- \u003Crule file>\n- \u003Chook file>\n- \u003Cskill file>\n- \u003Cmemory dir>\n```\n\n### Passo 2 - CRITICAR\n\nCompare the observed state against the rule: **all agent files must live in `.devin\u002F`**. Identify every missing or mis-placed item. For each missing item, note which bundle resource should provide it.\n\n### Passo 3 - GERAR ALTERNATIVAS\n\nFor each missing component, generate at least two alternatives and record trade-offs:\n\n| Component | Alt 1 | Alt 2 | Alt 3 | Best fit |\n|---|---|---|---|---|\n| Issue tracker | GitHub (gh) | Local markdown | GitLab | depends on `git remote` |\n| Rules | `.devin\u002Fglobal_rules.md` | `.devin\u002Frules\u002F*.md` | both | both |\n| Memory | `.devin\u002Fmemory\u002F` | none | - | always enable |\n| Hooks | copy bundle hooks | create minimal set | none | copy from bundle |\n| MCP | `.devin\u002Fmcp_config.json` template | none | - | ask user |\n\n### Passo 4 - REVISAR\n\nApply the best-fit alternative for each component. This is the deterministic setup order:\n\n1. **Run the engineering-skills setup** to configure issue tracker, triage labels, and domain docs (all inside `.devin\u002F`).\n2. **Create `.devin\u002Fglobal_rules.md`** with a short `## Agent skills` block and the repo-specific rules from the engineering-skills setup.\n2.5. **Create `.devin\u002Frules\u002Fagents.md` from the project template** - copy `skills\u002Fproject-setup\u002Ftemplates\u002Fagents.md` into `.devin\u002Frules\u002Fagents.md` and replace the stack-specific placeholder with the project's concrete rules (e.g., TypeScript without `any`, linter commands, naming conventions). This is the project's per-stack agent rules file; keep it short and action-oriented.\n3. **Create `.devin\u002Frules\u002F*.md`** for optional, trigger-scoped rules.\n4. **Create `.devin\u002Fhooks.v1.json`** with the essential hooks from the bundle:\n   - `behavioral-nudge.py` on `UserPromptSubmit`\n   - `check-ai-signature.py` on `PreToolUse` for `write`\u002F`edit`\n   - `check-push-green.py` on `PreToolUse` for `exec`\n   - `destructive-gate.py` on `PreToolUse` for `exec`\n   - `context-budget.py` on `SessionStart`\n   - `memory-retrieval.py` on `UserPromptSubmit`\n   - `memory-post-edit.py` on `PostToolUse` for `write`\u002F`edit`\n   - `memory-post-exec.py` on `PostToolUse` for `exec`\n   - `memory-stop.py` on `Stop`\n5. **Create `.devin\u002Fmcp_config.json`** as an empty scaffold if the project has no MCP servers; otherwise ask the user which servers to add.\n6. **Create `.devin\u002Fskills\u002Fproject-memory\u002F`** if it does not exist, copying `note.md`, `capture-memory.py`, `query-memory.py`, and `audit-memory.py` from the bundle. Use `\u002Fproject-memory` to walk the user through the first capture.\n7. **Create a local copy of the engineering-skills setup** if the user wants the engineering flow available locally.\n8. **Create `.devin\u002Fmemory\u002F`** directory and seed `MOC.md`.\n\n### Passo 4.5 - POPULAR A BASE DE CONHECIMENTO\n\nThe `.devin\u002F` structure is not a solid base until it has content. Run the following setup skills in order, recording everything in `.devin\u002Fledgers\u002Fproject-setup.md`:\n\n1. **Run `grilling`** to capture the project's big-picture goals, constraints, and stakeholders. Save the approved design (if one emerges) to `.devin\u002Fspecs\u002F`.\n2. **Run `domain-modeling`** to build `.devin\u002FCONTEXT.md` and `.devin\u002Fadr\u002F`. Resolve ambiguous or overloaded terms before they leak into code.\n3. **Run `project-memory`** to capture a first memory entry - stack, conventions, and any decisions the user already shared.\n4. **Run `triage`** once on the existing issue tracker to show the user the triage flow and confirm label mapping.\n5. **Run `planning-pipeline`** on the most urgent item to demonstrate the spec -> tickets flow.\n\nStop after each step if the user has no content to populate yet. The goal is to leave the project with at least a populated `CONTEXT.md`, one memory entry, and a triaged issue, not to force a full spec.\n\n### Passo 5 - VALIDAR\n\nRun the project-level validation suite:\n\n- `python audit.py` in the project root if the project has one.\n- If no project audit exists, run a minimal structural check:\n  - `ls .devin\u002Fglobal_rules.md`, `.devin\u002Fhooks.v1.json`, `.devin\u002Fmcp_config.json`, `.devin\u002Fskills\u002F`, `.devin\u002Fmemory\u002F`\n  - `python -m json.tool .devin\u002Fhooks.v1.json`\n  - `python -m json.tool .devin\u002Fmcp_config.json`\n\n### Passo 6 - FUTURE PACE\n\nProject the setup against 3 hypothetical future sessions:\n\n1. **New feature request** - does the agent know where to write tickets, capture memory, and read domain docs?\n2. **Code review request** - does the agent find the standards sources and the `AGENTS.md` rule block?\n3. **Multi-session task** - does the agent have memory retrieval hooks and a local issue tracker to record progress?\n\nAt least two must be clearly helped; otherwise the setup is incomplete.\n\n### Passo 7 - ECOLOGICAL CHECK\n\nCheck for side effects:\n\n- Did the setup create any file outside `.devin\u002F`? If yes, delete or move it.\n- Did any hook conflict with an existing project hook?\n- Is the `context-budget.py` hook adding too much token cost?\n- Are there duplicate skills in `.devin\u002Fskills\u002F` and `%APPDATA%\u002Fdevin\u002Fskills\u002F`?\n\n### Passo 8 - SIMULAR\n\nRun `install.ps1 -Force` (or copy the `.devin\u002F` files) and restart a fresh Devin CLI session against the project. Verify:\n\n- `skill list --path .devin\u002Fskills` shows the local skills.\n- `python audit.py` (or the structural check) passes.\n- A test `write` to a project file triggers `check-ai-signature.py` (if configured).\n\n### Passo 9 - CLASSIFICAR\n\nClassify the setup:\n\n| Classe | Critério | Ação |\n|---|---|---|\n| **MELHOROU** | All 3 future scenarios helped, no side effects, validation passed | Mark ledger as `done` |\n| **NEUTRO** | Validation passed, no side effects, but \u003C2 scenarios helped | Revisit missing component |\n| **PIOROU** | Validation failed or side effects found | Revert the offending change and return to Passo 3 |\n| **INCONCLUSIVO** | Could not simulate (no fresh session) | Do not declare done; ask user to test |\n\n### Passo 10 - REPETIR OU CONVERGIR\n\n- If the user asks for more tools, skills, or hooks, return to **Passo 1** and update the ledger.\n- If nothing more is requested and the setup is classified **MELHOROU** or **NEUTRO**, the setup is complete.\n\n## Output format\n\nWhen finishing, report:\n\n```\nSETUP: \u003Crepo-name>\nOBSERVED: \u003Cstack> | \u003Cmonorepo> | \u003Cremote>\nFASE0: \u003Csources checked>\nCOMPONENTS: \u003Clist of .devin\u002F files created or updated>\nVALIDATION: \u003Cpass|fail>\nFUTURE_PACE: \u003Cn\u002F3 scenarios helped>\nECOLOGICAL: \u003Cside effects or none>\nCLASSIFICATION: \u003CMELHOROU|NEUTRO|PIOROU|INCONCLUSIVO>\nPENDING: \u003Cwhat the user still needs to decide or provide>\n```\n\n## Red flags - STOP and ask\n\n- The user asks to write files outside `.devin\u002F`.\n- A requested hook conflicts with the project's CI or security policy.\n- The user wants to skip the engineering-skills setup but still use `triage`, `planning-pipeline`, or `wayfinder`.\n- A proposed MCP server requires a secret that the user has not provided.\n\n## Common mistakes\n\n- Copying every global skill into the project. Only copy skills that benefit from project-specific tuning; the global bundle is still available.\n- Creating `AGENTS.md` at the project root. Always prefer `.devin\u002Fglobal_rules.md`.\n- Skipping the ledger. Without a ledger, the agent cannot prove completion.\n- Skipping simulation. A setup that is not loaded by a fresh session is not done.\n\n## Cross-references\n\n- The engineering-skills setup - issue tracker, triage labels, domain docs.\n- `\u002Fgrilling` - capture the project's goals and produce a design doc.\n- `\u002Fai-coding-dictionary` - align any AI-coding jargon before it enters the project glossary.\n- `\u002Fdomain-modeling` - build `.devin\u002FCONTEXT.md` and `.devin\u002Fadr\u002F`.\n- `\u002Fproject-memory` - capture and retrieve project knowledge.\n- `\u002Ftriage` - first triage run on the issue tracker.\n- `\u002Fplanning-pipeline` - demonstrate spec → tickets flow.\n- `\u002Fself-extend` - add individual rules, skills, hooks, or MCP servers.\n- `\u002Fcontinuous-improvement` - the 10-step loop this skill adapts.\n",{"name":5,"version":24,"triggers":25,"description":7},"1.0.0",[26,27],"user","model","main","02b95ddb62959a00b3c31442c2046aca0d19563c","skills\u002Fproject-setup",1,"https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle","https:\u002F\u002Fleostruka.github.io\u002Fdevin-bundle\u002F","https:\u002F\u002Fgithub.com\u002FLeostruka","2026-11-15 05:19:58",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Leostruka\u002Fdevin-bundle --skill project-setup",{"tool":42,"command":43},"bunx","bunx skills add Leostruka\u002Fdevin-bundle --skill project-setup",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Leostruka\u002Fdevin-bundle --skill project-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fproject-setup\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"templates\u002Fagents.md","REFERENCE","参考文档",1477,"https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fproject-setup\u002Ftemplates\u002Fagents.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7E0K3MG2XC4FSRV0MK6SFR1","montador-de-ideias","Use when assembling, expanding, or elevating a raw project idea or initial prompt into an ultra-detailed, first-principles dossier and compiled master prompt with journalistic OSINT market research, Tech Lead and Staff Architect justifications, atomic and modular hardening\u002Foptimization, and high-impact contact surfaces.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fmontador-de-ideias\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7E0J7JJWZ8QMK01RZ3B3C9Z","git-github-adaptive-engineering","Use when any task touches git history, GitHub issues\u002FPRs\u002Freleases\u002FCI, repo governance, or branch and merge decisions. Runs the Fase Zero situational-awareness battery, picks one of five delivery flows via the adaptive decision engine, and enforces commit\u002FPR information-density standards. Orchestrates the gh, git-workflows, github-actions, pr, and debug\u002Ffinish skills.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fgit-github-adaptive-engineering\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7E0GJFRPFEVQQMXEM58EWDM","adaptive-agenda-calendar-routine-engine","Use when planning or executing work across hours, days, weeks, or sprints. Turns the calendar into a strict time-blocked agenda (HH:MM-HH:MM blocks carrying a routine profile, expected inputs, and a handoff output artifact), runs the 5-stage cognitive flow (Radar and Hunt -> Triage plus Steve Jobs conception -> workbench manifest -> >=32-cycle loop -> Close plus Open-Minded Scrum), and unfolds macro calendar milestones into micro agenda blocks through extensions\u002Fgcal\u002Fwrapper.py.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fadaptive-agenda-calendar-routine-engine\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AE2K9FTY0BVS48N0A9JFKF","demo","Use when demonstrating a skill in a fixture project.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7AE2G3DP38PTV3B1N7MW5TS","duplicate-skill","Use when testing duplicate skill name detection.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Fbeta\u002FSKILL.md",[],[],{"skillNo":93,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AE2DBR8ZHT6T875MJ392GK","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Falpha\u002FSKILL.md",[],[]]