Chalk Labs
Need help deploying ai-execute-plan?
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/cristiano-pacheco-ai-execute-plan
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/ai-execute-plan
What's inside
- Skill name
ai-execute-plan- Description
- Execute a technical implementation plan.
- License
- MIT
- Instructions
- 112 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- implementation-notes-template.md · references/
SKILL.md (first lines)
You are responsible for **correctly implementing an engineering plan**. Read the plan, do the setup, and **implement it** properly - no hacks or shortcuts. This is the execution step for `ai-create-plan`. The plan is read from Obsidian; the **code is written in the local repository**; implementation notes are kept in Obsidian when there is relevant context to preserve. <critical>You are not lazy. Do not rush. Verify the required files, check the tests, and reason carefully to ensure correct understanding and execution.</critical> <critical>THE PLAN IS NOT COMPLETE UNTIL ALL TESTS PASS WITH 100% SUCCESS.</critical> <critical>NEVER mention plan documents in code comments - these documents are not committed to the project, so such references are useless.</critical> <critical>Use the context7 MCP to consult documentation for the languages, frameworks, and libraries involved.</critical> ## Inputs (read from the vault) - Plan: `engineering/<project>/workplans/<plan>/plan.md` - Project standards: the repo's `docs/` folder, if present ## Output to Obsidian Code changes go to the local repository. The only thing written to the Obsidian vault is `implementation-notes.md`, and only when there is relevant context to preserve - written **directly on the local filesystem** (no MCP). **Vault root:** `$OBSIDIAN_AI_VAULT` (defaults to `$HOME/Documents/obsidian/obsidian` if unset). The vault docs live under `<vault>/engineering/...`. Use the `Read`/`Write`/`Edit` tools (and `ls` via Bash) with the **absolute** path, e.g. `$OBSIDIAN_AI_VAULT/engineering/<project>/...`. Wikilink text inside notes stays vault-root-relative and unchanged (`[[engineering/...]]`) - never put the absolute path inside `[[...]]`. **Two separate repositories — never mix them.** This skill writes to **two** different git repos: 1. **The code repo** (the current working directory) - where you implement the plan. Any `git add` / `git commit` here is the user's responsibility and outside this skill's scope; do not auto-commit code unless the user asks. 2. **The vault repo** (`$OBSIDIAN_AI_VAULT`) - where the implementation notes live. The vault commit is delegated to `ai-commit`. <critical>NEVER run `git add` / `git commit` / `git push` against the vault from inside this skill. Delegate the vault commit to the `ai-commit` skill (see `ai-commit/SKILL.md`). `ai-commit` resolves the vault root from `$OBSIDIAN_AI_VAULT` and guards against operating inside the code repo.</critical> If `implementation-notes.md` is written or updated, delegate the vault commit to the `ai-commit` skill. Pass the commit message: ``` ai-execute-plan: <plan> ``` `ai-commit` resolves the vault root from `$OBSIDIAN_AI_VAULT`, stages, commits, and pushes. If `ai-commit` reports nothing staged, no `origin`, or a push failure, report it briefly and finish - don't abort the skill. `ai-setup` configures the repo and its `origin`. ### Resolve the project base path 1. Run `git rev-parse --show-toplevel`; the basename is the project name (this is also the repo you implement in). 2. If not a git repo, propose a name from `basename "$PWD"` (kebab-cased) and **confirm with the user**. 3. Base path: `engineering/<project>`. ### Resolve the plan and read inputs **If the user gave you a plan identifier** (the `<plan>` slug, e.g. `integrate-zoho-provider`) in their request, use it directly as `<plan>` and confirm the folder exists (`ls -1 "<vault>/engineering/<project>/workplans"`). Otherwise, list `<vault>/engineering/<project>/workplans` (`ls -1`) to find the plan folder; if ambiguous or missing, ask the user. Read the plan with the `Read` tool from `<vault>/engineering/<project>/workplans/<plan>/plan.md`. If it's missing, stop and tell the user to run `ai-create-plan` first. ### Maintain implementation notes Create or update `<vault>/engineering/<project>/workplans/<plan>/implementation-notes.md` only when there is relevant context that is not already planned or obvious from the code. Follow `references/implementation-notes-template.md`. Write it with the `Write` tool - it overwrites if present and creates any missing parent folders. Capture only what helps future maintainers or reviewers: - decisions made because the plan was ambiguous or incomplete - assumptions made during implementation - changes made that were not explicitly planned - tradeoffs considered and chosen - deviations from the original plan - issues discovered while implementing - test results and verification notes - anything important that is not obvious from the code Directly under the notes' H1, add a related-links blockquote (this is a vault note, not code - the no-references-in-code rule does not apply here): `> **Plan:** [[engineering/<project>/workplans/<plan>/plan|plan]]`. ### Maintain the index (keep the graph connected) If implementation notes are written, wire them into the Obsidian graph with append-if-missing. Wikilinks use vault-root-relative paths + alias. 1. **Plan index** - `engineering/<project>/workplans/<plan>/index.md`: read it (if missing, create it with `# <plan>` and a `Back: [[engineering/<project>/index|<project>]]` link); if the wikilink for `implementation-notes` isn't present, add a bullet `- [[engineering/<project>/workplans/<plan>/implementation-notes|Implementation Notes]]` under `## Documents` (with the `Edit` tool, or `Write` the updated file). 2. **Project index** - `engineering/<project>/index.md`: ensure a bullet `- [[engineering/<project>/workplans/<plan>/index|<plan>]]` exists under `## Workplans` (create the file with `# <project>` + `Back: [[engineering/index|Engineering]]` if missing). 3. **Root index** - `engineering/index.md`: ensure a bullet `- [[engineering/<project>/index|<project>]]` exists under `## Projects` (create it if missing). Never duplicate an existing link. `ai-reindex` rebuilds all indexes deterministically; this step just keeps the graph live. ## Execution steps ### 1. Pre-plan setup Read the plan and project standards. Understand the requested behavior, dependencies, risks, and verification requirements. ### 2. Plan analysis Consider the main objectives, how the plan fits the project, alignment with project standards, and possible implementation approaches. Identify anything missing or risky before editing code. ### 3. Plan summary Briefly state: Plan ID, objective, key technical approach, files likely to change, dependencies, main risks, and verification commands. ### 4. Approach plan List the concrete steps you will take. ### 5. Implement immediately After the summary and approach, **begin implementing right away**: run required commands, make the code changes in the local repo, and follow established project standards. ### 6. Review Run `make lint && make test` (or the project's equivalent). Fix every issue. Do not finalize until all issues are resolved and tests pass 100%. ### 7. Notes If relevant context exists that was not planned or is not obvious from code, write or update `implementation-notes.md` using the rules above. If nothing relevant needs to be preserved, do not create notes just to say there were none. ### 8. Report State which plan was implemented, which verification commands passed, whether implementation notes were written, and echo `Plan ID: <plan>` so the user can reference it later. <critical>DO NOT SKIP ANY STEP.</critical> <critical>Do not mark anything as completed in the vault. This workflow has no task checkbox.</critical>
From cristiano-pacheco/ai-tools, MIT.
More from cristiano-pacheco/ai-tools
- 0.583score
ai-full-code-review
cristiano-pacheco
Review a branch diff for production risk.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
ai-create-pr
cristiano-pacheco
Write a PR title and description.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
ai-commit
cristiano-pacheco
Commit and push vault artifacts or explicitly scoped code changes.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
ai-code-review
cristiano-pacheco
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.556score
ai-implement
cristiano-pacheco
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
100-go-rules
cristiano-pacheco
Apply a compact, Go-version-aware rulebook derived from the 100 numbered mistakes cataloged by 100go.co when writing, reviewing, debugging, refactoring…
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-execute-task
cristiano-pacheco
Implement the next task from a list.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-review-techspec
cristiano-pacheco
Review a tech spec as principal architect.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-codebase-review
cristiano-pacheco
Audit a whole codebase for bottlenecks.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-create-plan
cristiano-pacheco
Create a technical implementation plan.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-reindex
cristiano-pacheco
Rebuild Obsidian wikilink indexes.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-create-techspec
cristiano-pacheco
Create a tech spec from a PRD.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 22, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cristiano-pacheco/ai-tools
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from cristiano-pacheco
- 0.583score
ai-full-code-review
cristiano-pacheco
Review a branch diff for production risk.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
ai-create-pr
cristiano-pacheco
Write a PR title and description.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
ai-commit
cristiano-pacheco
Commit and push vault artifacts or explicitly scoped code changes.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
ai-code-review
cristiano-pacheco
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.556score
ai-implement
cristiano-pacheco
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
100-go-rules
cristiano-pacheco
Apply a compact, Go-version-aware rulebook derived from the 100 numbered mistakes cataloged by 100go.co when writing, reviewing, debugging, refactoring…
SkillBFreshness: B★ 1Claude 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 ai-execute-plan 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
ai-execute-plan skill. Agent Mart. https://agentmart.dev/skills/cristiano-pacheco-ai-execute-plan (last updated 2026-10-24)