100-go-rules
Apply a compact, Go-version-aware rulebook derived from the 100 numbered mistakes cataloged by 100go.co when writing, reviewing, debugging, refactoring…
Skill by cristiano-pacheco
Chalk Labs
Need help deploying 100-go-rules?
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-100-go-rules
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
Use cases: design, backend, testing, devops
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
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/100-go-rules
What's inside
- Skill name
100-go-rules- Description
- Apply a compact, Go-version-aware rulebook derived from the 100 numbered mistakes cataloged by 100go.co when writing, reviewing, debugging, refactoring, testing, benchmarking, or optimizing Go code. Includes compact bad/better code examples colocated with each of the 100 rules. Use for Go code reviews, API/package design, slices/maps/strings, errors, concurrency, standard-library usage, tests/benchmarks, memory/performance, Docker/Kubernetes runtime behavior, or explicit 100 Go Mistakes rule numbers. Baseline is Go 1.26; adapt to the module's declared Go language version when known.
- License
- MIT
- Instructions
- 89 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (14)
- SKILL.md
- 01-code-project.md · references/
- 02-data-types.md · references/
- 03-control-structures.md · references/
- 04-strings.md · references/
- 05-functions-methods.md · references/
- 06-errors.md · references/
- 07-concurrency-foundations.md · references/
- 08-concurrency-practice.md · references/
- 09-standard-library.md · references/
- 10-testing.md · references/
- 11-optimization-runtime.md · references/
- version-notes-go1.26.md · references/
- validate_rules.py · scripts/
SKILL.md (first lines)
# 100 Go Rules Use this skill as a compact rule engine, not as a book to read end-to-end. ## Selection and operating baseline - Select this global reference for material Go-language or quality decisions. It complements a specialist skill when needed; specialists do not invoke it mechanically. - Locate the target module's `go.mod` before applying version-dependent guidance. Use its `go` directive for language semantics when present. - When no target module or `go` directive is available, use Go 1.26 as the fallback baseline. Do not describe that fallback as a discovered project version. - Treat user-specified version constraints as authoritative. - Read `references/version-notes-go1.26.md` when a finding touches version-sensitive behavior or the project targets a version other than 1.26. - Prefer current Go semantics, compiler/runtime evidence, and standard-library behavior over historical advice. ## Progressive disclosure Load the smallest domain file that covers the task. Each numbered rule is self-contained and keeps its explanation and `Bad`/`Better` examples together, so never search for a second examples file. | Rules | Domain | Reference | |---|---|---| | 1-16 | Code/project | `references/01-code-project.md` | | 17-29 | Data types | `references/02-data-types.md` | | 30-35 | Control structures | `references/03-control-structures.md` | | 36-41 | Strings | `references/04-strings.md` | | 42-47 | Functions/methods | `references/05-functions-methods.md` | | 48-54 | Errors | `references/06-errors.md` | | 55-60 | Concurrency foundations | `references/07-concurrency-foundations.md` | | 61-74 | Concurrency practice | `references/08-concurrency-practice.md` | | 75-81 | Standard library | `references/09-standard-library.md` | | 82-90 | Testing | `references/10-testing.md` | | 91-100 | Optimization/runtime | `references/11-optimization-runtime.md` | Follow these loading rules: 1. For a normal task, load one domain file; load at most three when the code genuinely spans domains. 2. For a specific rule number, load only its domain file and focus on that rule's section. 3. For a code review, use the colocated examples only as diagnostic/remediation aids; do not mechanically copy them into the response. 4. For a full audit against all 100 rules, evaluate domain files sequentially rather than preloading all eleven. 5. Read `references/version-notes-go1.26.md` only for version-sensitive findings or compatibility analysis. ## Execution and completion 1. Determine the effective Go version and select only the applicable domain reference(s). 2. Apply the relevant rules to the concrete code or design decision; validate claims against local code and use focused tests, benchmarks, compiler, or runtime evidence when available. 3. Report the effective version (and whether it was discovered or a fallback), loaded domain(s), material guidance, and validation evidence. State when no validation command was available. ## Applying rules - Treat each rule as a diagnostic heuristic, not an unconditional law. - Prioritize correctness and resource safety, then API clarity/maintainability, then performance. - Validate a suspected issue against actual code context before reporting it. - Do not report a rule merely because its keyword appears. - Do not recommend speculative abstractions or micro-optimizations without evidence. - For performance findings, use or request benchmarks/profiles when the claim depends on workload behavior. - When rules conflict, preserve correctness and choose the simplest API for demonstrated requirements. - Treat each **Bad**/**Better** pair as an illustration, not a mechanical rewrite template. Adapt names, ownership, errors, concurrency, and lifecycle to the actual code. ## Code review output For each material finding, provide: - severity: `bug`, `risk`, `maintainability`, or `performance` - location or code fragment - rule number and short title - concise explanation tied to the concrete code - smallest practical fix - a compact before/after snippet when it materially clarifies the fix - version note only when behavior differs across Go versions Avoid dumping unrelated rules. If no relevant violation is found, say so. ## Code generation and refactoring Apply relevant rules silently while producing code. Mention rule numbers only when they explain a non-obvious design choice, tradeoff, or compatibility constraint. ## Source and adaptation policy The numbered taxonomy and titles originate from Teiva Harsanyi's **100 Go Mistakes and How to Avoid Them** / 100go.co. Rule explanations and code snippets in this skill are compact adaptations written for this skill, updated for Go 1.26, and are not intended as verbatim copies of the site's prose or examples. Preserve this attribution if redistributing or substantially extending the corpus.
From cristiano-pacheco/ai-tools, MIT.
More from cristiano-pacheco/ai-tools
- 0.583score
ai-create-pr
cristiano-pacheco
Write a PR title and description.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
ai-full-code-review
cristiano-pacheco
Review a branch diff for production risk.
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 - 0.543score
ai-create-plan
cristiano-pacheco
Create a technical implementation plan.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-create-techspec
cristiano-pacheco
Create a tech spec from a PRD.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-reindex
cristiano-pacheco
Rebuild Obsidian wikilink indexes.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-execute-plan
cristiano-pacheco
Execute a technical implementation plan.
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-execute-task
cristiano-pacheco
Implement the next task from a list.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-codebase-review
cristiano-pacheco
Audit a whole codebase for bottlenecks.
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
More from cristiano-pacheco
- 0.583score
ai-create-pr
cristiano-pacheco
Write a PR title and description.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
ai-full-code-review
cristiano-pacheco
Review a branch diff for production risk.
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 - 0.543score
ai-codebase-review
cristiano-pacheco
Audit a whole codebase for bottlenecks.
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 100-go-rules 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
100-go-rules skill. Agent Mart. https://agentmart.dev/skills/cristiano-pacheco-100-go-rules (last updated 2026-10-24)