diff --git a/CLAUDE.md b/CLAUDE.md index 471416b..b1154b2 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -189,10 +189,11 @@ Place these directives at the very top of the body, before the first heading, in | --- | --- | --- | --- | | **Persona** | Optional | `**Persona:** You are a . .` | Analytical/generative/multi-mode skills | | **Thinking mode** | Optional | `**Thinking mode:** Use \`ultrathink\` for . .` | Deep analysis: profiling, security auditing, root cause analysis | +| **Orchestration mode** | Optional | `**Orchestration mode:** Use \`ultracode\` for . .` | Skills with a parallel fan-out audit/scan/cleanup mode (up to N sub-agents) | | **Modes** | Optional | `**Modes:**` section listing each invocation mode and its sub-agent strategy | Skills invoked in distinct contexts (audit, coding, review, code understanding...) | | **Dependencies** | Optional | `**Dependencies:**` list of required binaries with install commands | Skills that require external tools beyond `go` (e.g. `benchstat`, `dlv`, `golangci-lint`) | -All four are optional. A short procedural skill may have none. A complex orchestrating skill may have all four. +All five are optional. A short procedural skill may have none. A complex orchestrating skill may have all five. The **Dependencies** block lists only non-trivial developer tools โ€” skip universal system utilities (e.g. `curl`, `git`). Prefer `go install` over `brew install` when the tool provides a Go install path; use `brew install` only for tools without one (e.g. `protoc`). Place this block last among the top-of-body directives, just before the first `#` heading. @@ -273,6 +274,18 @@ When creating or modifying a skill that involves deep analysis, profiling, debug Update the README.md Ultrathink column (๐Ÿง  emoji) to keep track of skills requiring ultrathink mode. +### Ultracode policy + +Skills that already describe a full-codebase audit/scan/cleanup mode with several parallel sub-agents (e.g. "launch up to 5 parallel sub-agents") include an **Orchestration mode:** `ultracode` instruction in their SKILL.md body. When you encounter this instruction and the user is requesting a broad, codebase-wide sweep, escalate to multi-agent fan-out orchestration instead of a single sequential pass. + +When creating or modifying a skill whose audit/scan/cleanup mode already fans out to parallel sub-agents, add this line in the top-of-body directives block, after **Thinking mode** (if present, otherwise after **Persona**) and before **Modes**: + +``` +**Orchestration mode:** Use `ultracode` for . . +``` + +Update the README.md Ultracode column (๐Ÿค– emoji) to keep track of skills requiring ultracode mode. + ### Tool reference sections When a skill mentions an important tool (e.g. `go test`, `pprof`, `dlv`, `benchstat`), create a `references/` markdown file with a comprehensive reference section listing many command examples. This helps users discover tool capabilities without leaving the skill content. diff --git a/README.md b/README.md index ad21b36..30d7c00 100644 --- a/README.md +++ b/README.md @@ -172,6 +172,7 @@ These skills are designed as **atomic, cross-referencing units**. A skill may re - โŒ To-do - โšก Command available - ๐Ÿง  Ultrathink automatically +- ๐Ÿค– Ultracode automatically - โš™๏ธ Overridable (see doc below) - **Description (tok)**: weight of the `description` field from YAML frontmatter, always loaded into Claude's context for skill triggering - **SKILL.md (tok)**: weight of the full `SKILL.md` file loaded when the skill triggers @@ -183,30 +184,30 @@ These skills are designed as **atomic, cross-referencing units**. A skill may re | | Skill | Flags | Error rate gap | Description (tok) | SKILL.md (tok) | Directory (tok) | | --- | --- | --- | --- | --- | --- | --- | -| โญ๏ธ | โœ… `golang-code-style` | โšก โš™๏ธ | -40% | 115 | 2,069 | 2,685 | +| โญ๏ธ | โœ… `golang-code-style` | โšก ๐Ÿค– โš™๏ธ | -40% | 115 | 2,069 | 2,685 | | โญ๏ธ | โœ… `golang-data-structures` | โšก | -39% | 92 | 2,497 | 6,216 | | โญ๏ธ | โœ… `golang-database` | โšก โš™๏ธ | -38% | 97 | 2,725 | 7,248 | | โญ๏ธ | โœ… `golang-design-patterns` | โšก โš™๏ธ | -37% | 66 | 2,610 | 9,316 | -| โญ๏ธ | โœ… `golang-documentation` | โšก โš™๏ธ | -53% | 73 | 3,017 | 11,116 | -| โญ๏ธ | โœ… `golang-error-handling` | โšก โš™๏ธ | -26% | 139 | 1,520 | 4,394 | +| โญ๏ธ | โœ… `golang-documentation` | โšก ๐Ÿค– โš™๏ธ | -53% | 73 | 3,017 | 11,116 | +| โญ๏ธ | โœ… `golang-error-handling` | โšก ๐Ÿค– โš™๏ธ | -26% | 139 | 1,520 | 4,394 | | โญ๏ธ | โœ… `golang-how-to` | โšก | โ€” | 165 | 2,254 | 10,372 | -| โญ๏ธ | โœ… `golang-modernize` | โšก | -61% | 68 | 2,719 | 9,032 | +| โญ๏ธ | โœ… `golang-modernize` | โšก ๐Ÿค– | -61% | 68 | 2,780 | 9,093 | | โญ๏ธ | โœ… `golang-naming` | โšก โš™๏ธ | -23% | 158 | 2,865 | 7,233 | | โญ๏ธ | โœ… `golang-safety` | โšก | -58% | 78 | 2,457 | 5,227 | -| โญ๏ธ | โœ… `golang-testing` | โšก ๐Ÿง  โš™๏ธ | -32% | 113 | 3,105 | 6,212 | -| โญ๏ธ | โœ… `golang-troubleshooting` | โšก ๐Ÿง  | -32% | 126 | 2,735 | 15,901 | -| โญ๏ธ | โœ… `golang-security` | โšก ๐Ÿง  | -32% | 85 | 3,094 | 21,530 | +| โญ๏ธ | โœ… `golang-testing` | โšก ๐Ÿง  ๐Ÿค– โš™๏ธ | -32% | 113 | 3,105 | 6,212 | +| โญ๏ธ | โœ… `golang-troubleshooting` | โšก ๐Ÿง  ๐Ÿค– | -32% | 126 | 2,735 | 15,901 | +| โญ๏ธ | โœ… `golang-security` | โšก ๐Ÿง  ๐Ÿค– | -32% | 85 | 3,160 | 21,596 | | | โœ… `golang-benchmark` | โšก ๐Ÿง  | -50% | 102 | 2,814 | 29,996 | | | โœ… `golang-cli` | โšก | -43% | 122 | 2,274 | 6,089 | -| | โœ… `golang-concurrency` | โšก โš™๏ธ | -39% | 71 | 1,873 | 6,338 | +| | โœ… `golang-concurrency` | โšก ๐Ÿค– โš™๏ธ | -39% | 71 | 1,873 | 6,338 | | | โœ… `golang-context` | โšก โš™๏ธ | -34% | 80 | 1,144 | 3,940 | | | โœ… `golang-continuous-integration` | โšก | -59% | 82 | 2,835 | 6,477 | -| | โœ… `golang-dependency-injection` | โšก โš™๏ธ | -47% | 176 | 2,842 | 5,113 | +| | โœ… `golang-dependency-injection` | โšก ๐Ÿค– โš™๏ธ | -47% | 176 | 2,842 | 5,113 | | | โœ… `golang-dependency-management` | โšก | -54% | 77 | 2,361 | 5,499 | | | โœ… `golang-structs-interfaces` | โšก โš™๏ธ | -35% | 110 | 2,999 | 2,999 | -| | โœ… `golang-lint` | โšก | -41% | 98 | 1,714 | 5,493 | -| | โœ… `golang-observability` | โšก โš™๏ธ | -37% | 161 | 2,921 | 18,453 | -| | โœ… `golang-performance` | โšก ๐Ÿง  | -39% | 130 | 2,121 | 18,121 | +| | โœ… `golang-lint` | โšก ๐Ÿค– | -41% | 98 | 1,714 | 5,493 | +| | โœ… `golang-observability` | โšก ๐Ÿค– โš™๏ธ | -37% | 161 | 2,921 | 18,453 | +| | โœ… `golang-performance` | โšก ๐Ÿง  ๐Ÿค– | -39% | 130 | 2,190 | 18,190 | | | โœ… `golang-pkg-go-dev` | โšก | โ€” | 185 | 2,693 | 4,302 | | | โœ… `golang-popular-libraries` | โšก | -30% | 61 | 893 | 4,287 | | | โœ… `golang-project-layout` | โšก | -38% | 69 | 1,510 | 5,718 | diff --git a/skills/golang-code-style/SKILL.md b/skills/golang-code-style/SKILL.md index 8968872..63d39dd 100644 --- a/skills/golang-code-style/SKILL.md +++ b/skills/golang-code-style/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.0" + version: "1.2.1" openclaw: emoji: "๐ŸŽจ" homepage: https://github.com/samber/cc-skills-golang @@ -17,6 +17,8 @@ metadata: allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(git:*) Agent --- +**Orchestration mode:** Use `ultracode` when reviewing code style across a large codebase โ€” orchestrate the sub-agents described in the "Parallelizing Code Style Reviews" section, each covering an independent style concern, and merge their findings. + > **Community default.** A company skill that explicitly supersedes `samber/cc-skills-golang@golang-code-style` skill takes precedence. # Go Code Style diff --git a/skills/golang-concurrency/SKILL.md b/skills/golang-concurrency/SKILL.md index f7b3c1d..c5325eb 100644 --- a/skills/golang-concurrency/SKILL.md +++ b/skills/golang-concurrency/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.1.4" + version: "1.1.5" openclaw: emoji: "โšก" homepage: https://github.com/samber/cc-skills-golang @@ -19,6 +19,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go concurrency engineer. You assume every goroutine is a liability until proven necessary โ€” correctness and leak-freedom come before performance. +**Orchestration mode:** Use `ultracode` for auditing concurrent code across a large codebase โ€” orchestrate the five sub-agents described in the "Parallelizing Concurrency Audits" section and consolidate their findings into one report. + **Modes:** - **Write mode** โ€” implement concurrent code (goroutines, channels, sync primitives, worker pools, pipelines). Follow the sequential instructions below. diff --git a/skills/golang-dependency-injection/SKILL.md b/skills/golang-dependency-injection/SKILL.md index b523b70..040f2a1 100644 --- a/skills/golang-dependency-injection/SKILL.md +++ b/skills/golang-dependency-injection/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.1" + version: "1.2.2" openclaw: emoji: "๐Ÿ”Œ" homepage: https://github.com/samber/cc-skills-golang @@ -19,6 +19,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go software architect. You guide teams toward testable, loosely coupled designs โ€” you choose the simplest DI approach that solves the problem, and you never over-engineer. +**Orchestration mode:** Use `ultracode` when refactoring a large coupled codebase toward dependency injection โ€” orchestrate the three sub-agents described in Refactor mode (global/init discovery, concrete-dependency mapping, service-locator detection) and consolidate into one migration plan. + **Modes:** - **Design mode** (new project, new service, or adding a service to an existing DI setup): assess the existing dependency graph and lifecycle needs; recommend manual injection or a library from the decision table; then generate the wiring code. diff --git a/skills/golang-documentation/SKILL.md b/skills/golang-documentation/SKILL.md index 88d2353..f555311 100644 --- a/skills/golang-documentation/SKILL.md +++ b/skills/golang-documentation/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.1.5" + version: "1.1.6" openclaw: emoji: "๐Ÿ“" homepage: https://github.com/samber/cc-skills-golang @@ -19,6 +19,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go technical writer and API designer. You treat documentation as a first-class deliverable โ€” accurate, example-driven, and written for the reader who has never seen this codebase before. +**Orchestration mode:** Use `ultracode` for documenting or auditing documentation across a large codebase โ€” orchestrate the sub-agents described in the "Parallelizing Documentation Work" section (one per package, or one per doc layer/file) and merge their output into the final docs. + **Modes:** - **Write mode** โ€” generating or filling in missing documentation (doc comments, README, CONTRIBUTING, CHANGELOG, llms.txt). Work sequentially through the checklist in Step 2, or parallelize across packages/files using sub-agents. diff --git a/skills/golang-error-handling/SKILL.md b/skills/golang-error-handling/SKILL.md index 08cb71f..73976ab 100644 --- a/skills/golang-error-handling/SKILL.md +++ b/skills/golang-error-handling/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.0" + version: "1.2.1" openclaw: emoji: "โš " homepage: https://github.com/samber/cc-skills-golang @@ -19,6 +19,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go reliability engineer. You treat every error as an event that must either be handled or propagated with context โ€” silent failures and duplicate logs are equally unacceptable. +**Orchestration mode:** Use `ultracode` for auditing error handling across a large codebase โ€” orchestrate the five category sub-agents described in the "Parallelizing Error Handling Audits" section (creation, wrapping, single-handling rule, panic/recover, structured logging) and consolidate their findings. + **Modes:** - **Coding mode** โ€” writing new error handling code. Follow the best practices sequentially; optionally launch a background sub-agent to grep for violations in adjacent code (swallowed errors, log-and-return pairs) without blocking the main implementation. diff --git a/skills/golang-lint/SKILL.md b/skills/golang-lint/SKILL.md index d8d6af4..9ce1467 100644 --- a/skills/golang-lint/SKILL.md +++ b/skills/golang-lint/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.2" + version: "1.2.3" openclaw: emoji: "๐Ÿงน" homepage: https://github.com/samber/cc-skills-golang @@ -23,6 +23,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go code quality engineer. You treat linting as a first-class part of the development workflow โ€” not a post-hoc cleanup step. +**Orchestration mode:** Use `ultracode` when adopting linting on a legacy codebase โ€” orchestrate the five sub-agents described in the "Parallelizing Legacy Codebase Cleanup" section (auto-fix, security linters, error handling, style/formatting, code quality) so independent linter categories are fixed concurrently. + **Modes:** - **Setup mode** โ€” configuring `.golangci.yml`, choosing linters, enabling CI: follow the configuration and workflow sections sequentially. diff --git a/skills/golang-modernize/SKILL.md b/skills/golang-modernize/SKILL.md index 39fce33..d845d40 100644 --- a/skills/golang-modernize/SKILL.md +++ b/skills/golang-modernize/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.3" + version: "1.2.4" openclaw: emoji: "๐Ÿ”„" homepage: https://github.com/samber/cc-skills-golang @@ -21,6 +21,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go modernization engineer. You keep codebases current with the latest Go idioms and standard library improvements โ€” you prioritize safety and correctness fixes first, then readability, then gradual improvements. +**Orchestration mode:** Use `ultracode` for a full-codebase modernization scan โ€” orchestrate the five sub-agents described in Full-scan mode (deprecated packages, language features, standard library upgrades, testing patterns, tooling and infra) and consolidate results using the migration priority guide. + **Modes:** - **Inline mode** (developer is actively coding): suggest only modernizations relevant to the current file or feature; mention other opportunities you noticed but do not touch unrelated files. diff --git a/skills/golang-observability/SKILL.md b/skills/golang-observability/SKILL.md index d10a7b8..6a97c80 100644 --- a/skills/golang-observability/SKILL.md +++ b/skills/golang-observability/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.1" + version: "1.2.2" openclaw: emoji: "๐Ÿ“ก" homepage: https://github.com/samber/cc-skills-golang @@ -19,6 +19,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Persona:** You are a Go observability engineer. You treat every unobserved production system as a liability โ€” instrument proactively, correlate signals to diagnose, and never consider a feature done until it is observable. +**Orchestration mode:** Use `ultracode` for auditing observability coverage across a codebase โ€” orchestrate the five signal-specific sub-agents described in Audit mode (metrics, logging, tracing, profiling, RUM) and merge their coverage findings. + **Modes:** - **Coding / instrumentation** (default): Add observability to new or existing code โ€” declare metrics, add spans, set up structured logging, wire pprof toggles. Follow the sequential instrumentation guide. diff --git a/skills/golang-performance/SKILL.md b/skills/golang-performance/SKILL.md index 80d59cb..e859dd5 100644 --- a/skills/golang-performance/SKILL.md +++ b/skills/golang-performance/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.3" + version: "1.2.4" openclaw: emoji: "๐ŸŽ" homepage: https://github.com/samber/cc-skills-golang @@ -25,6 +25,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Thinking mode:** Use `ultrathink` for performance optimization. Shallow analysis misidentifies bottlenecks โ€” deep reasoning ensures the right optimization is applied to the right problem. +**Orchestration mode:** Use `ultracode` for a broad architectural performance review โ€” orchestrate the three sub-agents described in Review mode (architecture) (allocation and memory layout, I/O and concurrency, algorithmic complexity and caching). A single hot-path review stays sequential; fan-out only pays off at package/service scope. + **Modes:** - **Review mode (architecture)** โ€” broad scan of a package or service for structural anti-patterns (missing connection pools, unbounded goroutines, wrong data structures). Use up to 3 parallel sub-agents split by concern: (1) allocation and memory layout, (2) I/O and concurrency, (3) algorithmic complexity and caching. diff --git a/skills/golang-security/SKILL.md b/skills/golang-security/SKILL.md index 069938e..fc5cc66 100644 --- a/skills/golang-security/SKILL.md +++ b/skills/golang-security/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.1.9" + version: "1.1.10" openclaw: emoji: "๐Ÿ”’" homepage: https://github.com/samber/cc-skills-golang @@ -25,6 +25,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Thinking mode:** Use `ultrathink` for security audits and vulnerability analysis. Security bugs hide in subtle interactions โ€” deep reasoning catches what surface-level review misses. +**Orchestration mode:** Use `ultracode` for a full-codebase security audit โ€” orchestrate the five vulnerability-domain sub-agents described in Audit mode as a fan-out-then-synthesize workflow. Parallelism covers more attack surface per pass; the synthesis step deduplicates findings and ranks them by severity. + **Modes:** - **Review mode** โ€” reviewing a PR for security issues. Start from the changed files, then trace call sites and data flows into adjacent code โ€” a vulnerability may live outside the diff but be triggered by it. Sequential. diff --git a/skills/golang-testing/SKILL.md b/skills/golang-testing/SKILL.md index f89b7f2..b31d3be 100644 --- a/skills/golang-testing/SKILL.md +++ b/skills/golang-testing/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.2" + version: "1.2.3" openclaw: emoji: "๐Ÿงช" homepage: https://github.com/samber/cc-skills-golang @@ -25,6 +25,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Thinking mode:** Use `ultrathink` for test strategy design and failure analysis. Shallow reasoning misses edge cases and produces brittle tests that pass today but break tomorrow. +**Orchestration mode:** Use `ultracode` for auditing a large test suite โ€” orchestrate the three sub-agents described in Audit mode (unit quality and coverage gaps, integration isolation, goroutine/race issues) and merge their findings into one gap report. + **Modes:** - **Write mode** โ€” generating new tests for existing or new code. Work sequentially through the code under test; use `gotests` to scaffold table-driven tests, then enrich with edge cases and error paths. diff --git a/skills/golang-troubleshooting/SKILL.md b/skills/golang-troubleshooting/SKILL.md index 9830acb..02aae84 100644 --- a/skills/golang-troubleshooting/SKILL.md +++ b/skills/golang-troubleshooting/SKILL.md @@ -6,7 +6,7 @@ license: MIT compatibility: Designed for Claude Code or similar AI coding agents, and for projects using Golang. metadata: author: samber - version: "1.2.2" + version: "1.2.3" openclaw: emoji: "๐Ÿ”" homepage: https://github.com/samber/cc-skills-golang @@ -25,6 +25,8 @@ allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(g **Thinking mode:** Use `ultrathink` for debugging and root cause analysis. Rushed reasoning leads to symptom fixes โ€” deep thinking finds the actual root cause. +**Orchestration mode:** Use `ultracode` for a codebase-wide bug hunt โ€” orchestrate the five bug-category sub-agents described in Codebase bug hunt mode. A single-issue debug session should stay sequential; orchestration only pays off when scanning broadly for unknown bugs. + **Modes:** - **Single-issue debug** (default): Follow the sequential Golden Rules โ€” read the error, reproduce, one hypothesis at a time. Do not launch sub-agents; focused sequential investigation is faster for a single known symptom.