From 0f3fe1d8487b02baf30538f486a6775352020671 Mon Sep 17 00:00:00 2001 From: Luong NGUYEN Date: Sat, 11 Jul 2026 00:15:00 +0200 Subject: [PATCH] docs(skills): slim self-assessment skill for context efficiency Cut SKILL.md body ~230 lines by extracting the deep-assessment round questions, output templates, and topic recommendations into references/ (deep-assessment-rounds.md, output-templates.md, topic-recommendations.md). Keep the scoring-map table inline for correctness. Rewrite description, add a worked example and Acceptance Criteria. Normalize frontmatter; metadata.version 2.3.0 -> 2.4.0. --- .../references/deep-assessment-rounds.md | 68 +++++++++++ .../references/output-templates.md | 112 ++++++++++++++++++ .../references/topic-recommendations.md | 99 ++++++++++++++++ 3 files changed, 279 insertions(+) create mode 100644 .claude/skills/self-assessment/references/deep-assessment-rounds.md create mode 100644 .claude/skills/self-assessment/references/output-templates.md create mode 100644 .claude/skills/self-assessment/references/topic-recommendations.md diff --git a/.claude/skills/self-assessment/references/deep-assessment-rounds.md b/.claude/skills/self-assessment/references/deep-assessment-rounds.md new file mode 100644 index 0000000..1c67b85 --- /dev/null +++ b/.claude/skills/self-assessment/references/deep-assessment-rounds.md @@ -0,0 +1,68 @@ +# Deep Assessment — Round Questions + +The 5 rounds for Deep Assessment. Present one AskUserQuestion call per round (multi-select, max 4 options). Each round covers 2 feature areas with 2 options each. The scoring map for each round is duplicated in SKILL.md Step 2B so results can be computed without re-reading this file. + +--- + +**Round 1 — Slash Commands & Memory** (header: "Commands") + +"Which of these have you done? Select all that apply." +Options: +1. "Created a custom slash command or skill" — Written a SKILL.md file with frontmatter, or created .claude/commands/ files +2. "Used dynamic context in commands" — Used `$ARGUMENTS`, `$0`/`$1`, backtick `!command` syntax, or `@file` references in skill/command files +3. "Set up project + personal memory" — Created both a project CLAUDE.md and personal ~/.claude/CLAUDE.md (or CLAUDE.local.md) +4. "Used memory hierarchy features" — Understand the 7-level priority order, used .claude/rules/ directory, path-specific rules, or @import syntax + +**Scoring:** Options 1-2 → **Slash Commands** (0-2); Options 3-4 → **Memory** (0-2) + +--- + +**Round 2 — Skills & Hooks** (header: "Automation") + +"Which of these have you done? Select all that apply." +Options: +1. "Installed and used an auto-invoked skill" — A skill that triggers automatically based on its description, without manual /command invocation +2. "Controlled skill invocation behavior" — Used `disable-model-invocation`, `user-invocable`, or `context: fork` with agent field in SKILL.md frontmatter +3. "Set up a PreToolUse or PostToolUse hook" — Configured a hook that runs before/after tool execution (e.g., command validator, auto-formatter) +4. "Used advanced hook features" — Configured prompt-type hooks, component-scoped hooks in SKILL.md, HTTP hooks, or hooks with custom JSON output (updatedInput, systemMessage) + +**Scoring:** Options 1-2 → **Skills** (0-2); Options 3-4 → **Hooks** (0-2) + +--- + +**Round 3 — MCP & Subagents** (header: "Integration") + +"Which of these have you done? Select all that apply." +Options: +1. "Connected an MCP server and used its tools" — e.g., GitHub MCP for PRs/issues, database MCP for queries, or any external data source +2. "Used advanced MCP features" — Project-scope .mcp.json, OAuth authentication, MCP resources with @mentions, Tool Search, or `claude mcp serve` +3. "Created or configured custom subagents" — Defined agents in .claude/agents/ with custom tools, model, or permissions +4. "Used advanced subagent features" — Worktree isolation, persistent agent memory, background tasks with Ctrl+B, agent allowlists with `Task(agent_name)`, or agent teams + +**Scoring:** Options 1-2 → **MCP** (0-2); Options 3-4 → **Subagents** (0-2) + +--- + +**Round 4 — Checkpoints & Advanced Features** (header: "Power User") + +"Which of these have you done? Select all that apply." +Options: +1. "Used checkpoints for safe experimentation" — Created checkpoints, used Esc+Esc or /rewind, restored code and/or conversation, or used Summarize option +2. "Used planning mode or extended thinking" — Activated planning via /plan, Shift+Tab, or --permission-mode plan; toggled extended thinking with Alt+T/Option+T +3. "Configured permission modes" — Used acceptEdits, plan, dontAsk, or bypassPermissions mode via CLI flags, keyboard shortcuts, or settings +4. "Used remote/desktop/web features" — Used `claude remote-control`, `claude --remote`, `/teleport`, `/desktop`, or worktrees with `claude -w` + +**Scoring:** Option 1 → **Checkpoints** (0-1); Options 2-4 → **Advanced Features** (0-3, cap at 2) + +--- + +**Round 5 — Plugins & CLI** (header: "Mastery") + +"Which of these have you done? Select all that apply." +Options: +1. "Installed or created a plugin" — Used a bundled plugin from marketplace, or created a .claude-plugin/ directory with plugin.json manifest +2. "Used plugin advanced features" — Plugin hooks, plugin MCP servers, LSP configuration, plugin namespaced commands, or --plugin-dir flag for testing +3. "Used print mode in scripts or CI/CD" — Used `claude -p` with --output-format json, --max-turns, piped input, or integrated into GitHub Actions / CI pipelines +4. "Used advanced CLI features" — Session resumption (-c/-r), --agents flag, --json-schema for structured output, --fallback-model, --from-pr, or batch processing loops + +**Scoring:** Options 1-2 → **Plugins** (0-2); Options 3-4 → **CLI** (0-2) diff --git a/.claude/skills/self-assessment/references/output-templates.md b/.claude/skills/self-assessment/references/output-templates.md new file mode 100644 index 0000000..6c75c1e --- /dev/null +++ b/.claude/skills/self-assessment/references/output-templates.md @@ -0,0 +1,112 @@ +# Output Templates + +Blank markdown templates for the assessment results and learning path. SKILL.md points here to keep the main body lean; the worked example and verification rules stay in SKILL.md. + +## Quick Assessment results (Step 3A) + +```markdown +## Claude Code Skill Assessment Results + +### Your Level: [Level 1: Beginner / Level 2: Intermediate / Level 3: Advanced] + +You checked **N/8** items. + +[One-line motivational summary based on level] + +### Your Skill Profile + +| Area | Status | +|------|--------| +| Basic CLI & Conversations | [Checked/Gap] | +| CLAUDE.md & Memory | [Checked/Gap] | +| Slash Commands (built-in) | [Checked/Gap] | +| Custom Commands & Skills | [Checked/Gap] | +| MCP Servers | [Checked/Gap] | +| Hooks | [Checked/Gap] | +| Subagents | [Checked/Gap] | +| Print Mode & CI/CD | [Checked/Gap] | + +### Identified Gaps + +[For each unchecked item, provide a 1-line description of what to learn and a link to the tutorial] + +### Your Personalized Learning Path + +[Output the level-specific learning path — see Step 4] +``` + +## Deep Assessment results (Step 3B) + +```markdown +## Claude Code Skill Assessment Results + +### Overall Level: [Level 1 / Level 2 / Level 3] + +**Total Score: N/20 points** + +[One-line motivational summary] + +### Your Skill Profile + +| Feature Area | Score | Mastery | Status | +|-------------|-------|---------|--------| +| Slash Commands | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| Memory | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| Skills | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| Hooks | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| MCP | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| Subagents | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| Checkpoints | N/1 | [None/Proficient] | [Learn/Mastered] | +| Advanced Features | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| Plugins | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | +| CLI | N/2 | [None/Basic/Proficient] | [Learn/Review/Mastered] | + +**Mastery key:** 0 = None, 1 = Basic, 2 = Proficient + +### Strength Areas +[List topics with score 2/2 — these are mastered] + +### Priority Gaps (Learn Next) +[List topics with score 0 — these need attention first, ordered by dependency] + +### Review Areas +[List topics with score 1/2 — basics known but advanced features not yet used] + +### Your Personalized Learning Path + +[Output gap-specific learning path — see Step 4] +``` + +## Learning Path (Step 4) + +```markdown +### Your Personalized Learning Path + +**Estimated time**: ~N hours (adjusted for your current skills) + +#### Phase 1: [Phase Name] (~N hours) +[Only if they have gaps in these areas] + +**[Topic Name]** — [Learn from scratch / Deep dive into advanced features] +- Tutorial: [link to tutorial directory] +- Focus on: [specific sections/concepts they need] +- Key exercise: [one concrete exercise to do] +- You'll know it's done when: [specific success criterion] + +**[Topic Name]** — ... + +--- + +#### Phase 2: [Phase Name] (~N hours) +... + +--- + +### Recommended Practice Projects + +Based on your gaps, try these real-world exercises to solidify your learning: + +1. **[Project name]**: [1-line description combining 2-3 gap topics] +2. **[Project name]**: [1-line description] +3. **[Project name]**: [1-line description] +``` diff --git a/.claude/skills/self-assessment/references/topic-recommendations.md b/.claude/skills/self-assessment/references/topic-recommendations.md new file mode 100644 index 0000000..7ac19bd --- /dev/null +++ b/.claude/skills/self-assessment/references/topic-recommendations.md @@ -0,0 +1,99 @@ +# Topic-Specific Recommendations + +Use these specific recommendations when a topic is a gap. Paths are relative to this reference file (`.claude/skills/self-assessment/references/`). + +**Slash Commands (score 0)**: +- Tutorial: [01-slash-commands/](../../../../01-slash-commands/) +- Focus on: Built-in commands reference, creating your first SKILL.md, `$ARGUMENTS` syntax +- Key exercise: Create a `/optimize` command and test it +- Done when: You can create a custom skill with arguments and dynamic context + +**Slash Commands (score 1 — review)**: +- Focus on: Dynamic context with `!`backtick`` syntax, `@file` references, `disable-model-invocation` vs `user-invocable` control +- Done when: You can create a skill that injects live command output and controls its own invocation behavior + +**Memory (score 0)**: +- Tutorial: [02-memory/](../../../../02-memory/) +- Focus on: CLAUDE.md creation, `/init` and `/memory` commands, `#` prefix for quick updates +- Key exercise: Create a project CLAUDE.md with your coding standards +- Done when: Claude remembers your preferences across sessions + +**Memory (score 1 — review)**: +- Focus on: 7-level hierarchy and priority order, .claude/rules/ directory with path-specific rules, `@import` syntax (max depth 5), Auto Memory MEMORY.md (200-line limit) +- Done when: You have modular rules for different directories and understand the full hierarchy + +**Skills (score 0)**: +- Tutorial: [03-skills/](../../../../03-skills/) +- Focus on: SKILL.md format, auto-invocation via description field, progressive disclosure (3 loading levels) +- Key exercise: Install the code-review skill and verify it auto-triggers +- Done when: A skill automatically activates based on conversation context + +**Skills (score 1 — review)**: +- Focus on: `context: fork` with `agent` field for subagent execution, `disable-model-invocation` vs `user-invocable`, 2% context budget, bundled resources (scripts/, references/, assets/) +- Done when: You can create a skill that runs in a subagent with forked context + +**Hooks (score 0)**: +- Tutorial: [06-hooks/](../../../../06-hooks/) +- Focus on: Configuration structure (matcher + hooks array), PreToolUse/PostToolUse events, exit codes (0=success, 2=block), JSON input/output format +- Key exercise: Create a PreToolUse hook that validates Bash commands +- Done when: A hook blocks dangerous commands before execution + +**Hooks (score 1 — review)**: +- Focus on: All 25 hook events (including PostToolUseFailure, StopFailure, TaskCreated, CwdChanged, FileChanged, PostCompact, Elicitation, ElicitationResult), 4 hook types (command, http, prompt, agent), component-scoped hooks in SKILL.md frontmatter, HTTP hooks with allowedEnvVars, `CLAUDE_ENV_FILE` for SessionStart/CwdChanged/FileChanged +- Done when: You can create a prompt-based Stop hook and a component-scoped hook in a skill + +**MCP (score 0)**: +- Tutorial: [05-mcp/](../../../../05-mcp/) +- Focus on: `claude mcp add` command, transport types (HTTP recommended), GitHub MCP setup, environment variable expansion +- Key exercise: Add GitHub MCP server and query PRs +- Done when: You can query live data from an external service via MCP + +**MCP (score 1 — review)**: +- Focus on: Project-scope .mcp.json (requires team approval), OAuth 2.0 auth, MCP resources with `@server:resource` mentions, Tool Search (ENABLE_TOOL_SEARCH), `claude mcp serve`, output limits (10k/25k/50k) +- Done when: You have a project .mcp.json and understand Tool Search auto mode + +**Subagents (score 0)**: +- Tutorial: [04-subagents/](../../../../04-subagents/) +- Focus on: Agent file format (.claude/agents/*.md), built-in agents (general-purpose, Plan, Explore), tools/model/permissionMode config +- Key exercise: Create a code-reviewer subagent and test delegation +- Done when: Claude delegates code review to your custom agent + +**Subagents (score 1 — review)**: +- Focus on: Worktree isolation (`isolation: worktree`), persistent agent memory (`memory` field with scopes), background agents (Ctrl+B/Ctrl+F), agent allowlists with `Task(agent_name)`, agent teams (`--teammate-mode`) +- Done when: You have a subagent with persistent memory running in worktree isolation + +**Checkpoints (score 0)**: +- Tutorial: [08-checkpoints/](../../../../08-checkpoints/) +- Focus on: Esc+Esc and /rewind access, 5 rewind options (restore code+conversation, restore conversation, restore code, summarize, cancel), limitations (bash filesystem ops not tracked) +- Key exercise: Make experimental changes, then rewind to restore +- Done when: You can confidently experiment knowing you can rewind + +**Advanced Features (score 0)**: +- Tutorial: [09-advanced-features/](../../../../09-advanced-features/) +- Focus on: Planning mode (/plan or Shift+Tab), permission modes (5 types), extended thinking (Alt+T toggle) +- Key exercise: Use planning mode to design a feature, then implement it +- Done when: You can switch between planning and implementation modes fluently + +**Advanced Features (score 1 — review)**: +- Focus on: Remote control (`claude remote-control`), web sessions (`claude --remote`), desktop handoff (`/desktop`), worktrees (`claude -w`), task lists (Ctrl+T), managed settings for enterprise +- Done when: You can hand off sessions between CLI, web, and desktop + +**Plugins (score 0)**: +- Tutorial: [07-plugins/](../../../../07-plugins/) +- Focus on: Plugin structure (.claude-plugin/plugin.json), what plugins bundle (commands, agents, MCP, hooks, settings), installation from marketplace +- Key exercise: Install a plugin and explore its components +- Done when: You understand when to use a plugin vs standalone components + +**Plugins (score 1 — review)**: +- Focus on: Creating plugin.json manifest, plugin hooks (hooks/hooks.json), LSP configuration (.lsp.json), `${CLAUDE_PLUGIN_ROOT}` variable, --plugin-dir for testing, marketplace publishing +- Done when: You can create and test a plugin for your team + +**CLI (score 0)**: +- Tutorial: [10-cli/](../../../../10-cli/) +- Focus on: Interactive vs print mode, `claude -p` with piping, `--output-format json`, session management (-c/-r) +- Key exercise: Pipe a file to `claude -p` and get JSON output +- Done when: You can use Claude non-interactively in a script + +**CLI (score 1 — review)**: +- Focus on: --agents flag with JSON config, --json-schema for structured output, --fallback-model, --from-pr, --strict-mcp-config, batch processing with for loops, `claude mcp serve` +- Done when: You have a CI/CD script that uses Claude with structured JSON output