Merge branch 'feat/pr-9-skill-improvements'
This commit is contained in:
Florian BRUNIAUX
commit
52f0e31305
19 changed files with 104 additions and 245 deletions
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: audit-agents-skills
|
||||
description: Comprehensive quality audit for Claude Code agents, skills, and commands with comparative analysis
|
||||
description: "Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates."
|
||||
allowed-tools: Read, Grep, Glob, Bash, Write
|
||||
context: inherit
|
||||
agent: specialist
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: ccboard
|
||||
description: Comprehensive TUI/Web dashboard for Claude Code monitoring
|
||||
description: "Launch and navigate the ccboard TUI/Web dashboard for Claude Code. Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects."
|
||||
version: 0.1.0
|
||||
category: monitoring
|
||||
keywords: [dashboard, tui, mcp, sessions, costs, analytics]
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: cyber-defense-team
|
||||
description: Orchestrate a 4-agent cyber defense pipeline to analyze log files for threats. Spawns log-ingestor → anomaly-detector → risk-classifier → threat-reporter as parallel-then-sequential agents. Produces a Markdown incident report.
|
||||
description: "Orchestrate a 4-agent cyber defense pipeline to analyze log files for threats. Use when investigating security logs, detecting anomalies in access patterns, classifying breach severity, or generating incident reports from nginx/auth/syslog files."
|
||||
version: 1.0.0
|
||||
usage: /cyber-defense-team [log-file-path]
|
||||
args:
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: design-patterns
|
||||
description: Analyze codebase for GoF design patterns - detection, suggestions, evaluation with stack-aware adaptations
|
||||
description: "Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue."
|
||||
allowed-tools: Read, Grep, Glob, mcp__grepai__grepai_search
|
||||
context: fork
|
||||
agent: specialist
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: guide-recap
|
||||
description: Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.
|
||||
description: "Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate release notes, announcements, social media posts, or recap summaries from guide updates."
|
||||
argument-hint: "<latest|vX.Y.Z|week [YYYY-MM-DD]> [--interactive] [--format=linkedin|twitter|newsletter|slack] [--lang=fr|en] [--save]"
|
||||
tags: [changelog, social-media, content, linkedin, twitter]
|
||||
---
|
||||
|
|
|
|||
|
|
@ -1,9 +1,6 @@
|
|||
---
|
||||
name: issue-triage
|
||||
description: >
|
||||
3-phase issue backlog management: audit open issues, deep analyze selected ones, draft and execute
|
||||
triage actions with mandatory validation. Args: "all" to analyze all, issue numbers to focus
|
||||
(e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
|
||||
description: "3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only."
|
||||
tags: [github, issue, triage, maintainer, multi-agent]
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: landing-page-generator
|
||||
description: Generate complete landing pages from repositories. Analyzes README, features, and structure to create static sites following established patterns. Use for new project landings, open-source showcases, documentation portals.
|
||||
description: "Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages across multiple repos."
|
||||
tags: [landing-page, static-site, github-pages, marketing]
|
||||
---
|
||||
|
||||
|
|
@ -155,6 +155,14 @@ Generate these sections in order:
|
|||
└── static.yml # GitHub Pages deployment
|
||||
```
|
||||
|
||||
### Step 5: Validation Checkpoint
|
||||
|
||||
Before finalizing, verify:
|
||||
- All sections render correctly in a browser
|
||||
- Links point to valid targets (GitHub repo, docs, install commands)
|
||||
- Responsive layout works at mobile (375px), tablet (768px), and desktop (1280px) widths
|
||||
- Accessibility: skip links present, ARIA labels on interactive elements, color contrast passes WCAG AA
|
||||
|
||||
## Tech Stack
|
||||
|
||||
- **No build step**: Pure HTML + CSS + JS
|
||||
|
|
@ -225,13 +233,6 @@ Creates `~/projects/my-project-landing/` with:
|
|||
- Review generated FAQ - may need customization
|
||||
- Test responsive design after generation
|
||||
|
||||
## Related Use Cases
|
||||
|
||||
- Open-source project showcases
|
||||
- Documentation portals
|
||||
- Product landing pages
|
||||
- Tool/utility marketing sites
|
||||
|
||||
## References
|
||||
|
||||
See `references/landing-pattern.md` for detailed pattern documentation.
|
||||
|
|
|
|||
|
|
@ -1,9 +1,6 @@
|
|||
---
|
||||
name: pr-triage
|
||||
description: >
|
||||
4-phase PR backlog management: audit open PRs, deep review selected ones, post validated
|
||||
review comments, and optionally create local worktrees for hands-on review. Args: "all"
|
||||
to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only.
|
||||
description: "4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only."
|
||||
tags: [github, pr, triage, review, maintainer, multi-agent, worktree]
|
||||
---
|
||||
|
||||
|
|
@ -63,37 +60,27 @@ If either fails, stop and explain what is missing.
|
|||
### Data Gathering (parallel commands)
|
||||
|
||||
```bash
|
||||
# Repo identity
|
||||
gh repo view --json nameWithOwner -q .nameWithOwner
|
||||
|
||||
# Open PRs with full metadata (body for cross-reference issues)
|
||||
gh pr list --state open --limit 50 \
|
||||
--json number,title,author,createdAt,updatedAt,additions,deletions,changedFiles,isDraft,mergeable,reviewDecision,statusCheckRollup,body
|
||||
|
||||
# Collaborators (to distinguish internal from external PRs)
|
||||
gh api "repos/{owner}/{repo}/collaborators" --jq '.[].login'
|
||||
```
|
||||
|
||||
**Collaborators fallback**: if `gh api .../collaborators` returns 403/404:
|
||||
```bash
|
||||
# Extract authors from last 10 merged PRs
|
||||
gh pr list --state merged --limit 10 --json author --jq '.[].author.login' | sort -u
|
||||
```
|
||||
If still ambiguous, ask via `AskUserQuestion`.
|
||||
|
||||
For each PR, fetch existing reviews AND changed files:
|
||||
For each PR, fetch reviews and changed files:
|
||||
|
||||
```bash
|
||||
gh api "repos/{owner}/{repo}/pulls/{num}/reviews" \
|
||||
--jq '[.[] | .user.login + ":" + .state] | join(", ")'
|
||||
|
||||
# Changed files (required for overlap detection)
|
||||
gh pr view {num} --json files --jq '[.files[].path] | join(",")'
|
||||
```
|
||||
|
||||
**Rate-limiting note**: fetching files requires N API calls (1 per PR). For repos with 20+ PRs, prioritize candidates for overlap detection (same functional domain, same author).
|
||||
|
||||
**Note**: `author` is an object `{login: "..."}` — always extract `.author.login`.
|
||||
**Notes**: Fetching files requires 1 API call per PR — for 20+ PRs, prioritize overlap candidates. The `author` field is an object; always extract `.author.login`.
|
||||
|
||||
### Analysis
|
||||
|
||||
|
|
@ -181,7 +168,6 @@ Note: Phase 3 (posting comments) is NOT offered here — it requires the drafts
|
|||
After displaying the triage table, copy to clipboard using platform-appropriate command:
|
||||
|
||||
```bash
|
||||
# Detect platform and copy
|
||||
UNAME=$(uname -s)
|
||||
if [ "$UNAME" = "Darwin" ]; then
|
||||
pbcopy <<'EOF'
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: release-notes-generator
|
||||
description: Generate release notes in 3 formats (CHANGELOG.md, PR body, Slack announcement) from git commits. Automatically categorizes changes and converts technical language to user-friendly messaging. Use when preparing a production release.
|
||||
description: "Generate release notes in 3 formats (CHANGELOG.md, PR body, Slack announcement) from git commits. Automatically categorizes changes and converts technical language to user-friendly messaging. Use for releases, changelogs, version notes, what's new summaries, or ship announcements."
|
||||
tags: [release-notes, changelog, slack, git, automation]
|
||||
---
|
||||
|
||||
|
|
@ -8,25 +8,14 @@ tags: [release-notes, changelog, slack, git, automation]
|
|||
|
||||
Generate comprehensive release notes in 3 formats from git commits.
|
||||
|
||||
## When to Use This Skill
|
||||
## Workflow
|
||||
|
||||
- Preparing a production release (develop -> main)
|
||||
- Creating release PR with proper documentation
|
||||
- Generating Slack announcement for stakeholders
|
||||
- Updating CHANGELOG.md with new version
|
||||
- Analyzing commits since last release
|
||||
|
||||
## What This Skill Does
|
||||
|
||||
1. **Analyzes Git History**: Scans commits since last release tag or specified version
|
||||
2. **Fetches PR Details**: Gets PR titles, descriptions, and labels via `gh api`
|
||||
3. **Categorizes Changes**: Groups into features, bug fixes, improvements, security, breaking changes
|
||||
4. **Generates 3 Outputs**:
|
||||
- **CHANGELOG.md section** (technical, complete)
|
||||
- **PR Release body** (semi-technical, checklist)
|
||||
- **Slack message** (product-focused, user-friendly)
|
||||
5. **Transforms Language**: Converts technical jargon to accessible messaging
|
||||
6. **Migration Alert**: Displays prominent warning if database migrations are required
|
||||
1. **Analyze git history** since last release tag or specified version
|
||||
2. **Fetch PR details** (titles, descriptions, labels) via `gh api`
|
||||
3. **Categorize changes** into features, bug fixes, improvements, security, breaking changes
|
||||
4. **Generate 3 outputs**: CHANGELOG.md section (technical), PR release body (semi-technical), Slack message (user-friendly)
|
||||
5. **Transform language** from technical jargon to accessible messaging
|
||||
6. **Alert on migrations** if database migrations are detected
|
||||
|
||||
## How to Use
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: rtk-optimizer
|
||||
description: Optimize command outputs with RTK (Rust Token Killer) for 70% token reduction
|
||||
description: "Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens."
|
||||
version: 1.0.0
|
||||
tags: [optimization, tokens, efficiency, git]
|
||||
---
|
||||
|
|
|
|||
|
|
@ -1,23 +1,21 @@
|
|||
---
|
||||
name: skill-creator
|
||||
description: Create new Claude Code skills with proper structure, YAML frontmatter, and bundled resources. Generates skill templates following best practices for modular, self-contained capability packages.
|
||||
description: "Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution."
|
||||
tags: [meta, skill, generator, claude-code]
|
||||
---
|
||||
|
||||
# Skill Creator
|
||||
|
||||
This skill helps you create new Claude Code skills with proper structure and best practices.
|
||||
Generate new Claude Code skills with correct directory structure, YAML frontmatter, and optional bundled resources.
|
||||
|
||||
## When to Use This Skill
|
||||
## When to Use
|
||||
|
||||
- Creating a new custom skill for your project
|
||||
- Standardizing skill structure across your team
|
||||
- Creating a new custom skill for a project
|
||||
- Standardizing skill structure across a team
|
||||
- Generating skill templates with scripts, references, and assets
|
||||
- Packaging skills for distribution
|
||||
|
||||
## Skill Structure
|
||||
|
||||
A Claude skill consists of:
|
||||
## Skill Directory Structure
|
||||
|
||||
```
|
||||
skill-name/
|
||||
|
|
@ -27,99 +25,71 @@ skill-name/
|
|||
└── assets/ # Optional: Templates, images, boilerplate (not loaded into context)
|
||||
```
|
||||
|
||||
## SKILL.md Format
|
||||
## Workflow
|
||||
|
||||
Every skill requires a `SKILL.md` file with:
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: skill-name
|
||||
description: One-line description of what the skill does and when to use it.
|
||||
---
|
||||
|
||||
# Skill Name
|
||||
|
||||
Brief introduction explaining the skill's purpose.
|
||||
|
||||
## When to Use This Skill
|
||||
|
||||
- Trigger condition 1
|
||||
- Trigger condition 2
|
||||
- Trigger condition 3
|
||||
|
||||
## What This Skill Does
|
||||
|
||||
1. **Step 1**: Description
|
||||
2. **Step 2**: Description
|
||||
3. **Step 3**: Description
|
||||
|
||||
## How to Use
|
||||
|
||||
### Basic Usage
|
||||
[Examples of how to invoke the skill]
|
||||
|
||||
### With Options
|
||||
[Advanced usage patterns]
|
||||
|
||||
## Example
|
||||
|
||||
**User**: "Example prompt"
|
||||
|
||||
**Output**:
|
||||
[Example output]
|
||||
|
||||
## Tips
|
||||
|
||||
- Best practice 1
|
||||
- Best practice 2
|
||||
|
||||
## Related Use Cases
|
||||
|
||||
- Related task 1
|
||||
- Related task 2
|
||||
```
|
||||
|
||||
## How to Use
|
||||
|
||||
### Create a New Skill
|
||||
### 1. Create the Skill
|
||||
|
||||
```
|
||||
Create a new skill called "my-skill-name" in ~/.claude/skills/
|
||||
```
|
||||
|
||||
### Create with Specific Purpose
|
||||
Or with a specific purpose:
|
||||
|
||||
```
|
||||
Create a skill for generating release notes from git commits,
|
||||
with templates for CHANGELOG.md and Slack announcements
|
||||
```
|
||||
|
||||
### Initialize Skill Structure
|
||||
|
||||
Run the initialization script:
|
||||
Or via the initialization script:
|
||||
|
||||
```bash
|
||||
python3 ~/.claude/skills/skill-creator/scripts/init_skill.py <skill-name> --path <output-directory>
|
||||
```
|
||||
|
||||
### Package Skill for Distribution
|
||||
### 2. Generated SKILL.md Template
|
||||
|
||||
The created SKILL.md follows this structure:
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: skill-name
|
||||
description: "What the skill does. Use when [trigger conditions]."
|
||||
---
|
||||
|
||||
# Skill Name
|
||||
|
||||
## When to Use
|
||||
- Trigger condition 1
|
||||
- Trigger condition 2
|
||||
|
||||
## What This Skill Does
|
||||
1. **Step 1**: Description
|
||||
2. **Step 2**: Description
|
||||
|
||||
## How to Use
|
||||
[Usage examples]
|
||||
|
||||
## Example
|
||||
**User**: "Example prompt"
|
||||
**Output**: [Example output]
|
||||
```
|
||||
|
||||
### 3. Validate the Skill
|
||||
|
||||
After creation, verify:
|
||||
|
||||
1. **Frontmatter**: `name` is kebab-case, 1-64 chars; `description` is a quoted string with "Use when" clause
|
||||
2. **Content**: Has "When to Use" section with trigger conditions and at least one usage example
|
||||
3. **Structure**: SKILL.md is under 5000 words; references and assets are in correct subdirectories
|
||||
4. **Test**: Invoke the skill with a real use case and confirm expected output
|
||||
|
||||
### 4. Package for Distribution (Optional)
|
||||
|
||||
```bash
|
||||
python3 ~/.claude/skills/skill-creator/scripts/package_skill.py <path/to/skill-folder> [output-directory]
|
||||
```
|
||||
|
||||
## Design Principles
|
||||
|
||||
### Progressive Disclosure
|
||||
|
||||
Context loads hierarchically to optimize token usage:
|
||||
1. **Metadata** (~100 words): Always present via skill description
|
||||
2. **SKILL.md** (<5k words): Loaded when skill is triggered
|
||||
3. **Bundled resources**: Loaded as needed during execution
|
||||
|
||||
### Organizational Patterns
|
||||
|
||||
Choose the pattern that fits your skill:
|
||||
## Organizational Patterns
|
||||
|
||||
| Pattern | Best For | Structure |
|
||||
|---------|----------|-----------|
|
||||
|
|
@ -128,59 +98,22 @@ Choose the pattern that fits your skill:
|
|||
| **Reference/Guidelines** | Standards, specs | Rules and examples |
|
||||
| **Capabilities-Based** | Interrelated features | Feature descriptions |
|
||||
|
||||
### Naming Conventions
|
||||
|
||||
- Use `kebab-case` for skill names: `release-notes-generator`
|
||||
- Use descriptive names that indicate purpose
|
||||
- Keep names concise but meaningful
|
||||
|
||||
## Bundled Resources
|
||||
|
||||
### scripts/
|
||||
|
||||
Executable code for deterministic, repeatable tasks:
|
||||
- `init_skill.py` - Initialize new skill structure
|
||||
- `package_skill.py` - Package skill for distribution
|
||||
|
||||
### references/
|
||||
|
||||
Documentation loaded contextually:
|
||||
- API documentation
|
||||
- Style guides
|
||||
- Domain knowledge
|
||||
|
||||
### assets/
|
||||
|
||||
Templates and resources (not auto-loaded):
|
||||
- Output templates
|
||||
- Boilerplate code
|
||||
- Images and fonts
|
||||
|
||||
## Example: Creating a Release Notes Skill
|
||||
|
||||
**User**: "Create a skill for generating release notes with 3 output formats: CHANGELOG.md, PR body, and Slack message"
|
||||
**User**: "Create a skill for generating release notes with 3 output formats"
|
||||
|
||||
**Steps**:
|
||||
1. Initialize structure: `init_skill.py release-notes-generator --path ~/.claude/skills/`
|
||||
2. Add templates to `assets/`:
|
||||
- `changelog-template.md`
|
||||
- `pr-release-template.md`
|
||||
- `slack-template.md`
|
||||
3. Add transformation rules to `references/`:
|
||||
- `tech-to-product-mappings.md`
|
||||
1. Initialize: `init_skill.py release-notes-generator --path ~/.claude/skills/`
|
||||
2. Add templates to `assets/`: `changelog-template.md`, `pr-release-template.md`, `slack-template.md`
|
||||
3. Add rules to `references/`: `tech-to-product-mappings.md`
|
||||
4. Complete `SKILL.md` with usage instructions
|
||||
5. Package: `package_skill.py ~/.claude/skills/release-notes-generator`
|
||||
5. Validate: check frontmatter, test with a real commit range
|
||||
6. Package: `package_skill.py ~/.claude/skills/release-notes-generator`
|
||||
|
||||
## Tips
|
||||
|
||||
- Keep SKILL.md under 5000 words for efficient context usage
|
||||
- Use references/ for domain knowledge that doesn't change often
|
||||
- Put templates in assets/ so they're not auto-loaded
|
||||
- Test your skill with real use cases before packaging
|
||||
- Include concrete examples in your SKILL.md
|
||||
|
||||
## Related Use Cases
|
||||
|
||||
- Creating project-specific automation skills
|
||||
- Building team-shared development workflows
|
||||
- Packaging reusable Claude capabilities
|
||||
- Use `references/` for domain knowledge that doesn't change often
|
||||
- Put templates in `assets/` so they're not auto-loaded into context
|
||||
- Always include a "Use when" clause in the description frontmatter
|
||||
- Test with real use cases before packaging
|
||||
|
|
|
|||
|
|
@ -1,12 +1,8 @@
|
|||
---
|
||||
name: talk-pipeline
|
||||
description: Orchestrator for the complete talk preparation pipeline (REX or Concept mode). Runs all 6 stages in sequence with human-in-the-loop checkpoints.
|
||||
description: "Orchestrates the complete talk preparation pipeline from raw material to revision sheets, running 6 stages in sequence with human-in-the-loop checkpoints for REX or Concept mode talks. Use when starting a new talk pipeline, resuming a pipeline from a specific stage, or running the full end-to-end preparation workflow."
|
||||
tags: [talk, pipeline, presentation, orchestrator]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
- AskUserQuestion
|
||||
- Task
|
||||
allowed-tools: "Write, Read, AskUserQuestion, Task"
|
||||
---
|
||||
|
||||
# Talk Pipeline Orchestrator
|
||||
|
|
|
|||
|
|
@ -1,11 +1,8 @@
|
|||
---
|
||||
name: talk-stage1-extract
|
||||
description: Stage 1 — Extract and structure source material into a talk summary. Auto-detects REX vs Concept type.
|
||||
description: "Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or auditing existing material before committing to a talk."
|
||||
tags: [talk, pipeline, presentation, stage-1]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
- AskUserQuestion
|
||||
allowed-tools: "Write, Read, AskUserQuestion"
|
||||
---
|
||||
|
||||
# Talk Stage 1: Extract
|
||||
|
|
|
|||
|
|
@ -1,11 +1,8 @@
|
|||
---
|
||||
name: talk-stage2-research
|
||||
description: Stage 2 (REX mode only) — Git archaeology, changelog analysis, verified factual timeline. Skip automatically in Concept mode.
|
||||
description: "Performs git archaeology, changelog analysis, and builds a verified factual timeline by cross-referencing git history with source material. REX mode only — skipped automatically in Concept mode. Use when building a REX talk and you need verified commit metrics, release timelines, and contributor data from a git repository."
|
||||
tags: [talk, pipeline, presentation, stage-2, git]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
- Bash
|
||||
allowed-tools: "Write, Read, Bash"
|
||||
---
|
||||
|
||||
# Talk Stage 2: Research (REX mode only)
|
||||
|
|
|
|||
|
|
@ -1,10 +1,8 @@
|
|||
---
|
||||
name: talk-stage3-concepts
|
||||
description: Stage 3 — Build a numbered, scored concept catalogue. Every concept gets HIGH / MEDIUM / LOW talk-potential rating.
|
||||
description: "Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest presentation potential."
|
||||
tags: [talk, pipeline, presentation, stage-3]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
allowed-tools: "Write, Read"
|
||||
---
|
||||
|
||||
# Talk Stage 3: Concepts
|
||||
|
|
|
|||
|
|
@ -1,11 +1,8 @@
|
|||
---
|
||||
name: talk-stage4-position
|
||||
description: Stage 4 — Strategic angles, titles, descriptions, peer feedback draft. Includes mandatory CHECKPOINT before script can start.
|
||||
description: "Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory CHECKPOINT for user confirmation before scripting. Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles."
|
||||
tags: [talk, pipeline, presentation, stage-4, checkpoint]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
- AskUserQuestion
|
||||
allowed-tools: "Write, Read, AskUserQuestion"
|
||||
---
|
||||
|
||||
# Talk Stage 4: Position + CHECKPOINT
|
||||
|
|
|
|||
|
|
@ -1,10 +1,8 @@
|
|||
---
|
||||
name: talk-stage5-script
|
||||
description: Stage 5 — 5-act pitch with speaker notes, slide spec, and Kimi prompt for AI slide generation. Requires validated angle + title from Stage 4.
|
||||
description: "Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt."
|
||||
tags: [talk, pipeline, presentation, stage-5, kimi]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
allowed-tools: "Write, Read"
|
||||
---
|
||||
|
||||
# Talk Stage 5: Script
|
||||
|
|
|
|||
|
|
@ -1,10 +1,8 @@
|
|||
---
|
||||
name: talk-stage6-revision
|
||||
description: Stage 6 — Revision sheets for during and after the talk. Master concept table, Q&A cheat-sheet, glossary, external resources.
|
||||
description: "Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery."
|
||||
tags: [talk, pipeline, presentation, stage-6]
|
||||
allowed-tools:
|
||||
- Write
|
||||
- Read
|
||||
allowed-tools: "Write, Read"
|
||||
---
|
||||
|
||||
# Talk Stage 6: Revision
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
name: voice-refine
|
||||
description: Transform verbose voice input into optimized Claude prompts
|
||||
description: "Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts."
|
||||
allowed-tools: Read
|
||||
context: inherit
|
||||
agent: specialist
|
||||
|
|
@ -85,39 +85,11 @@ dans le projet donc faut que ça matche avec ça...
|
|||
| Information retention | >95% |
|
||||
| Structure clarity | High |
|
||||
|
||||
## Integration with Voice Tools
|
||||
## Filtering Rules
|
||||
|
||||
### Wispr Flow
|
||||
1. Dictate with `Cmd+Shift+Space`
|
||||
2. Paste into Claude Code
|
||||
3. Run `/voice-refine`
|
||||
**Remove**: filler words ("euh", "um", "like", "basically"), repetitions, tangents, hedging ("maybe", "probably" unless relevant), politeness padding ("please", "could you").
|
||||
|
||||
### Superwhisper
|
||||
1. Record with hotkey
|
||||
2. Text appears in active window
|
||||
3. Run `/voice-refine` to structure
|
||||
|
||||
### macOS Dictation
|
||||
1. `Fn Fn` to start
|
||||
2. Speak naturally
|
||||
3. Run `/voice-refine` to clean up
|
||||
|
||||
## What Gets Removed
|
||||
|
||||
- Filler words: "euh", "um", "like", "you know", "basically"
|
||||
- Repetitions: same concept stated multiple ways
|
||||
- Tangents: off-topic thoughts
|
||||
- Hedging: "maybe", "I think", "probably" (unless relevant)
|
||||
- Politeness padding: "please", "could you", "I'd like"
|
||||
|
||||
## What Gets Preserved
|
||||
|
||||
- Technical requirements
|
||||
- Constraints and limitations
|
||||
- Context about existing code
|
||||
- Expected output format
|
||||
- Edge cases mentioned
|
||||
- Business logic rules
|
||||
**Preserve**: technical requirements, constraints, existing code context, expected output format, edge cases, business logic rules.
|
||||
|
||||
## See Also
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue