phx-brief
Interactive briefing of a plan file — explains reasoning, schema decisions,
Install / Use
npx skills add oliver-kriska/claude-elixir-phoenix --skill phx-briefInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Content & MediaSupported Platforms
Our assessment of phx-brief
phx-brief scores 84/100 on our quality scale, 857th of 1,184 Content & Media skills we index.
Its SKILL.md is 4.6 KB long, well organised into 16 sections with 4 code examples: a solid amount of guidance for an agent.
It has 560 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated 3 days ago, so phx-brief is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
phx-brief compared with similar skills
All 4 of these similar skills score higher than phx-brief; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| phx-brief (this skill)by oliver-kriska | 84 | 560 | 3d ago | SKILL.md |
| siyuanby siyuan-note | 100 | 46.6k | today | MCP Server |
| algorithmic-artby anthropics | 100 | 177.9k | 13d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 13d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 130.2k | 14d ago | SKILL.md |
Frequently asked questions
- How do I install phx-brief?
- Run
npx skills add oliver-kriska/claude-elixir-phoenix --skill phx-brief. The install tabs above show the steps for each supported agent. - Which AI agents does phx-brief work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is phx-brief safe to use?
- It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is phx-brief still maintained?
- The repository was last updated 3 days ago, so phx-brief is actively maintained.
Skill content
View source on GitHubname: phx-brief description: Interactive briefing of a plan file — explains reasoning, schema decisions, component choices. Use when developers need to understand a plan before approving.
Plan Briefing
Interactive walkthrough of a plan's reasoning, decisions, and solution shape. Designed for developers who need to understand a plan in 1-2 minutes instead of reading the full document.
Why This Exists
Plans answer "what to do" but bury "why." This skill bridges that gap with an interactive walkthrough.
Usage
phx-brief # Latest plan
phx-brief .claude/plans/user-auth/plan.md # Specific plan
Arguments
$ARGUMENTS= Path to plan file (optional, auto-detects latest)
Mode Detection
Read the plan file and determine mode from phase statuses:
- All phases
[PENDING]= Pre-work briefing (what WILL happen) - Any phase
[COMPLETED]or[IN_PROGRESS]= Post-work briefing (what WAS done and why)
Execution Flow
Step 1: Locate and Load Plan
-
If
$ARGUMENTShas a path, use it -
Otherwise, find latest plan:
Use Glob to find
.claude/plans/*/plan.mdand pick the most recent. -
If no plan found, tell user and suggest
phx-plan -
Read the plan file
Step 2: Load Supporting Artifacts
Read what's available (don't fail if missing):
.claude/plans/{slug}/summaries/consolidated.md(research summary).claude/plans/{slug}/scratchpad.md(decisions, dead-ends).claude/plans/{slug}/progress.md(work log, post-work only)
Step 3: Present Briefing Sections
Present ONE section at a time, wrapped in the visual briefing block
(see references/briefing-guide.md Visual Formatting).
The section MUST be emitted as visible response text BEFORE the
AskUserQuestion call. Content composed only in thinking/reasoning
is invisible to the user, and the question field is too short to
carry it. If the user would see only a "Continue?" dialog, the section
was never shown. Write the ★ Briefing block as normal output first,
then ask:
- If sections remain: question "Continue the briefing?" with options "Next: {title}", "Ask me a question about this", "Stop here"
- If final section: no question needed, show closing message
Section Flow (Pre-Work Mode)
| # | Title | Source | |---|-------|--------| | 1 | What We're Building | Summary + Scope | | 2 | Key Decisions | Technical Decisions + scratchpad rationale | | 3 | Solution Shape | Phases overview + Data Model | | 4 | Risks & Confidence | Risks table + unknowns/spikes |
Section Flow (Post-Work Mode)
| # | Title | Source | |---|-------|--------| | 1 | What Was Built | Summary + completion status | | 2 | Key Decisions & Why | Technical Decisions + scratchpad | | 3 | How It Was Built | Phases with implementation notes | | 4 | Lessons & Patterns | Risks encountered + patterns used |
See references/briefing-guide.md for section content templates.
Iron Laws
- ONE section at a time — never dump all content
- User controls pace — always offer to stop
- Explain WHY, not just WHAT — rationale over listing
- Ground in artifacts — focus on insights specific to this plan's research, decisions, and scratchpad entries, not general programming concepts
- Keep each section under 20 lines — this is a briefing, not a lecture
- NEVER skip sections or auto-start work — briefing is read-only; do not execute plan tasks or launch
phx-workwithout explicit user request - SECTION TEXT BEFORE THE QUESTION — every ★ Briefing block is
visible response text emitted before its
AskUserQuestion; never deliver a section only inside thinking or the question field
Closing Message
After final section (or when user stops):
That's the briefing! For full details, see:
{plan_path}
Ready to proceed? Try `phx-work {plan_path}` to start execution.
Post-work variant:
That's what was built! For full details, see:
{plan_path}
Consider `phx-compound` to capture key learnings for future reference.
Integration
phx-plan --> phx-brief (optional) --> phx-work --> phx-brief (optional)
create understand before execute understand after
Complex Plan Enhancement
For plans with 5+ phases or 4+ key decisions, consider suggesting
visual rendering after Section 3. See
references/visual-explainer.md for thresholds and commands.
Notes
- Runs in main conversation context (not a subagent)
- Model: no special requirement — uses default session model
- No artifacts written — briefing is ephemeral, plan IS the artifact
- Reference file readable since skill runs in user's session
Related Skills
siyuan
46.6kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
130.2kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
