mcpbeat Sign in

Phx Work Skill for Claude

Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.

7k tokens
context cost
the whole folder, loaded on every use
6
files
instructions only
0
copies elsewhere
how many repositories repackaged it
514
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/oliver-kriska/claude-elixir-phoenix --skill phx-work

What comes with it

18 498 bytes besides the instruction
references/error-recovery.md
references/execution-guide.md
references/file-formats.md
references/harness-patterns.md
references/resume-strategies.md

The instruction itself

12 sections, as written by the author

Work

Execute tasks from a plan file with checkpoint tracking and verification.

Usage

phx-work .claude/plans/user-auth/plan.md
phx-work .claude/plans/user-auth/plan.md --from P2-T3
phx-work --skip-blockers
phx-work  # Resumes most recent plan

Arguments

  • <plan-file> -- Path to plan file (optional, auto-detects recent)
  • --from <task-id> -- Resume from specific task (e.g., P2-T3)
  • --skip-blockers -- Continue past blocked tasks
  • --continue -- Resume IN_PROGRESS plan from checkboxes

Iron Laws (NON-NEGOTIABLE)

  • NEVER auto-proceed to phx-review or any next workflow

phase -- always ask the user what to do next

  • AUTO-CONTINUE between plan phases -- when Phase N completes,

immediately start Phase N+1. Do NOT stop or ask for permission

between phases. Only stop at BLOCKERS or when ALL phases are done.

  • Plan checkboxes ARE the state -- [x] = done; [ ] = pending

unless the row is visibly tagged [BLOCKED]. No separate JSON state files.

Resume by reading the plan.

  • Verify after EVERY task -- never skip verification
  • Max 3 retries then BLOCKER -- don't keep retrying forever
  • Stage specific files -- never use git add -A or git add .
  • Read scratchpad BEFORE implementing -- scratchpad has dead-ends

and decisions that prevent rework. Step 2 is not optional.

  • Clarify ambiguous tasks -- ask the user rather than guessing

when a plan task's intent is unclear

Step 1: Research Decision

Ask the user for plans with >3 tasks:

> This plan has {count} remaining tasks across {count} phases.

>

> 1. Start working -- Begin immediately (familiar patterns)

> 2. Quick research -- Read source files first (~10 min)

> 3. Extensive research -- Web search + docs (~30 min)

Skip for plans with 3 or fewer simple tasks -- just start.

> Split warning: Plans with >10 tasks risk 2-3 context

> compactions. Suggest splitting via phx-plan if not already.

Step 2: Check Context (MANDATORY)

Read scratchpad and compound docs before writing any code — skipping

this causes rework. Read .claude/plans/{slug}/scratchpad.md (short,

critical context) for dead-ends and decisions, then Grep .claude/solutions/

for solved patterns. Apply findings: skip dead-ends, follow decisions,

reuse patterns. Ask the user when a task's intent is ambiguous — never

guess, corrections are expensive.

Step 3: Load, Create Task List, and Resume

Read plan file, count [x] (completed) vs [ ] (remaining).

Select the first unchecked task not tagged [BLOCKED]. Stop if an unresolved

[BLOCKED] task precedes it unless --skip-blockers is explicit.

--skip-blockers skips only tagged blocked rows; --from <blocked-id>

explicitly retries that row and clears [BLOCKED] when starting.

Use the plan file as the portable task list. For every unchecked item,

preserve its - [ ] [Pn-Tm] row and ordering. At the start of a task, set its

phase to [IN_PROGRESS] and append a Started: entry to

.claude/plans/{slug}/progress.md. Mark the plan checkbox [x] only after

verification passes, then append the completion evidence to progress.md.

Dependencies remain explicit in phase order: do not start a later phase while

an earlier phase has unchecked non-blocked tasks. This checklist is the progress

UI, durable state, and resume mechanism; no runtime task API is required.

With --from P2-T3: Skip to that specific task.

Stale-plan check: if the plan predates this session (file mtime), spot-check

2-3 files it references before executing — assumptions may have drifted.

See references/resume-strategies.md for all resume modes.

Step 4: Execute Tasks

Execute each unchecked task (- [ ] [Pn-Tm][concern] Description):

  • Start task: mark its phase [IN_PROGRESS] and log the start in .claude/plans/{slug}/progress.md
  • Apply concern guidance from the annotation and its required verification (see references/execution-guide.md); it never selects a named worker
  • Implement the task
  • Verify: mix format + mix compile --warnings-as-errors

(at phase end, also run mix test <affected> — see tiers below)

  • Complete task: Mark checkbox [x] on pass, **append

implementation note** inline, and log verification evidence in progress.md. Example:

- [x] [P1-T3] Add user schema — citext for email, composite index on [user_id, status]

This survives context compaction; the plan is re-read on resume.

  • On failure: retry up to 3 times, then keep the row unchecked and

append [BLOCKED], optionally mark its phase [BLOCKED], record the

blocker in progress.md, write a DEAD-END to scratchpad, and stop by

default. Continue only when --skip-blockers was explicitly supplied

Parallel groups: Tasks under ### Parallel: may use native generic workers only when independent; otherwise execute them sequentially in the current session. See references/execution-guide.md

for the optional-worker pattern, sequential fallback, and checkpoint flow.

Verification tiers (scoped to minimize redundant runs):

  • Per-task: mix compile --warnings-as-errors only

and mix format --check-formatted <changed_files>

  • Per-phase: mix compile --warnings-as-errors + mix test <affected_files> + mix credo --strict

(scope tests: mix test test/path/to_affected_test.exs — NOT full suite)

  • Per-feature: when Tidewave tools are independently configured and exposed, use a behavioral runtime smoke test; otherwise run a focused repository test and a local/manual smoke check (see execution-guide.md)
  • Final gate: mix test (full suite — run ONCE at the end, not per-phase)

Token efficiency: Do NOT narrate each verification step. Execute

tool calls directly without "Let me now run..." preamble. Only narrate

when explaining a non-obvious decision or reporting a failure. When

several checkboxes complete together (parallel groups, resume catch-up),

batch them into ONE edit pass — never one Edit call per checkbox.

No hook is assumed. Run mix format explicitly during verification and

mix format --check-formatted <changed_files> before completing each task.

Step 5: Completion

Summarize results, then ask the user a normal conversational question:

> Implementation complete! {done}/{total} tasks finished.

> {count} files modified across {count} phases.

Options: 1. Run review (phx-review) (Recommended),

  • Get a briefing (phx-brief — understand what was built),
  • Create a git commit with the platform's native git workflow, 4. Continue manually.

If any task fixed a non-obvious bug, also mention phx-compound

to capture the solution.

With blockers: list them, offer Replan (phx-plan),

Review first (phx-review), or Handle myself.

If blockers remain, auto-write HANDOFF to scratchpad:

### [HH:MM] HANDOFF: {plan name}
Status: {done}/{total} tasks. Blockers: {list}.
Next: {first unchecked task ID and description}.
Key decisions: {brief list from this session}.

Include context beyond checkboxes for fresh session resume.

NEVER auto-start phx-review or any other phase.

Step 6: Check for Additional Plans

After completion, use Glob to find other plan files matching

.claude/plans/*/plan.md. If pending plans exist, inform the

user. Do NOT auto-start.

Integration

phx-plan → phx-work (YOU ARE HERE) → phx-review → phx-compound
                 ↑ ASK USER before each transition

References

  • references/execution-guide.md -- Task routing, parallel execution, verification
  • references/resume-strategies.md -- Resume modes and state persistence
  • references/file-formats.md -- Plan and progress file formats
  • references/error-recovery.md -- Error handling and blockers
  • references/harness-patterns.md -- Critic-refiner pattern for debugging loops

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take oliver-kriska/phx-work from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.