Agent skill

Task Coverage Protocol

by GoogleCloudPlatform in GoogleCloudPlatform/cxas-scrapi

Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism.

Apache-2.0Auto-check passedDevelopment

Install Task Coverage Protocol

skills CLI
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill task-coverage-protocol -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GoogleCloudPlatform/cxas-scrapi task-coverage-protocol --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/protocols/task-coverage-protocol .claude/skills/task-coverage-protocol && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
task-coverage-protocol
GitHub stars
107
Token cost
~873 tokens
SKILL.md length
383 words
Files
67 (incl. scripts)
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism.

  • Works in 5 steps: Scoped Scan & Scoping Setup → Consume the Handoff Directive → Yield Terminal & Polling Gate → …
  • Tasks that involve Async programming
  • SKILL.md covers Architectural Overview and Execution Workflow
  • Runs Python scripts from its folder; calls python3

What it does

Task Coverage Protocol is an agent skill from GoogleCloudPlatform/cxas-scrapi. Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 72 other files, including scripts (for example `evals/TESTING.md`, `evals/cases/add_items_1032/SETUP.md` and `evals/cases/add_items_1032/case.yaml`).

It sits in Development, covering Async programming. The repository describes itself as: A powerful Python API, CLI, and set of Agent Skills for CX Agent Studio to automate, evaluate, and scale your agents with ease. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Async programming

Example prompts

  • “Use the task-coverage-protocol skill to enforce 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism”
  • “/task-coverage-protocol”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Scoped Scan & Scoping Setup
  2. Consume the Handoff Directive
  3. Yield Terminal & Polling Gate
  4. Progress Verification & Next Slices
  5. Final Compilation & Completion

What it can do on your machine

Read from SKILL.md and the folder at commit ffba639. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Task Coverage Protocol loads about 873 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 383 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~873

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from GoogleCloudPlatform/cxas-scrapi at commit ffba639, republished under its Apache-2.0 licence (© GoogleCloudPlatform). 383 words, ~873 tokens.

Download SKILL.mdSave it as .claude/skills/task-coverage-protocol/SKILL.md (or your agent's skills folder). This skill also uses 66 other files; get the full folder from GitHub.
name
task-coverage-protocol
description
Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism.

PROTOCOL: Supervisor-Driven Task Coverage Checklist

This protocol governs how you must handle large, repetitive, or multi-step requirements ingestion tasks to prevent context drift, avoid memory exhaustion, and guarantee 100% file coverage. Workloads are partitioned into sliced batches dynamically monitored by a decoupled supervisor.

Architectural Overview

Instead of attempting to list and process hundreds of files in a single conversation turn, tasks are executed asynchronously:

  1. The Ingestor Supervisor scans the directory, partitions the files, and outputs a structured batch directive.
  2. You (or parallel subagents) consume this directive, process only the assigned slice of files, and write the output files to the designated folder.
  3. The supervisor verifies and grades the outputs before queueing the next slice.

Execution Workflow

1. Scoped Scan & Scoping Setup

When instructed to ingest a requirements directory (e.g. "Ingest and parse all files in this folder"), you MUST launch the Supervisor script to initialize the task state:

bash
python3 protocols/task-coverage-protocol/scripts/ingestor_supervisor.py \
  --source_dir="path/to/source" \
  --target_skill="path/to/cxas-cuj-report-generator/"
2. Consume the Handoff Directive

The supervisor will scan the target folder, slice the files into batch lists of size 10, and print a structured directive to standard output: SPAWN_BATCH_DIRECTIVE: {"spec_file": "/tmp/ingestor/batch_spec.json", "output_dir": "/tmp/ingestor/outputs/"}

Upon seeing this token, you MUST:

  1. Read the spec file /tmp/ingestor/batch_spec.json to retrieve the list of files, prompts, and expected output paths.
  2. Spawn fresh, parallel subagents (one per file or partition) using their respective prompt files (e.g., /tmp/ingestor/prompts/<file_name>_prompt.txt).
  3. Instruct the subagents to write their generated YAML transcripts directly to /tmp/ingestor/outputs/<file_name>_output.txt.
Show full SKILL.md (145 more words)Show less
3. Yield Terminal & Polling Gate

Once parallel subagents have been spawned in the background, you MUST immediately stop calling tools and go idle (or report status) to release the terminal lock. The supervisor will poll the output directory until all files are completed.

4. Progress Verification & Next Slices

When all subagents have delivered their YAML transcripts, run the supervisor script again:

bash
python3 protocols/task-coverage-protocol/scripts/ingestor_supervisor.py \
  --source_dir="path/to/source" \
  --target_skill="path/to/cxas-cuj-report-generator/"
  • Verification Pass: If the supervisor grades all outputs as passing, it automatically advances the file pointer and writes the next batch spec. Consume the new directive and repeat the parallel spawning cycle!
  • Verification Fail: If the supervisor detects any syntax, schema, or linguistic violations, it automatically triggers recovery, rebasing, or load bisection. Re-spawn the corrective subagents as directed.
5. Final Compilation & Completion

When all batch slices are fully processed, the supervisor will declare All files successfully ingested! and compile the final interactive CUJ reports.

© GoogleCloudPlatform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 66 other files (scripts) in .agents/skills/cxas-cuj-report-generator/protocols/task-coverage-protocol of GoogleCloudPlatform/cxas-scrapi.

  • SKILL.md
  • evals/TESTING.md
  • evals/cases/add_items_1032/SETUP.md
  • evals/cases/add_items_1032/case.yaml
  • evals/cases/add_items_1032/setup.py
  • evals/cases/add_items_10423/SETUP.md
  • evals/cases/add_items_10423/case.yaml
  • evals/cases/add_items_10423/setup.py
  • evals/cases/add_items_173/SETUP.md
  • evals/cases/add_items_173/case.yaml
  • evals/cases/add_items_173/setup.py
  • evals/cases/add_items_3/SETUP.md
  • evals/cases/add_items_3/case.yaml
  • evals/cases/add_items_3/setup.py
  • evals/cases/e2e_successful_task_coverage
  • … and 52 more

Open the folder on GitHubat commit ffba639

Compare with similar skills

Task Coverage Protocol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Task Coverage Protocol compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Coverage Protocol this skillGoogleCloudPlatform/cxas-scrapi107—~873Automated safety check: PassApache-2.0
YugabyteDB ASH Instrumentationyugabyte/yugabyte-db11k—~4.5kAutomated safety check: PassCustom licence
Mirage VFS Adapter Authoringstrukto-ai/mirage3.7k—~2.5kAutomated safety check: PassApache-2.0
Golang Patternsantoniopaya22/go-rest-template1729 repos~3.5kAutomated safety check: PassNone
Rust Async Patternsdiodeme/Gold-Band14310 repos~3.1kAutomated safety check: PassAGPL-3.0
Swift Concurrencyhenrypldev/react-native-nitro-mlx1003 repos~3.1kAutomated safety check: PassMIT

Similar skills

  • YugabyteDB ASH Instrumentation

    yugabyte/yugabyte-db

    Procedure for adding or changing YugabyteDB Active Session History wait states in TServer and DocDB C++ code, including the macro to use for sync and async paths.

    11k GitHub stars~4.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Golang Patterns

    antoniopaya22/go-rest-template

    Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

    172 GitHub starsUsed in 9 repos~3.5k tokens
    DevelopmentAuto-check passed
  • Rust Async Patterns

    diodeme/Gold-Band

    Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns.

    143 GitHub starsUsed in 10 repos~3.1k tokens
    DevelopmentAuto-check passed
  • Swift Concurrency

    henrypldev/react-native-nitro-mlx

    Diagnose Swift Concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration when working with tasks, actors, @MainActor, Sendable, data races, thread safety, or…

    100 GitHub starsUsed in 3 repos~3.1k tokens
    DevelopmentAuto-check passed
  • Rust Engineer

    farm-fe/farm

    Writes, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions.

    5.6k GitHub starsUsed in 1 repo~1.5k tokens
    DevelopmentAuto-check passed

More from GoogleCloudPlatform/cxas-scrapi

All 14 skills in this repo
  • Cxas Agent Foundry

    GoogleCloudPlatform/cxas-scrapi

    End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and…

    107 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Cxas Autolabel Rules

    GoogleCloudPlatform/cxas-scrapi

    Author, validate, and manage Contact Center AI (CCAI) Insights Autolabeling Rules.

    107 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Cxas Configurable Dashboards

    GoogleCloudPlatform/cxas-scrapi

    Author, validate, and manage Contact Center AI (CCAI) Insights Configurable Dashboards.

    107 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Cxas Dfcx Migration

    GoogleCloudPlatform/cxas-scrapi

    Migrate Dialogflow CX (DFCX) agents to CXAS (Customer Experience Agent Studio) agents.

    107 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Cxas Loss Analysis

    GoogleCloudPlatform/cxas-scrapi

    Retrieves non-contained CCAI Insights conversations (losses), uses agent intelligence to cluster them into common failure patterns, and generates a markdown report.

    107 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Cxas Sim Eval

    GoogleCloudPlatform/cxas-scrapi

    Converts CXAS golden evaluations to SCRAPI SimulationEvals test cases.

    107 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Task Coverage Protocol

What does Task Coverage Protocol do?

Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism. Task Coverage Protocol is an agent skill from GoogleCloudPlatform/cxas-scrapi. Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism.

When should I use Task Coverage Protocol?

Task Coverage Protocol fits situations like: tasks that involve Async programming.

How do I install Task Coverage Protocol in Claude Code?

Run `npx skills add GoogleCloudPlatform/cxas-scrapi --skill task-coverage-protocol -a claude-code`. Or copy the skill folder (.agents/skills/cxas-cuj-report-generator/protocols/task-coverage-protocol in GoogleCloudPlatform/cxas-scrapi) into .claude/skills/task-coverage-protocol in your project. Claude Code loads it when a task matches its description.

How do I install Task Coverage Protocol in Codex?

Run `npx skills add GoogleCloudPlatform/cxas-scrapi --skill task-coverage-protocol -a codex`. Or copy the skill folder (.agents/skills/cxas-cuj-report-generator/protocols/task-coverage-protocol in GoogleCloudPlatform/cxas-scrapi) into .agents/skills/task-coverage-protocol in your project. Codex loads it when a task matches its description.

Can I use Task Coverage Protocol in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GoogleCloudPlatform/cxas-scrapi --skill task-coverage-protocol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-coverage-protocol, .gemini/skills/task-coverage-protocol, .github/skills/task-coverage-protocol and .opencode/skills/task-coverage-protocol in your project.

What does Task Coverage Protocol need to run?

Going by SKILL.md and its folder, Task Coverage Protocol needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Task Coverage Protocol access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Task Coverage Protocol safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Task Coverage Protocol use?

Task Coverage Protocol is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Task Coverage Protocol use?

About 873 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Task Coverage Protocol?

Skills that share tags, products or a category with Task Coverage Protocol: YugabyteDB ASH Instrumentation (yugabyte/yugabyte-db, 11k stars), Mirage VFS Adapter Authoring (strukto-ai/mirage, 3.7k stars), Golang Patterns (antoniopaya22/go-rest-template, 172 stars) and Rust Async Patterns (diodeme/Gold-Band, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Coverage Protocol?

GoogleCloudPlatform (a GitHub organization) maintains it in GoogleCloudPlatform/cxas-scrapi, which has 107 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.

Source: GoogleCloudPlatform/cxas-scrapi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.