Agent skill

Squid Implement Task

by iusztinpaul in iusztinpaul/squid

Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS.

Apache-2.0Auto-check passedTesting & QA

Install Squid Implement Task

skills CLI
$ npx skills add iusztinpaul/squid --skill squid-implement-task -a claude-code

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

GitHub CLI
$ gh skill install iusztinpaul/squid squid-implement-task --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/iusztinpaul/squid.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/squid-implement-task .claude/skills/squid-implement-task && 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
squid-implement-task
GitHub stars
203
Token cost
~1.3k tokens
SKILL.md length
508 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS.

  • Works in 2 steps: Resolve the task list → Per task, in order: SWE → Tester → commit
  • More GROOMED tasks are ready to build
  • SKILL.md covers Step 1 — Resolve the task list, Step 2 — Per task, in order:…, Output and Notes
  • Calls git

What it does

Squid Implement Task is an agent skill from iusztinpaul/squid. Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. Use when one or more GROOMED tasks are ready to build. To plan a feature first use /squid-plan; for the full end-to-end pipeline use /squid-implement-night.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering End-to-end testing. The licence is Apache-2.0.

When your agent uses it

  • More GROOMED tasks are ready to build
  • Tasks that involve End-to-end testing

Example prompts

  • “/squid-implement-task”

Workflow steps

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

  1. Resolve the task list
  2. Per task, in order: SWE → Tester → commit

What it can do on your machine

Read from SKILL.md and the folder at commit f5bf6b3. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Squid Implement Task loads about 1.3k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 508 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from iusztinpaul/squid at commit f5bf6b3, republished under its Apache-2.0 licence (© iusztinpaul). 508 words, ~1,348 tokens.

Download SKILL.mdSave it as .claude/skills/squid-implement-task/SKILL.md (or your agent's skills folder).
name
squid-implement-task
description
Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. Use when one or more GROOMED tasks are ready to build. To plan a feature first use /squid-plan; for the full end-to-end pipeline use /squid-implement-night.
argument-hint
<task-ref | "task description" | plan-ref | list of task-refs>

Implement Task — inner SWE↔Tester loop (1 or N tasks)

Take a task (or a list of tasks / an approved Tasks Plan) and drive each one through the inner SWE → Tester loop, committing each task once it passes. Runs in whatever working tree it's invoked in — the feature worktree when /squid-implement-night invokes it (pass Working directory: {path} to every agent), your current branch when standalone. No worktrees are created here (that's /squid-plan's job) and no human gates run here (those live in /squid-plan and at the end of /squid-implement-night).

$ARGUMENTS is one of: a single task ref (NNN-slug / #N), a free-form task description, the feature's pending task files (tasks/<NNN>-*.md, status: pending), or several refs. If empty, ask the human what to implement.

You are the orchestrator — a MANAGER, not an implementer. You launch agents, enforce the Tester gate, and commit on green. You do NOT write code, run tests, or review the diff yourself beyond inspection (git diff, git log).

Read AGENTS.md first to confirm the active tracker mode (file or gh) and the project's stack + test commands.

Critical rules:

  • Never rubber-stamp the Tester. Spot-check that each AC marked PASS has real evidence (test name, file:line, command output) and that the e2e adversarial section actually attempted break paths. Re-launch with concrete feedback if not.
  • One agent per task. Never bundle multiple tasks into one agent call.
  • Commit each task on PASS — do NOT push. Pushing, PR creation, acceptance, and review are /squid-review's job.

Step 1 — Resolve the task list

Build an ordered list of tasks from $ARGUMENTS:

  • Tracker ref(s) (NNN-slug / #N) → load each task's tasks/<NNN>-<slug>.md.
  • Approved Tasks Plan → the feature's tasks/<NNN>-*.md files with status: pending, in NNN order (gh mode: the feature's open issues).
  • Free-form description → a single ephemeral task; don't create a task file unless the human asks.
  • Empty → ask the human what to implement.

Surface the resolved task list back in one short block before starting.


Show full SKILL.md (223 more words)Show less

Step 2 — Per task, in order: SWE → Tester → commit

For each task in the list, run the loop:

2a. SWE implements
Agent(
  subagent_type="squid:software-engineer",
  prompt="""Implement task {ID}. Read AGENTS.md first. Follow your role definition.
  {Working directory: {path}  — include this line only when orchestrated by /squid-implement-night.}
  Stay on the current feature branch — do NOT create a per-task branch (no `feat/{ID}-…`); if you are on `main`, create ONE `feat/{slug}` branch first per your Branch section. Each task is one commit on that shared feature branch.
  Write code AND tests. Run the project's format-fix + lint-fix + pre-commit + unit-tests until clean.
  DO NOT commit yet — the Tester goes first. Append a SWE log entry (or include it in your final message for ephemeral tasks)."""
)
2b. Tester verifies
Agent(
  subagent_type="squid:tester",
  prompt="""QA task {ID}. Read AGENTS.md first. Follow your role definition — your headline duty is the e2e adversarial pass.
  {Working directory: {path}.}
  SWE summary: {hand-off message}.
  Verify every acceptance criterion with evidence. Append a Tester log entry. Verdict: PASS or FAIL."""
)
2c. Handle the verdict — Fails?
  • FAIL (or a rubber-stamped PASS) → relay concrete feedback to the SWE and re-run 2b on the same task:
    Agent(
      subagent_type="squid:software-engineer",
      prompt="QA failed on task {ID}. {Working directory: {path}.} Concrete feedback: {failed ACs + break-path failures + fixes}. Apply the fixes, re-run the local QA loop, append a log entry. DO NOT commit."
    )
  • PASS (verified) → go to 2d.

Retry cap — Tester FAIL max 5 per task. On the 5th FAIL without a PASS: mark the task blocked, surface USER ACTION REQUIRED with the failing AC + last Tester report, and STOP — do not continue to later tasks (the foundation is broken). The counter resets when the task changes.

2d. Commit the task (on PASS only)
Agent(
  subagent_type="squid:software-engineer",
  prompt="""Tester PASSED task {ID}. {Working directory: {path}.} Commit JUST this task per your Commit section
  (generator, specific files, task reference, file-mode `status: done` + `git mv` to tasks/done/). DO NOT push."""
)
2e. Finished tasks?
  • More tasks remain → next task (back to 2a).
  • All tasks done → STOP; see Output.

Output

Code + tests, committed per task (no push). Report a short summary: tasks done, the commit subject + ref for each, and any task that hit the retry cap. When invoked by /squid-implement-night, hand this summary back so it can proceed to /squid-review.


Notes

  • Rollup / fix tasks handed in by /squid-review (or by a human) are just more tasks — feed them in and the same loop applies.

© iusztinpaul, 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

Just SKILL.md in skills/squid-implement-task of iusztinpaul/squid.

Open the folder on GitHubat commit f5bf6b3

Compare with similar skills

Squid Implement Task 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.

Squid Implement Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Squid Implement Task this skilliusztinpaul/squid203—~1.3kAutomated safety check: PassApache-2.0
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
Uloop Replay Inputkurotu/VRCQuestTools3733 repos~615Automated safety check: PassMIT
Ui4 Convert Testspayloadcms/payload45k—~3.5kAutomated safety check: PassMIT
E2Estackia/rtp2httpd2.2k—~517Automated safety check: PassGPL-2.0

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed
  • Uloop Replay Input

    kurotu/VRCQuestTools

    Replay recorded PlayMode keyboard and mouse input. An agent skill from kurotu/VRCQuestTools.

    373 GitHub starsUsed in 3 repos~615 tokens
    Testing & QAAuto-check passed
  • Ui4 Convert Tests

    payloadcms/payload

    A skill your agent uses when UI changes are complete and e2e tests need updating.

    45k GitHub stars~3.5k tokensUpdated today
    Testing & QAAuto-check passed
  • E2E

    stackia/rtp2httpd

    Write, run, review, or debug rtp2httpd E2E tests and their harness in e2e/ and scripts/run-e2e.sh.

    2.2k GitHub stars~517 tokensUpdated 6 days ago
    Testing & QAAuto-check passed
  • Moav E2E

    MotherofallVPNs/MoaV

    Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.

    448 GitHub stars~1.9k tokensUpdated yesterday
    Testing & QAAuto-check: notes

More from iusztinpaul/squid

All 13 skills in this repo
  • Squid Implement Night

    iusztinpaul/squid

    Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR.

    203 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Squid Review

    iusztinpaul/squid

    Push the committed feature branch, create or update its PR, then run Product Architect acceptance and PR-Reviewer on it.

    203 GitHub stars~873 tokensUpdated 1 mo ago
    Auto-check passed
  • Squid Review CI

    iusztinpaul/squid

    Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE.

    203 GitHub stars~607 tokensUpdated 1 mo ago
    Auto-check passed
  • Squid Testing Python

    iusztinpaul/squid

    Write and evaluate effective Python tests using pytest. An agent skill from iusztinpaul/squid.

    203 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Squid Architecture Review

    iusztinpaul/squid

    Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.

    203 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Squid Clean Harness

    iusztinpaul/squid

    Shrink an agent harness (.agents/ skills + resources) to the minimum tokens that keep the exact same logic.

    203 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Squid Implement Task

What does Squid Implement Task do?

Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. Squid Implement Task is an agent skill from iusztinpaul/squid. Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS.

When should I use Squid Implement Task?

Squid Implement Task fits situations like: more GROOMED tasks are ready to build; tasks that involve End-to-end testing.

How do I install Squid Implement Task in Claude Code?

Run `npx skills add iusztinpaul/squid --skill squid-implement-task -a claude-code`. Or copy the skill folder (skills/squid-implement-task in iusztinpaul/squid) into .claude/skills/squid-implement-task in your project. Claude Code loads it when a task matches its description.

How do I install Squid Implement Task in Codex?

Run `npx skills add iusztinpaul/squid --skill squid-implement-task -a codex`. Or copy the skill folder (skills/squid-implement-task in iusztinpaul/squid) into .agents/skills/squid-implement-task in your project. Codex loads it when a task matches its description.

Can I use Squid Implement Task 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 iusztinpaul/squid --skill squid-implement-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/squid-implement-task, .gemini/skills/squid-implement-task, .github/skills/squid-implement-task and .opencode/skills/squid-implement-task in your project.

What does Squid Implement Task need to run?

Going by SKILL.md and its folder, Squid Implement Task needs the command-line tools its instructions call (git).

Does Squid Implement Task access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Squid Implement Task 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. Review the folder before installing.

What licence does Squid Implement Task use?

Squid Implement Task 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 Squid Implement Task use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 Squid Implement Task?

Skills that share tags, products or a category with Squid Implement Task: Web Application Testing (anthropics/skills, 180k stars), TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars), Uloop Replay Input (kurotu/VRCQuestTools, 373 stars) and Ui4 Convert Tests (payloadcms/payload, 45k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Squid Implement Task?

iusztinpaul (a GitHub user) maintains it in iusztinpaul/squid, which has 203 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 3, 2026.

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