New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Coral Debug

by Human-Agent-Society in Human-Agent-Society/CORAL

Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks…

Apache-2.0Auto-check passedDevelopment

Install Coral Debug

skills CLI
$ npx skills add Human-Agent-Society/CORAL --skill coral-debug -a claude-code

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

GitHub CLI
$ gh skill install Human-Agent-Society/CORAL coral-debug --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/Human-Agent-Society/CORAL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/coral-debug .claude/skills/coral-debug && 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
coral-debug
GitHub stars
1.1k
Token cost
~1.8k tokens
SKILL.md length
571 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks…

  • Editing code under coral/
  • SKILL.md covers Reproduce loops, Where to look when X breaks, Inspect a live or finished run and Test + lint, plus 2 more sections
  • Calls uv, jq and git
  • Chasing a CORAL bug

What it does

Coral Debug is an agent skill from Human-Agent-Society/CORAL. Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks (hung graders, agent restart loops, stalled agents, missing heartbeat actions, corrupted shared state, broken worktree symlinks, grader import errors, wrong-task resume), how to inspect a live or finished run under .coral/public/, and the canonical lint/test commands. Use when editing code under coral/ or chasing a…

Its SKILL.md is about 1.8k 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 Development, covering Git worktrees and Linting and formatting. It works with pytest. The repository describes itself as: Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026. The licence is Apache-2.0.

When your agent uses it

  • Editing code under coral/
  • Chasing a CORAL bug
  • NOT when adding a new task
  • Extending the framework

Example prompts

  • “/coral-debug”

Requirements

  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 0123dfb. 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:

    • uv
    • jq
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use uv and 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

Coral Debug loads about 1.8k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 571 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 Human-Agent-Society/CORAL at commit 0123dfb, republished under its Apache-2.0 licence (© Human-Agent-Society). 571 words, ~1,758 tokens.

Download SKILL.mdSave it as .claude/skills/coral-debug/SKILL.md (or your agent's skills folder).
name
coral-debug
description
Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks (hung graders, agent restart loops, stalled agents, missing heartbeat actions, corrupted shared state, broken worktree symlinks, grader import errors, wrong-task resume), how to inspect a live or finished run under `.coral/public/`, and the canonical lint/test commands. Use when editing code under `coral/` or chasing a CORAL bug, NOT when adding a new task or extending the framework.

CORAL debug & change-verification workflows

This skill is for people (and Claude Code) hacking on the CORAL package itself, not for users authoring a task. For authoring guides see the siblings:

  • coral-new-task — creating a new examples/<task>/ (seed + task.yaml + grader)
  • coral-extend — extending CORAL itself (new runtime, new CLI command, new bundled skill, ...)

Reproduce loops

Pick the smallest one that exercises your change.

Editing...Fastest reproduce
coral/grader/{task_grader,loader,subprocess_grader}.py or a builtin graderuv run coral validate examples/circle_packing (or any example with a packaged grader)
coral/grader/daemon.py (parallel grading, queueing, worktree isolation)uv run pytest tests/test_grader_daemon.py -v
coral/grader/{base,protocol}.pyuv run pytest tests/test_grader.py tests/test_subprocess_grader.py -v
coral/cli/*.py (argparse, dispatch, output formatting)Run the command directly: uv run coral log --help, uv run coral status, etc. against a latest run under examples/<task>/results/
coral/hooks/post_commit.py (submit_eval)uv run pytest tests/test_hooks.py -v, then end-to-end via coral start -c task.yaml agents.count=1 and watch .coral/public/attempts/
coral/agent/manager.py, state.py, exit_classifier.pyuv run pytest tests/test_manager_reliability.py tests/test_manager_seen_attempts.py -v
coral/agent/builtin/*.py (a runtime)uv run pytest tests/test_<runtime>.py if it exists, then coral start -c task.yaml agents.runtime=<name> agents.count=1
coral/workspace/{project,worktree,repo,grader_env}.pyuv run pytest tests/test_workspace.py tests/test_grader_env.py -v
coral/hub/{attempts,notes,skills,checkpoint,heartbeat}.pyuv run pytest tests/test_hub.py tests/test_checkpoint.py tests/test_heartbeat.py -v
coral/template/coral_md.py or templatesuv run pytest tests/test_template.py -v
coral/config.pyuv run pytest tests/test_config.py -v
coral/web/* (dashboard)uv run coral ui against any existing run; reload the browser after edits

End-to-end smoke (slow but exercises the whole pipeline):

bash
uv run coral start -c examples/circle_packing/task.yaml agents.count=1 run.session=local
# Wait for one eval to land in .coral/public/attempts/, then:
uv run coral stop

Where to look when X breaks

SymptomFirst place to look
Grader hangs / pending attempts pile up.coral/public/grader_daemon.pid (is daemon alive?), .coral/public/grader_daemon_heartbeat (mtime), .coral/public/eval_logs/<hash>/ for grader stdout/stderr
coral eval errors outThe pending JSON itself: .coral/public/attempts/<hash>.json — status and feedback fields. Source: coral/hooks/post_commit.py::submit_eval
Agent restart loopcoral status shows pause state. Source: coral/agent/manager.py (restart_burst_threshold, restart_burst_window). Per-agent runtime stdout/stderr is captured under the worktree.
Stalled agentagents.timeout watchdog in coral/agent/manager.py. Grader-queue exemption (grader_pending_max_age) skips the watchdog while a recent submission is still pending.
Heartbeat actions not firing.coral/public/heartbeat/<agent_id>.json (per-agent action list), .coral/public/eval_count (global counter). Logic: coral/agent/heartbeat.py::HeartbeatRunner.check.
Shared state corrupted / race.coral/public/.git/ is a real git repo — git -C .coral/public log shows checkpoint history; coral notes --history is the friendly view.
Worktree symlinks missingcoral/workspace/worktree.py — symlinks .coral/public/ into each agent worktree under the runtime-specific name (.claude / .codex / .opencode).
Grader can't import its packageCheck .coral/private/grader_venv/ — setup_grader_env ran uv venv + grader.setup once at run start. Re-running coral start on the same run_dir does NOT re-bootstrap; delete the venv to force it.
Resume picks up wrong taskcoral resume reads .coral/config.yaml and .coral/config_dir. The latest symlink at results/<task-slug>/latest decides which run is resumed.
Show full SKILL.md (164 more words)Show less

Inspect a live or finished run

bash
RUN=$(readlink -f results/<task-slug>/latest)
ls "$RUN/.coral/public/"            # attempts/, notes/, skills/, agents/, logs/, eval_logs/, eval_count
cat "$RUN/.coral/public/attempts/<hash>.json" | jq .
ls "$RUN/agents/"                    # one worktree per agent
cat "$RUN/.coral/config.yaml"        # exact config used (post-merge)

The web dashboard (coral ui) reads the same files; if you're debugging dashboard rendering, coral/web/api.py is the route handler and coral/web/static/ is the built React bundle.

Test + lint

bash
uv sync --extra dev                  # one-time, gets pytest + ruff
uv run pytest tests/ -v              # full suite (~seconds, no docker)
uv run pytest tests/test_<thing>.py -v -k <pattern>
uv run ruff check .                  # lint
uv run ruff format .                 # autoformat

There is no separate type-check step in CI yet; tests cover the contract.

Quick task scaffold for ad-hoc testing

When you need a throwaway task to exercise a code change:

bash
uv run coral init /tmp/coral-scratch
# edit /tmp/coral-scratch/grader/src/coral_scratch_grader/grader.py to return a simple float
uv run coral validate /tmp/coral-scratch
uv run coral start -c /tmp/coral-scratch/task.yaml agents.count=1 run.session=local

coral validate runs the grader against seed/ in a tempdir without spawning agents — the fastest way to confirm a grader change compiles and produces a Score.

Conventions

  • No git from agents. All commits go through coral eval. If you're adding a feature that needs to commit, route it through coral/hooks/post_commit.py or coral/hub/checkpoint.py.
  • Atomic writes for any JSON in .coral/public/. Use coral.hub.attempts.write_attempt (tmp + rename) as the model.
  • Idempotent setup. setup_run_dir, setup_grader_env, init_checkpoint_repo must all be safe to call twice.
  • Shared dir is configurable. Don't hardcode .claude; thread shared_dir through (see coral/template/coral_md.py).
  • Lazy imports in CLI dispatch (coral/cli/__init__.py) — keep coral --help fast.

© Human-Agent-Society, 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 .claude/skills/coral-debug of Human-Agent-Society/CORAL.

Open the folder on GitHubat commit 0123dfb

Compare with similar skills

Coral Debug 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.

Coral Debug compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coral Debug this skillHuman-Agent-Society/CORAL1.1k—~1.8kAutomated safety check: PassApache-2.0
Kedro Babysitkedro-org/kedro11k—~4kAutomated safety check: PassCustom licence
Cut Releasemicrosoft/apm4k—~2.5kAutomated safety check: PassMIT
Python Project Creatorhaddock-development/claude-reflect-system379—~1.4kAutomated safety check: NotesNone
Worktree Env Setupmeta-pytorch/attention-gym1.3k—~858Automated safety check: PassBSD-3-Clause
Experiment Iterative CoderEvoScientist/EvoSkills4763 repos~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Kedro Babysit

    kedro-org/kedro

    Run Kedro's local lint / format / type-check / tests on changed files (uses the project's pre-commit hooks, ruff, mypy, pytest, lint-imports, detect-secrets, Make targets — in the right venv), or…

    11k GitHub stars~4k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Cut Release

    microsoft/apm

    Official

    A skill your agent uses to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the…

    4k GitHub stars~2.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Python Project Creator

    haddock-development/claude-reflect-system

    Creates Python projects with proper structure, virtual environments, and dependency management.

    379 GitHub stars~1.4k tokensUpdated 8 mo ago
    DevelopmentAuto-check: notes

  • Worktree Env Setup

    meta-pytorch/attention-gym

    Sets up an isolated per-worktree Python environment for attention-gym development using nightly PyTorch and the CI-mirroring uv flow.

    1.3k GitHub stars~858 tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Experiment Iterative Coder

    EvoScientist/EvoSkills

    Iterative code refinement through plan → code → evaluate → refine cycles.

    476 GitHub starsUsed in 3 repos~2.5k tokens
    DevelopmentAuto-check passed

  • Adk Setup

    google/adk-python

    Official

    Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…

    22k GitHub stars~993 tokensUpdated yesterday
    DevelopmentAuto-check: notes

More from Human-Agent-Society/CORAL

  • Creating A Coral Task

    Human-Agent-Society/CORAL

    Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…

    1.1k GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Running Coral Experiments

    Human-Agent-Society/CORAL

    Run and manage CORAL experiments from the operator side — launch agents with coral start (dotlist overrides, model/count, tmux vs local), monitor with coral status / coral log / coral show / the web…

    1.1k GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Coral New Task

    Human-Agent-Society/CORAL

    End-to-end recipe for adding a new task under examples/ — the three pieces that have to line up (task.yaml, seed/, and grader/), what to put in each, the TaskGrader API surface, the coral validate →…

    1.1k GitHub stars~3.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Promoting Dev To Main

    Human-Agent-Society/CORAL

    A skill your agent uses when preparing, reviewing, resolving conflicts for, or merging a CORAL release pull request from the long-lived dev branch into main.

    1.1k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed

  • Setting Up Coral

    Human-Agent-Society/CORAL

    One-time machine setup after installing the coral CLI — register local agent runtimes as named bindings with coral setup / coral setup agent, validate them with coral agents doctor (incl.

    1.1k GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Coral Extend

    Human-Agent-Society/CORAL

    Add a new component to the CORAL framework itself — a new agent runtime under coral/agent/builtin/ (claudecode/codex/cursoragent style), a new CLI command in coral/cli/, a new bundled skill or…

    1.1k GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Coral Debug

What does Coral Debug do?

Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks…. Coral Debug is an agent skill from Human-Agent-Society/CORAL.coral/public/, and the canonical lint/test commands.

When should I use Coral Debug?

Coral Debug fits situations like: editing code under coral/; chasing a CORAL bug; NOT when adding a new task; extending the framework.

How do I install Coral Debug in Claude Code?

Run `npx skills add Human-Agent-Society/CORAL --skill coral-debug -a claude-code`. Or copy the skill folder (.claude/skills/coral-debug in Human-Agent-Society/CORAL) into .claude/skills/coral-debug in your project. Claude Code loads it when a task matches its description.

How do I install Coral Debug in Codex?

Run `npx skills add Human-Agent-Society/CORAL --skill coral-debug -a codex`. Or copy the skill folder (.claude/skills/coral-debug in Human-Agent-Society/CORAL) into .agents/skills/coral-debug in your project. Codex loads it when a task matches its description.

Can I use Coral Debug 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 Human-Agent-Society/CORAL --skill coral-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coral-debug, .gemini/skills/coral-debug, .github/skills/coral-debug and .opencode/skills/coral-debug in your project.

What does Coral Debug need to run?

Going by SKILL.md and its folder, Coral Debug needs the command-line tools its instructions call (uv, jq and git). Our summary lists: Docker.

Does Coral Debug access the network?

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

Is Coral Debug 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 Coral Debug use?

Coral Debug 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 Coral Debug use?

About 1.8k tokens (SKILL.md is roughly 7k 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 Coral Debug?

Skills that share tags, products or a category with Coral Debug: Kedro Babysit (kedro-org/kedro, 11k stars), Cut Release (microsoft/apm, 4k stars), Python Project Creator (haddock-development/claude-reflect-system, 379 stars) and Worktree Env Setup (meta-pytorch/attention-gym, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coral Debug?

Human-Agent-Society (a GitHub organization) maintains it in Human-Agent-Society/CORAL, which has 1,058 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 8, 2026.

Source: Human-Agent-Society/CORAL on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.