Agent skill

Issue Workflow

by atomisticnet in atomisticnet/aenet

Plan, implement, review, validate, and close aenet work tracked by shared or local issues, or explicitly linked GitHub issues.

MPL-2.0Auto-check passed

Install Issue Workflow

skills CLI
$ npx skills add atomisticnet/aenet --skill issue-workflow -a claude-code

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

GitHub CLI
$ gh skill install atomisticnet/aenet issue-workflow --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/atomisticnet/aenet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/issue-workflow .claude/skills/issue-workflow && 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
issue-workflow
GitHub stars
129
Token cost
~980 tokens
SKILL.md length
478 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MPL-2.0

At a glance

Plan, implement, review, validate, and close aenet work tracked by shared or local issues, or explicitly linked GitHub issues.

  • Addressing tracked work
  • SKILL.md covers Establish the contract and plan, Implement and review and Validate, close, and hand off
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Not read-only exploration

What it does

Issue Workflow is an agent skill from atomisticnet/aenet. Plan, implement, review, validate, and close aenet work tracked by shared or local issues, or explicitly linked GitHub issues. Use for addressing tracked work, not read-only exploration or triage.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with GitHub. The repository describes itself as: Atomic interaction potentials based on artificial neural networks. The licence is MPL-2.0.

When your agent uses it

  • Addressing tracked work
  • Not read-only exploration

Example prompts

  • “/issue-workflow”

What it can do on your machine

Read from SKILL.md and the folder at commit 9403bc5. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Issue Workflow loads about 980 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 478 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~980

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 atomisticnet/aenet at commit 9403bc5, republished under its MPL-2.0 licence (© atomisticnet). 478 words, ~980 tokens.

Download SKILL.mdSave it as .claude/skills/issue-workflow/SKILL.md (or your agent's skills folder).
name
issue-workflow
description
Plan, implement, review, validate, and close aenet work tracked by shared or local issues, or explicitly linked GitHub issues. Use for addressing tracked work, not read-only exploration or triage.

Issue Workflow

Follow AGENTS.md for approval, task storage, and external-action permissions. Read shared engineering standards before implementation or review. Use ISSUES.md for shared work and LOCAL_ISSUES.md for implementation tasks; a small task needs only a local issue. Keep records proportional to the work.

Establish the contract and plan

Read the complete task, related records, relevant implementation, tests, public callers, and documentation. Verify that the task still matches actual behavior. Identify acceptance criteria, compatibility constraints, numerical assumptions, required configurations, dependencies, and out-of-scope work.

Split work only when it contains independently reviewable units or requires separate contracts or validation. Record dependencies and keep an umbrella open until its children and combined acceptance criteria are complete.

Present the behavioral outcome, implementation units, regression checks, compatibility decisions, documentation changes, and validation plan. During planning, write only private development notes; leave code, tests, maintained documentation, and task status unchanged. Obtain approval under AGENTS.md before implementation. An approved detailed child sequence does not need repeated approval unless its scope or contracts materially change.

Implement and review

Apply the shared engineering standards' test-first policy, including characterization coverage and documented exceptions. Implement one approved logical unit, updating relevant tests, interface comments, documentation, and task evidence together. Use the build-test skill for backend checks and the documentation skill for substantive docs work.

For substantive shared work, use a local topic branch based on dev when isolation is useful. Follow the branch workflow in AGENTS.md: local topic branches are not routinely public, and temporary test/<purpose> branches used for hosted validation are deleted after their evidence is recorded.

Before declaring the unit ready to commit, inspect its complete diff and apply the review checklist. Passing tests do not substitute for reviewing numerical correctness, compatibility, simplicity, and test integrity. Preserve unrelated edits.

Resolve known P0-P2 findings within scope. Record proportionate P3 follow-ups. When a required fix materially expands the approved contract, describe the finding and obtain direction rather than silently broadening the task.

Show full SKILL.md (157 more words)Show less

Validate, close, and hand off

Run focused checks, then broaden as regression risk requires. Compare every acceptance criterion with the final implementation and actual validation. Distinguish environment failures, product failures, and unrun checks.

Close local work after validation, when ready to commit, by moving its entry into CLOSED_LOCAL_ISSUES.md with a concise outcome and validation receipt. For completed shared work, move its issue file to closed-issues/ and remove its active index entry before merging, following AGENTS.md. Neither closure requires a final commit hash or a date in the filename. Preserve ID counters. Leave deferred issues indexed and keep an issue open when a promised deliverable or required validation is missing. Do not close a parent merely because one child is complete. Only update GitHub with user authorization.

Summarize the result and evidence, identify remaining work, and propose the complete commit message under the AGENTS.md policy, including a body when the change warrants one. Do not commit without confirmation.

© atomisticnet, MPL-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/issue-workflow of atomisticnet/aenet.

Open the folder on GitHubat commit 9403bc5

Compare with similar skills

Issue Workflow 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.

Issue Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Issue Workflow this skillatomisticnet/aenet129—~980Automated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Diagnosing Superpowers Sessionsobra/superpowers296k3 repos~1.7kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    296k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.8k tokensUpdated today
    Research & ScienceAuto-check: notes

More from atomisticnet/aenet

  • Build Test

    atomisticnet/aenet

    Configure, build, and validate the aenet Fortran backend with CMake and CTest, including compiler, MPI, and BLAS variants relevant to the change.

    129 GitHub stars~1k tokensUpdated 12 days ago
    Auto-check passed
  • Code Review

    atomisticnet/aenet

    Review aenet commits, branches, diffs, or working-tree changes for correctness, numerical validity, compatibility, maintainability, and test quality.

    129 GitHub stars~537 tokensUpdated 12 days ago
    Auto-check passed
  • Documentation

    atomisticnet/aenet

    Create or substantially revise aenet maintained documentation, Fortran or C interface comments, CLI help, and runnable examples using the repository's current documentation sources.

    129 GitHub stars~654 tokensUpdated 12 days ago
    Auto-check passed

Works with

Questions about Issue Workflow

What does Issue Workflow do?

Plan, implement, review, validate, and close aenet work tracked by shared or local issues, or explicitly linked GitHub issues. Issue Workflow is an agent skill from atomisticnet/aenet. Plan, implement, review, validate, and close aenet work tracked by shared or local issues, or explicitly linked GitHub issues.

When should I use Issue Workflow?

Issue Workflow fits situations like: addressing tracked work; not read-only exploration.

How do I install Issue Workflow in Claude Code?

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

How do I install Issue Workflow in Codex?

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

Can I use Issue Workflow 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 atomisticnet/aenet --skill issue-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/issue-workflow, .gemini/skills/issue-workflow, .github/skills/issue-workflow and .opencode/skills/issue-workflow in your project.

What does Issue Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Issue Workflow is instructions for the agent only.

Does Issue Workflow 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 Issue Workflow 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 Issue Workflow use?

Issue Workflow is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Issue Workflow use?

About 980 tokens (SKILL.md is roughly 3.9k 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 Issue Workflow?

Skills that share tags, products or a category with Issue Workflow: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars) and Greploop (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Issue Workflow?

atomisticnet (a GitHub organization) maintains it in atomisticnet/aenet, which has 129 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 25, 2026.

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