MCPInstall

issue-spec

Create or revise a focused specification issue when explicitly requested or required by the repository contribution policy. Discover existing work, capture intent and acceptance criteria, and reconcile decisions before implementation.

Installs
61
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/onsager-ai/dev-skills --skill issue-spec
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads issue-spec automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Issue specification

Scope

This skill owns specification method, not which changes require a spec. Read AGENTS.md and the relevant repo workflow overlay for the target repository, always-spec surfaces, labels, required sections and exceptions. An explicit request to write a spec is sufficient to start; do not re-ask whether to do it. Use the repository's declared spec medium. Use GitHub issues when it adopts the issue-based SDD loop; do not migrate another repository's spec format by inference.

Prerequisites

Know the intended change, target repo and applicable contract. For GitHub work, use harness-operations only if capability mapping is needed. No personal installation or particular GitHub tool is required. Read the format reference when drafting and use the template as a starting point, not extra policy.

Procedure

  1. Discover relevant code, recent changes and existing issues/specs. Reuse or amend related work instead of creating a duplicate. Resolve the target repo from its checkout/remote and contract; do not infer it from the skill's source repo.
  2. Capture intent with Overview, Design, independently verifiable Plan items, matching Test items, Alignment and optional Notes. Include the repo's required impact/example sections. Keep the spec near 2000 tokens or less; split a larger feature into a parent and independently scoped children.
  3. State boundaries in Alignment. Proceed with already authorized implementation decisions. For a concrete unresolved human boundary needed for the work, use the structured question capability mapped by harness-operations; name its source, affected Plan items, options and tradeoffs. A plain-text question or Human decides checklist alone does not request the decision. Wait for an explicit answer before dependent work; continue independent authorized work. Reconcile the answer into the spec in the same sitting and clear answered blockers. If no permitted question tool exists, state that limitation and use the established handoff channel without assuming an answer.
  4. Validate scope, invariants, test coverage, dependencies and required labels. In GitHub bodies keep each prose paragraph or list item on one source line; blank lines separate blocks. Do not mark Plan items complete before delivery.
  5. Publish or update the spec through an available authorized tool. Apply existing repo labels, priority and area conventions; do not create a new taxonomy merely because this procedure uses one in an example. Establish child relationships with native sub-issues where supported, otherwise record explicit links.
  6. Hand ready work to pre-push and pr-lifecycle. Use the repository's worktree/branch rules. The common procedure does not choose a harness branch prefix.

Completion

Report the spec path/URL, scope, decisions and any blocked publication capability. A local draft is not a published issue. Under issue-based SDD, link final delivery with Closes #N, partial delivery with Part of #N, and reconcile Plan progress only after landing. If the repository has no spec gate, do not impose one.

Optional helpers

The list helper and show helper are optional CLI conveniences requiring authenticated GitHub CLI and jq. Use connected GitHub tools instead when those prerequisites are unavailable.

FAQ

What does the issue-spec skill do?

Create or revise a focused specification issue when explicitly requested or required by the repository contribution policy. Discover existing work, capture intent and acceptance criteria, and reconcile decisions before implementation.

How do I install issue-spec?

Run npx skills add https://github.com/onsager-ai/dev-skills --skill issue-spec in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/issue-spec/ (personal) or .claude/skills/issue-spec/ (project).

Which AI agents can use issue-spec?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is issue-spec safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains issue-spec?

It is published by onsager-ai in onsager-ai/dev-skills. It has 61 recorded installs.

More from onsager-ai/dev-skills

View all →

codegraph

onsager-ai/dev-skills

Pre-indexed code knowledge graph (MCP, SQLite + tree-sitter) for faster, lower-token exploration of brownfield codebases. Use when starting work on a repo larger than 500 files or when the task involves cross-file traversal — "where is X used", "what calls Y", "what breaks if I change Z", "trace flow from A to B", "explain this subsystem". Skip for single-file edits or sessions shorter than the cold-start cost. Triggers include "codegraph", "code graph", "index this repo", "where is X defined", "find callers of", "callees of", "blast radius of changing X", "explore this codebase". Cuts the grep + Read loops needed to orient, via O(1) SQLite lookups and FTS5 search over 8 MCP tools — but it's an unsound tree-sitter approximation, so grep stays the completeness backstop for renames/exhaustive callers.

Data & Databases819 installs

github-integration

onsager-ai/dev-skills

Open the skill to read its SKILL.md instructions.

66 installs

git-commit

onsager-ai/dev-skills

Best practices for creating clean, atomic git commits with good messages. Use when: (1) staging and committing changes, (2) writing commit messages, (3) deciding what to group in a single commit, (4) handling pre-commit hook failures, (5) choosing between amend and new commit. Triggers on "commit", "stage", "git add", "write a commit message", or "commit my changes".

web-testing

onsager-ai/dev-skills

Open the skill to read its SKILL.md instructions.

Testing & QA61 installs

agent-browser

onsager-ai/dev-skills

Open the skill to read its SKILL.md instructions.

plan-dag

onsager-ai/dev-skills

Open the skill to read its SKILL.md instructions.

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.