Agent skill

Meta Issue Creation

by cipherstash in cipherstash/stack

How an agent files a GitHub issue on cipherstash repos — required structure (Background / Problem / Proposal), dumbed-down wording rules, and pre-filing checks.

MITAuto-check passedDatabases

Install Meta Issue Creation

skills CLI
$ npx skills add cipherstash/stack --skill meta-issue-creation -a claude-code

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

GitHub CLI
$ gh skill install cipherstash/stack meta-issue-creation --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/cipherstash/stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/meta-issue-creation .claude/skills/meta-issue-creation && 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
meta-issue-creation
GitHub stars
157
Token cost
~1k tokens
SKILL.md length
524 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

How an agent files a GitHub issue on cipherstash repos — required structure (Background / Problem / Proposal), dumbed-down wording rules, and pre-filing checks.

  • Works in 3 steps: Search for existing coverage — open and… → Verify every mechanical claim against… → Pick the right repo. A problem caused…
  • Filing an issue on this repo
  • SKILL.md covers Before filing anything, Structure, Wording and Mechanics
  • Calls gh

What it does

Meta Issue Creation is an agent skill from cipherstash/stack. How an agent files a GitHub issue on cipherstash repos — required structure (Background / Problem / Proposal), dumbed-down wording rules, and pre-filing checks. Use whenever drafting or filing an issue on this repo or a sibling CipherStash repo (encrypt-query-language, protectjs-ffi, …).

Its SKILL.md is about 1k 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 Databases. It works with GitHub, Prisma and PostgreSQL. The repository describes itself as: Searchable, application-level encryption for building privacy-first apps. The licence is MIT.

When your agent uses it

  • Filing an issue on this repo
  • A sibling CipherStash repo (encrypt-query-language

Example prompts

  • “/meta-issue-creation”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Search for existing coverage — open and closed, this repo and the
  2. Verify every mechanical claim against code or the installed package
  3. Pick the right repo. A problem caused upstream (EQL SQL, prisma-next,

What it can do on your machine

Read from SKILL.md and the folder at commit 415b62c. 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:

    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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

Meta Issue Creation loads about 1k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 524 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 cipherstash/stack at commit 415b62c, republished under its MIT licence (© cipherstash). 524 words, ~1,024 tokens.

Download SKILL.mdSave it as .claude/skills/meta-issue-creation/SKILL.md (or your agent's skills folder).
name
meta-issue-creation
description
How an agent files a GitHub issue on cipherstash repos — required structure (Background / Problem / Proposal), dumbed-down wording rules, and pre-filing checks. Use whenever drafting or filing an issue on this repo or a sibling CipherStash repo (encrypt-query-language, protectjs-ffi, …).

Filing issues as an agent

These are internal skills for agents working on CipherStash repos. They are deliberately outside skills/ — everything in that directory ships to customers inside the stash tarball; nothing in .claude/skills/ does.

Before filing anything

  1. Search for existing coverage — open and closed, this repo and the sibling repo the problem might belong to:

    bash
    gh search issues --repo cipherstash/stack "<term>" --limit 30 --json number,title,state

    A closed issue that covers your problem is a finding, not a dead end — check why it closed (linked PR? shipped artifact? silent close?) before filing a duplicate. Reopening with a comment often beats a new issue.

  2. Verify every mechanical claim against code or the installed package before asserting it. Cite file:line. Separate what you verified from what is plausible — say which is which in the issue.

  3. Pick the right repo. A problem caused upstream (EQL SQL, prisma-next, protect-ffi) gets its issue upstream, with a consumer-impact issue here only if this repo needs its own mitigation. Cross-reference with the full owner/repo#N form so links work from both sides.

Structure

Required sections, in this order:

  • Background — orient a reader who is new to CipherStash, stack, and EQL. One short paragraph: what the relevant piece does and why it exists. Define every product term and acronym at first use ("EQL — the SQL library we install into the customer's database as the eql_v3 schema").
  • Problem — the mechanism (what actually happens, step by step), then the impact (who hits it, when, how often), then why nothing catches it today. A concrete failure narrative beats an abstraction: "queries slow from instant to scan-every-row, silently" — not "performance degradation may occur".
  • Proposal — numbered, concrete steps. If the full fix is large, include a cheap interim step that could ship first. State the failure behaviour you want ("fail loudly listing the statements — a loud failure beats a silent deletion").

Optional sections, when they earn their place:

  • Affected versions — when the problem is version-bounded.
  • Evidence / Verification — commands run, output observed, file:line.
  • Relationship to other work — links to sibling issues, and what each one does/doesn't cover. After filing, leave a short cross-link comment on the related issues pointing back — links must work in both directions or one side is never found.
Show full SKILL.md (164 more words)Show less

Wording

Dumbed down, always. Assume the reader joined yesterday:

  • Short sentences. Plain verbs. No internal shorthand or codenames.
  • Every acronym expanded at first use, even "obvious" ones (EQL, ZeroKMS, PSL).
  • Say what breaks in the user's world, not just in the code's world.
  • Titles are symptom-first and name the command or package: `stash eql upgrade` silently deletes search indexes — save and restore them beats "Improve EQL upgrade robustness".
  • Write #N only for a real GitHub issue or PR reference — GitHub autolinks every #N, so "step #2 of the plan" mints a bogus link to issue 2. Write "step 2", "item 3" instead.
  • Never reference internal Linear issues (CIP-… numbers) anywhere on GitHub — issues, PRs, comments, commit messages. GitHub is public; Linear is not. GitHub refs are fine.

Mechanics

  • gh issue create --repo cipherstash/<repo> --title '…' --label <label> --body "…".
  • Reuse existing labels (enhancement, bug, SDK, …) — check with gh label list rather than inventing new ones.
  • Sibling skill: meta-pr-creation for the PR that eventually closes the issue.

© cipherstash, MIT. 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/meta-issue-creation of cipherstash/stack.

Open the folder on GitHubat commit 415b62c

Compare with similar skills

Meta Issue Creation 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.

Meta Issue Creation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meta Issue Creation this skillcipherstash/stack157—~1kAutomated safety check: PassMIT
Better Drizzlealmeidazs/better-drizzle347—~1.7kAutomated safety check: PassApache-2.0
Prisma Database Setupcurvenote/curvenote1693 repos~1.4kAutomated safety check: PassMIT
Add Backendahpxex/open-dashboard146—~3.6kAutomated safety check: PassMIT
Mfs Findzilliztech/mfs150—~4kAutomated safety check: PassApache-2.0
Releaserogerpadilla/uql125—~842Automated safety check: PassMIT

Similar skills

  • Better Drizzle

    almeidazs/better-drizzle

    Write, review, and debug code that uses better-drizzle, the typed repository layer over Drizzle ORM 1.x (better(db), client.users.findMany, paginate, cursor, upsertMany, relation include/connect…

    347 GitHub stars~1.7k tokensUpdated 2 days ago
    DatabasesAuto-check passed
  • Prisma Database Setup

    curvenote/curvenote

    Guides for configuring Prisma with different database providers (PostgreSQL, MySQL, SQLite, MongoDB, etc.).

    169 GitHub starsUsed in 3 repos~1.4k tokens
    DatabasesAuto-check passed
  • Add Backend

    ahpxex/open-dashboard

    Everything about the data layer — pick one of six ready-to-run backend templates (TanStack Start + Drizzle + better-auth, Hono + Drizzle + better-auth, Hono + Prisma + better-auth, Hono + Drizzle +…

    146 GitHub stars~3.6k tokensUpdated 3 mo ago
    DatabasesAuto-check passed
  • Mfs Find

    zilliztech/mfs

    Search, grep, browse, and read across registered MFS data sources via the mfs CLI — codebases, docs, PDFs, web crawls, databases (postgres/mysql/mongo/snowflake/bigquery), issue trackers…

    150 GitHub stars~4k tokensUpdated 2 mo ago
    DatabasesAuto-check passed
  • Release

    rogerpadilla/uql

    Cut and publish a uql release - review the change, changelog entry, commit, version bump and tag, GitHub Release, npm publish, docs site.

    125 GitHub stars~842 tokensUpdated today
    DatabasesAuto-check passed
  • Database Fundamentals

    DanielPodolsky/ownyourcode

    Reviews schema design, SQL queries, ORM patterns. An agent skill from DanielPodolsky/ownyourcode.

    290 GitHub starsUsed in 1 repo~1.6k tokens
    DatabasesAuto-check passed

More from cipherstash/stack

All 14 skills in this repo
  • Meta PR Creation

    cipherstash/stack

    How an agent authors branches, commits, and pull requests on cipherstash/stack — naming, signed commits, the changeset/skills/meta-file checklist, and PR body structure with dumbed-down wording.

    157 GitHub stars~937 tokensUpdated today
    Auto-check passed
  • Stash Zerokms

    cipherstash/stack

    The ZeroKMS key model — keysets, clients, client keys, and the grant/revoke lifecycle.

    157 GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Stash Deployment

    cipherstash/stack

    Deploy a CipherStash encryption rollout to a live environment without losing data — the multi-deploy ladder (schema-add + dual-write → backfill → read cutover → stop dual-writes → drop plaintext)…

    157 GitHub stars~6.5k tokensUpdated today
    Auto-check passed
  • Supply-chain security controls for the @cipherstash/stack monorepo.

    157 GitHub stars~5.2k tokensUpdated today
    Auto-check: warnings
  • Stash Drizzle

    cipherstash/stack

    Integrate CipherStash encryption with Drizzle ORM using @cipherstash/stack-drizzle (EQL v3).

    157 GitHub stars~10k tokensUpdated today
    Auto-check: notes
  • Stash Edge

    cipherstash/stack

    Run CipherStash encryption on edge and non-Node runtimes with the @cipherstash/stack/wasm-inline entry — Deno, Supabase Edge Functions, Cloudflare Workers, and Bun.

    157 GitHub stars~6.4k tokensUpdated today
    Auto-check: notes

Categories

Questions about Meta Issue Creation

What does Meta Issue Creation do?

How an agent files a GitHub issue on cipherstash repos — required structure (Background / Problem / Proposal), dumbed-down wording rules, and pre-filing checks. Meta Issue Creation is an agent skill from cipherstash/stack. How an agent files a GitHub issue on cipherstash repos — required structure (Background / Problem / Proposal), dumbed-down wording rules, and pre-filing checks.

When should I use Meta Issue Creation?

Meta Issue Creation fits situations like: filing an issue on this repo; A sibling CipherStash repo (encrypt-query-language.

How do I install Meta Issue Creation in Claude Code?

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

How do I install Meta Issue Creation in Codex?

Run `npx skills add cipherstash/stack --skill meta-issue-creation -a codex`. Or copy the skill folder (.claude/skills/meta-issue-creation in cipherstash/stack) into .agents/skills/meta-issue-creation in your project. Codex loads it when a task matches its description.

Can I use Meta Issue Creation 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 cipherstash/stack --skill meta-issue-creation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meta-issue-creation, .gemini/skills/meta-issue-creation, .github/skills/meta-issue-creation and .opencode/skills/meta-issue-creation in your project.

What does Meta Issue Creation need to run?

Going by SKILL.md and its folder, Meta Issue Creation needs the command-line tools its instructions call (gh).

Does Meta Issue Creation access the network?

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

Is Meta Issue Creation 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 Meta Issue Creation use?

Meta Issue Creation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meta Issue Creation use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Meta Issue Creation?

Skills that share tags, products or a category with Meta Issue Creation: Better Drizzle (almeidazs/better-drizzle, 347 stars), Prisma Database Setup (curvenote/curvenote, 169 stars), Add Backend (ahpxex/open-dashboard, 146 stars) and Mfs Find (zilliztech/mfs, 150 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meta Issue Creation?

cipherstash (a GitHub organization) maintains it in cipherstash/stack, which has 157 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

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