agentleFS
albertomartureloalbertomarturelo/sii/.agents/skills/issue-new/SKILL.md

issue-new

Skill19 starsChanged 7 days agoMITView on GitHub

Create a self-sufficient GitHub issue on albertomarturelo/sii with the fixed 6-section CFD body. Invoke explicitly when a new unit of work needs an issue.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. jarimustonen/reitti-cli★ 1same name
    2. jarimustonen/project-canon★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask, in order, and confirm each answer before moving on:

    line 12
  2. Very specific:

    Reproduction steps: ONLY for fix. Minimal repro to confirm the bug (state whether the session was cached or fresh for SII bugs).

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Guide the user through creating a new GitHub issue on albertomarturelo/sii using the fixed 6-section body template. Ask, in order, and confirm each answer before moving on:

  1. Type. feature | fix | chore | docs | spike
  2. Title. Imperative mood, ≤80 chars, English. e.g. "Add rut parser + Mod-11 DV to @albertomarturelo/sii-core".
  3. Context. 2–4 sentences: what is the trigger, what is the user-visible outcome.
  4. Target location. Concrete paths. For net-new, name the package + file (e.g. packages/core/src/rut.ts — new file). For a new SII surface, read the « Where a new surface goes » table in docs/ROADMAP.md first (loaded on demand, ADR-033).
  5. Reference pattern. An existing file/module to mirror in shape, naming, and conventions. Skip ONLY if no analog exists; flag it.
  6. ADRs to load. ADR numbers the agent must read before starting. At minimum the architectural ones the change touches: ADR-003 for anything crossing the core boundary / ports, ADR-004 for any SII domain code, ADR-005 for identity/operate, ADR-006 for auth. If a needed decision isn't an ADR yet, STOP and run /new-decision first.
  7. Acceptance criteria (DoD). Bulleted markdown [ ] items. Include all three of:
    • Behavior — what works at the end (concrete CLI/MCP/plugin output or @albertomarturelo/sii-core API).
    • Tests — what tests exist (<module>.test.ts, vitest); state explicitly that fixtures are synthetic (no real PII).
    • Documentation — which of CONVENTIONS.md, conventions/sii-wire.md, STACK.md, ARCHITECTURE.md, ROADMAP.md, a sii-contract/*.md, or a new ADR is updated.
  8. Reproduction steps. ONLY for fix. Minimal repro to confirm the bug (state whether the session was cached or fresh for SII bugs).
  9. Estimated sessions. 1 | 2–3 | 4+. If > 1, propose decomposition into sub-issues before continuing.
  10. Labels. Type label + scope labels (core, cli, mcp, auth, portal, identity, docs, tests).

Then generate the body using the fixed template (do NOT deviate from section order or names — /issue-start parses by section header):

## Context
<step 3>

## Target
- Files / dirs: <step 4>
- Pattern to mirror: <step 5>

## ADRs to load
- ADR-NNN

## Acceptance criteria
- [ ] <step 7>

## Reproduction (fixes only)
<step 8 — OR omit this section entirely if not a fix>

## Estimated sessions
<step 9>

Then run:

gh issue create --repo albertomarturelo/sii \
  --title "<step 2>" --body "<body above>" \
  --label "<step 1>,<step 10 scopes>"

Output the issue URL when done. English only.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.