Index of every page on this site: llms.txt
All skills
multica-ai avatar

/multica-working-on-issues

@bac9e5b
by Multicamultica-ai/multica57k stars
7,479
Run it yourself

Superseded by the multica-platform skill — load that instead. This file only records where the Multica issue contracts moved to.

Use this Skill: https://skilld.dev/gh/multica-ai/multica/multica-working-on-issues

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈39 tokens for metadata: the name and description. ≈303 when used: this file.

Description uses 1.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈156 characters, or 1.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Moved into multica-platform

Multica's platform contracts are now one skill. Everything this skill used to carry — PR linking vs close intent, reading a linked PR's real state, custom properties, status side effects, sub-issues and stages, and finding who else is running — lives in:

multica-platform  →  references/issues.md

Load the multica-platform skill and open that file. Its routing table also names the reference for every other platform domain: mentions, agents, squads, autopilots, projects, runtimes, and skill import.

The contracts were reorganized, not shortened — with one exception. The issue metadata guidance was retired (MUL-6966), so a brief that sends you here for it points at something that is no longer there. What replaces it: durable state a person should see and filter by goes on a custom property, the stage the issue is at goes in its status, and everything else — what you did this run, what you found — goes in the result comment.

You are seeing this redirect because the Multica app on this machine is older than the server it is talking to, so its task brief still refers to the previous skill name. Updating the app removes this extra hop.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill is a simple redirect notice informing the user that its functionality has been moved to a different skill ('multica-platform'). It contains no executable code or malicious instructions.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at bac9e5b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
What it can do
Runs commands
user-invocable
false
All 1 allowed tools
Bash(multica *)

README badge

README badge for multica-ai/multica/multica-working-on-issues