skilld
All skills
aktsmm avatar

/retro-private-skills

@c44a6cc
by yamapanaktsmm/agent-skills26 stars
4

Reflect reusable learnings into a private Agent Skills repository with scoped safety gates and same-run private commit/push. Use when: skill retro, private skill authoring, skill repository fix, create or update SKILL.md.

Ask your Agent

Use this Skill: https://skilld.dev/gh/aktsmm/agent-skills/retro-private-skills

This session only. Nothing lands on disk.

referencesintake-workflow.md

≈313 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Private Skill Intake Workflow

Intake mechanically mirrors local Copilot skills into the private repository before optional curation. Run it only when the user explicitly asks to intake, import, or refresh local copies.

Request Action
Intake and improve Mirror first, then run normal retro authoring
Intake only Mirror and stop before curation
Normal private-skill retro Skip intake

Run <private-repo>/scripts/Sync-CopilotSkillsToPrivateRepo.ps1. It mirrors local skill sources into separate copilot-skills/skills/ and copilot-skills/m-skills/ trees and regenerates the mirror README.

This pre-step alone may write under <private-repo>/copilot-skills/**. Curated authoring remains limited to .github/skills/<skill>/. Never mix mirror output and curated edits in the same target tree.

Before mirroring, check whether .github/skills/<skill>/ already contains a curated skill with the same name. Stop and ask for an explicit coexistence or rename decision instead of creating an ambiguous raw duplicate.

Source: SKILL.md on GitHub

Third-party checks

1 warning22d3 checks · Risk MEDIUM
  • Gen Agent Trust Hub22d

    This skill automates the maintenance of a private AI agent skill repository by reflecting learnings from development artifacts like logs and diffs into documentation. Security analysis identified that the skill performs automated Git operations—including committing and pushing changes—and executes local PowerShell scripts for synchronization tasks. It also ingests external data (logs, history) that could potentially contain instructions aimed at influencing the agent's long-term behavior.

  • Socket22d

    No alerts

  • Snyk22d

    Risk: LOW · No issues

Provenance

Signed by skilld at c44a6cc. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday

Capability

argument-hint
反映したい学び、対象 skill 名、private repo path、mode（safe-auto / review-only / dry-run）
user-invocable
true
metadata
{
  "author": "yamapan (https://github.com/aktsmm)"
}

README badge

README badge for aktsmm/agent-skills/retro-private-skills