mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
65fcae6cda
Rewrite README.md Installation prose and references/skill-triggers.md to drop the bundles/ depth and --full-depth guidance, relabel the architecture diagram bundle node, and correct bundle-manifest-design.md to place manifests at <skill>/manifest.yaml with the 8-umbrella count. Fix the example manifest and schema descriptions, plus the production-excellence AGENTS.md depth note. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
1.5 KiB
1.5 KiB
Failure-Mode-to-Skill Index
Use this index when the work is blocked by a recognizable failure pattern rather than a named technology. Load the most specific skill first.
| Failure mode | Signals | Load |
|---|---|---|
| The premise may be wrong | A plausible explanation has not been checked against source or live output | systematic-debugging |
| A tool or API may be missing | You are about to build a workaround without checking the native capability | agent-skills, then the domain skill |
| Work keeps escalating | Two materially different approaches failed | systematic-debugging |
| A multi-agent decision is converging too early | One perspective appears sufficient but alternatives have not been tested | agent-council |
| A contribution may duplicate existing work | The requested feature sounds like something already in the repository | opensource-contributions |
| A workflow is repeated manually | The same sequence of skills is executed more than once | workflow-architect |
| Meaning drifts or disagrees between agents | Agents use the same word for different meanings, or semantic divergence and dead-ends block progress | semantic-spacetime |
This is a routing aid, not a replacement for reading the selected skill. Add a row only when the failure mode has a concrete trigger and an existing skill that addresses it.