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>
a315b77bd8
Re-point relative references inside the six non-tailscale/workflow-architect
bundle dirs now that they live one level shallower at the repo root:
- bundle-root SKILL.md/manifest.yaml/README.md: ../../<target> -> ../<target>,
cross-bundle ../../bundles/<x> -> ../<x>
- forward-deployed-engineering references/: ../../../<target> -> ../../<target>
- product-lifecycle references cross-bundle ../../bundles/neckbeard -> ../../neckbeard
- product-lifecycle references/discovery-brief.md prose headings drop bundles/ prefix
- neckbeard eval shell commands bundles/neckbeard/eval -> neckbeard/eval
- production-excellence AGENTS.md depth note updated
- manifest header comments point at ../schemas/bundle-manifest-v1.schema.json
- regenerate docs/lifecycle-capability-matrix.{md,json}
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
68 lines
2.1 KiB
YAML
68 lines
2.1 KiB
YAML
# Bundle manifest (bundle-manifest-v1) — see ../schemas/bundle-manifest-v1.schema.json
|
|
# and docs/bundle-manifest-design.md. Paths are relative to this bundle dir.
|
|
|
|
schema_version: 1
|
|
bundle_name: research-and-vault
|
|
|
|
purpose: >-
|
|
Chain web research, atomic extraction, and durable knowledge capture into a
|
|
repeatable research-to-note workflow: capture source URLs and dates before
|
|
interpretation, extract independent atomic claims before synthesis, and write
|
|
the durable note only after source coverage and gaps are explicit.
|
|
|
|
audience: >-
|
|
Agents and knowledge workers that repeatedly need the full research-to-note
|
|
sequence (web research, atomic extraction, durable capture) and want a stable
|
|
order of operations with a clear handoff artifact instead of ad-hoc steps;
|
|
not for single lookups or single notes, which route to the domain skill
|
|
directly.
|
|
|
|
stages:
|
|
- name: Web research
|
|
skills:
|
|
- ../research-methodology/SKILL.md
|
|
- name: Source capture
|
|
skills:
|
|
- ../research-methodology/SKILL.md
|
|
- name: Atomic extraction
|
|
skills:
|
|
- ../research-methodology/SKILL.md
|
|
- name: Synthesis and durable capture
|
|
skills:
|
|
- ../research-methodology/SKILL.md
|
|
|
|
included_skills:
|
|
- ../research-methodology/SKILL.md
|
|
|
|
prerequisites:
|
|
- artifact: A research question or topic and access to web-research tooling
|
|
skill: ../research-methodology/SKILL.md
|
|
|
|
outputs:
|
|
- source-capture-record
|
|
- atomic-claim-extract
|
|
- durable-note
|
|
|
|
handoffs:
|
|
- to: research-methodology
|
|
artifact: source-capture-record
|
|
note: >-
|
|
Source URLs and dates are captured before interpretation and carried into
|
|
extraction and synthesis; never interpret a source before its URL and
|
|
date are recorded.
|
|
- to: research-methodology
|
|
artifact: atomic-claim-extract
|
|
note: >-
|
|
Independent atomic claims are extracted before synthesis so the durable
|
|
note can trace each claim to its source.
|
|
- to: user
|
|
artifact: durable-note
|
|
note: >-
|
|
The finished durable note reports its output path and any unresolved gaps
|
|
in source coverage.
|
|
|
|
conflicts: []
|
|
|
|
eval_suite:
|
|
- evals/evals.json
|