Menu
Create a metadata-complete AgentOps skill
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/boshu2/agentops --skill skill-builderThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Use Agent Mail as an optional messaging and file-reservation adapter for explicitly coordinated writers. Triggers: "coordinate writers", "reserve files".
Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".
Initialize minimal AgentOps documentation and verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".
Showing SKILL.md
Based on SOC occupation classification
| name | skill-builder |
| description | Create a metadata-complete AgentOps skill |
skill-builder owns the full structural lifecycle of one skills/<slug>/
source package: create it, verify its structure, repair owned projections, and
audit its content discipline. It does not schedule work, allocate writers,
operate Git, validate a software candidate, promote learnings, or decide what
happens after a failure.
Before creating a new root, search skills/*/SKILL.md for an existing owner.
Extend an existing skill when it already owns the requested behavior.
| Trigger phrases | Mode | Entry point |
|---|---|---|
| "create a skill", "scaffold skill", "new skill" | create (build) | scripts/build.sh |
| "absorb external skill" | create (absorb-external) | scripts/build.sh |
| "check skill package" | check | scripts/heal.sh --check [--strict] |
| "heal skill", "repair skill hygiene" | heal | scripts/heal.sh --fix |
| "audit skill structure" | audit | scripts/audit.sh |
Choose exactly one build input:
from-scratch <slug> creates a blank source package.from-template <slug> --like <existing-slug> uses the existing skill only
for metadata defaults; it does not copy its prose.absorb-external <slug> --from <path> verifies the source exists, then
creates a clean-room blank package without copying names, prose, prompts,
scripts, or examples.The caller may set SKILL_TIER, SKILL_DEPENDENCIES,
SKILL_CAPABILITIES, and SKILL_EFFECTS. Values that represent lists must be
JSON arrays.
scripts/build.sh with one mode and one new slug.scripts/heal.sh --check --strict skills/<slug>.scripts/generate-skill-mesh.py to derive the catalog, registry,
router, graph, maps, counts, and runtime image manifests from SKILL.md
metadata.scripts/codex-sync.sh --only <slug> and
scripts/regen-codex-hashes.sh --only <slug> to derive the Codex twin.build.sh performs steps 1, 3, 4, and 5 once. It never retries or chooses a
next action.
bash skills/skill-builder/scripts/heal.sh --check [skills/<slug> ...]
bash skills/skill-builder/scripts/heal.sh --check --strict [skills/<slug> ...]
bash skills/skill-builder/scripts/heal.sh --fix [skills/<slug> ...]
Every explicit target must be a real, direct child of skills/ or
skills-codex/. Missing paths, traversal, and symlink spellings are rejected.
SKILL.md frontmatter.--fix mode only, regenerate metadata-owned projections and scoped Codex
twins, then stop.--check is read-only. --strict makes any finding produce exit 1. A failed
fix is returned to the caller; the skill does not retry or select another
action. Structural findings are printed as:
[FINDING_CODE] skills/example: concrete explanation
Generated Codex parity follows codex-parity.md. A second identical fix is idempotent, and remaining non-fixable findings stay explicit.
The optional read-only deep content audit is:
bash skills/skill-builder/scripts/audit.sh [--strict] [--json <path>] skills/<slug>
It combines the structural result with deterministic authoring checks and an
advisory quality score. It is not the core Validate phase, does not write a
verdict.v2, and has no delivery authority. Check definitions live in
audit-checks.md; density scoring is described in
context-density-checks.md.
A created source package contains:
skills/<slug>/
├── SKILL.md
└── scripts/validate.sh
The build report is .agents/scratch/skill-builder/<slug>-build.json and
conforms to schemas/build-report.json. Deep audit JSON conforms to
schemas/audit-report.json. Generated inventories and runtime projections are
not additional sources of truth. The caller owns any subsequent edit or
invocation.
name match.tier, dependencies, capabilities, effects,
canonical_status, and disposition.Any invalid input, structural failure, projection failure, or Codex sync failure exits nonzero after one attempt. The caller decides whether to revise or invoke the builder again.
authoring audit block