القائمة
Run a monthly B+ competitor-discovery radar for spec-driven and agent-workflow tools, render JSON-governed reports, grill suggested gzkit moves, and route approved opportunities without unattended governance mutation.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Validate and stage a candidate rendition from the corpus via gz content compose. Use when the agent has made compression decisions (drop/combine/rewrite of compressible corpus entries toward the declared setpoint) and wants the tool to validate invariant-floor compliance, compute byte evidence, write the candidate artifact, and emit a ledger event.
Enter and exit the MX Maintenance Hangar — operator's interface to gz mx. Use when entering the hangar to perform governance repair, checking hangar status mid-session, or cleanly exiting when repair is complete. Operator operates the skill; the skill invokes gz mx; nobody shells out.
Create and resume session handoff documents for agent context preservation across engineering sessions.
Create and resume session handoff documents for agent context preservation across engineering sessions.
Collaborative design dialogue that produces GovZero ADR artifacts. Use when exploring a new feature, capability, or architectural change before implementation — replaces superpowers brainstorming for this project. Triggers on "design X", "let's design", "brainstorm X", "I want to build X", "gz-design".
Cross the airlock membrane — the entry/exit gate every unit of work passes through (ADR-0.33.0). Use to inspect a target's seam-map before touching it (`gz airlock in`), account for what a transit disturbed (`gz airlock out`), or make a governed ad-hoc reconnaissance entry with light repair at most (`gz permitted-entry`). Diagnostic-only for now — a staged posture, not the declared end state; never writes L1 canon.
| name | gz-competitor-radar |
| description | Run a monthly B+ competitor-discovery radar for spec-driven and agent-workflow tools, render JSON-governed reports, grill suggested gzkit moves, and route approved opportunities without unattended governance mutation. |
| compatibility | Project-local skill contract. |
| category | agent-operations |
| metadata | {"skill-version":"1.0.1","govzero-framework-version":"v6","govzero-author":"gzkit-governance","govzero_layer":"Layer 1 - Evidence Gathering"} |
| lifecycle_state | active |
| owner | gzkit-governance |
| last_reviewed | "2026-07-25T00:00:00.000Z" |
| model | opus |
Monthly competitor radar for spec-driven development, agent skills, executable spec ecosystems, and adjacent workflow tools.
artifacts/reports/competitor-radar/registry.json and
monthly scan JSON files govern the Markdown. Markdown reports under
artifacts/reports/competitor-radar/ are generated projections and must not
be hand-edited.scripts/, per Agent Skills packaging guidance.Refresh sources. Browse current official sources first: project homepage, repository, docs, release notes, marketplace entry, and credible radar-style commentary. Do not rely on memory.
Update scan JSON. Write findings to
artifacts/reports/competitor-radar/scans/YYYY-MM.json. The agent authors
this JSON from evidence and from grill answers. The operator does not edit
JSON or Markdown.
Render reports.
uv run python .gzkit/skills/gz-competitor-radar/scripts/radar.py render
Validate JSON and generated Markdown.
uv run python .gzkit/skills/gz-competitor-radar/scripts/radar.py validate
Open the grill discussion. For each suggested move, ask one question at a time, recommend an answer, and walk the decision tree. Record answers back into the scan JSON, rerender, and revalidate.
Route only after decisions. Approved outcomes may update pool ADRs, file GHIs, or start design/promotion work. Rejections are recorded explicitly.
For every suggested move, ask:
Ask one question at a time. Prefer a recommended answer with tradeoffs. If the answer is discoverable from repo state or source evidence, gather it instead of asking the operator to type it.
All scripts are stdlib Python and portable with the skill:
uv run python .gzkit/skills/gz-competitor-radar/scripts/new_scan.py --month YYYY-MM
uv run python .gzkit/skills/gz-competitor-radar/scripts/render_report.py
uv run python .gzkit/skills/gz-competitor-radar/scripts/validate_registry.py
uv run python .gzkit/skills/gz-competitor-radar/scripts/validate_report.py
The wrapper scripts delegate to scripts/radar.py.
Registry source:
artifacts/reports/competitor-radar/registry.json
Monthly scan source:
artifacts/reports/competitor-radar/scans/YYYY-MM.json
Generated reports:
artifacts/reports/competitor-radar/index.md
artifacts/reports/competitor-radar/YYYY-MM.md
Validation compares rendered Markdown byte-for-byte against the JSON source. If the Markdown differs, edit the JSON or the renderer, rerender, and revalidate.
references/registry.schema.json — registry shape.references/scan.schema.json — monthly scan shape.references/report-template.md — report section contract.references/grill-questions.md — grill question bank.gz-designgz-adr-evaluategz-justifyghi-authorgz-agent-sync