scout-rivals
SolidUse when the owner wants to know how Muse compares to the open-source agent landscape RIGHT NOW — what openclaw, hermes-agent, and other notable open-source agents shipped recently, what Muse lacks, or when the parity reservoir feels stale; also as the per-fire entrypoint of a rival-watch loop. Produces judged intelligence only — building belongs to grow-muse/improve-muse.
Install
Quality Score: 78/100
Skill Content
Details
- Author
- wlsdks
- Repository
- wlsdks/muse-agent
- Created
- 2 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
scout
Competitive reconnaissance for your project — what do the repos solving this same problem do better, and what's worth adopting? Finds peer repos (ranked by activity, downloads, dependents — never raw stars), mines what their users beg for — issue reactions, releases, docs claims, every finding with a locator — and verdicts each candidate feature ADOPT/ADAPT/SKIP/WATCH, where SKIP is the default and "a competitor has it" is never a reason. ADOPT items become ready seeds for feature or autopilot; verdicts persist in out/scout/tracker.md so repeat runs open with what changed. Keyless. Use for "what are similar projects doing", "compare us to X", "what are we missing" — e.g. "/scout", "/scout <owner/repo>", "/scout deep <repo>". For X-vs-Y tech choices use verdict; for community buzz use pulse.
scout
Discover and vet skills, MCP servers, CLIs, and reference repos for the current project. Use on onboard, on /forge:scout, when the user asks what tools/MCPs/skills would help this project, or when the kernel hits a capability gap. Produces a vetted, ranked shortlist for human approval — never installs anything.
hyperbuild-2-market-recon
Step 2 of the hyperbuild pipeline — competitor recon. Spawns ONE hb-competitor-scout to discover and rank the competitor set, then a parallel wave of hb-competitor-analyst subagents (one per curated competitor: 6–8 standard, 12–15 premier) that each write a dossier to research/01-product-and-market/research/competitors/<slug>.md in the docs/RESEARCH-ARCHIVE.md research-file format (H3 claims written as complete assertions) covering latest version, feature set, changelog cadence, pricing, and store ratings. The orchestrator then registers those claims in runs/<run_tag>/temp/claims-01.json and merges the dossiers into research/01-product-and-market/author/competitor-landscape.md with a feature matrix. Runs concurrently with step 3 as the 2 ∥ 3 pair; step 3.5 audits these artifacts before step 4 builds the PRD on them. Invoked by the hyperbuild router via Skill(); not run directly by users.