scout-rivals

Solid

Use 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.

AI & Automation 6 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 78/100

Stars 20%
28
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# scout-rivals — date-anchored rival intelligence One invocation = one **delta scout**: what changed in the rival landscape since the last scout, judged through Muse's identity lens, delivered as ledger fuel for the building skills. This skill NEVER builds product code — its ship is the intelligence itself. The exhaustive base already exists: the 2026-06-23 teardown (`docs/goals/competitor-teardown.md`, 420 files → 231 judged opportunities in `growth-backlog.md` + `judgment-lens.md`). Re-deriving that ground is the documented waste this skill exists to prevent — scout the DELTA, never the base. ## The cycle 1. **ANCHOR** — run `date` (never assume); read the watermark block at the top of `docs/goals/rival-watch.md` (last scout date, per-repo upstream SHAs, roster + reference shelf). `git -C /Users/jinan/ai/<name> fetch origin` EVERY roster and shelf clone now — the fire reads today's upstream, never a stale checkout. Everything below is scoped to changes AFTER the watermark. 2. **SWEEP (delta only, verify-in-code)** — - **Named rivals** (roster in rival-watch.md carries repo URLs, SHAs, and the persistent local clones under `/Users/jinan/ai/<name>` — `git -C` fetch them, never re-clone; a NEW roster member gets a blobless clone there). High-velocity repos ship thousands of commits per window — sweep RELEASES + CHANGELOG first (observed fire 1: 7.8k commits in 3.5 weeks; raw log is for locating an implementing file, never th...

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

AI & Automation Listed

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.

7 Updated yesterday
duthaho
AI & Automation Listed

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.

0 Updated 2 days ago
BenMacDeezy
Web & Frontend Listed

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.

0 Updated 3 days ago
zakariaf