topic-radar
Aggregate read-only AI and technology trend signals (Polymarket, Hacker News, GitHub, arXiv, Hugging Face, news search) into source-grounded Markdown or JSON; the lower-level data engine behind `daily-brief`.
- License 许可
- MIT
- 最近更新
- 2026-08-29
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- topic-radar
- description
- Aggregate read-only AI and technology trend signals (Polymarket, Hacker News, GitHub, arXiv, Hugging Face, news search) into source-grounded Markdown or JSON; the lower-level data engine behind `daily-brief`.
02 资源文件 3
- 脚本bin/topic_radar.py85.5 KB
- 参考文档references/source-strategy.md5.7 KB
- 脚本scripts/topic-radar.sh206 B
03 SKILL.md 正文
Topic Radar
Contract
Prereqs:
- Python 3.11 or newer is available on
PATH(used by the bundledtopic_radar.pyscript, which is stdlib-only). - Network access for live lookups.
- Optional upstreams may rate-limit anonymous requests; the skill must degrade per-source instead of failing the whole digest.
- Polymarket source support prefers read-only MCP tool output when available; otherwise the bundled
polymarket-readonlyfallback (when the domain is installed alongsidereporting) is invoked transparently by the script.
Inputs:
- Natural-language AI or technology topics.
- Optional profile name:
terry-ai-techby default,ai-techfor the generic baseline, or aliasesterry,personal, anddefault. - Optional preset:
radarby default, orai-newsfor a faster daily AI news scan focused on official/news/HN sources. - Optional source list:
polymarket,hn,github,arxiv,hf,official,news, orall. - Daily, weekly, or monthly report request, custom rolling day window, fixed
--from/--toor--monthwindow, result limit, parallel fetch count, cache TTL, news provider strategy, brief mode, and output format. - Optional Polymarket MCP JSON export path passed with
--polymarket-mcp-json.
Outputs:
- Source-grounded AI/technology trend digest in Markdown or JSON.
- Optional clustered brief for fast reading across product, agent/tooling, enterprise, security/governance, and research/open-ecosystem signals.
- Ranked cross-source signal list with source metadata, URLs, timestamps, fixed or rolling window metadata, score rationale,
signalTier,signalMetrics, and per-source sections. - Optional
Early Watchlistentries for relevant but low-signal items. These entries stay in rawitemsoutput but should not be treated as Topline or adoption evidence. - Per-source errors when an upstream is unavailable, rate-limited, or malformed, including short response snippets when available.
- Public-response cache metadata so repeated follow-up scans are auditable.
- Sample-mode output for offline smoke checks and report-format review.
Exit codes:
0: success1: failure2: usage error3: unsafe delegated source environment detected
Failure modes:
- Unknown source, report type, format, profile, invalid fixed-window shape, or invalid numeric option.
- Live source returns invalid data, times out, or rate-limits; the affected source is reported in
errors, while other sources continue. - The broad
radarpreset usesnews-provider=auto: GDELT first, then Google News RSS fallback when GDELT is unavailable or empty. - The faster
ai-newspreset usesnews-provider=googleby default to avoid GDELT rate-limit stalls during daily scans. - Polymarket MCP output is missing, malformed, or has no usable records; continue to helper fallback unless
--polymarket-fallback noneis set. - Delegated Polymarket helper detects unsafe trading credentials; stop with exit
3.
Scripts (only entrypoints)
- $HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh
Write temporary raw collection output under:
agent-out path-for --domain tools
References
- Read references/source-strategy.md before changing source selection, ranking, or report sections.
Role Boundary
- Use
topic-radardirectly when the user asks for source-level scanning, custom sources, raw Markdown/JSON digest output, or automation input. - Use reporting.daily-brief when the user wants the normal daily information entrypoint: concise user-language synthesis, preference steering, freshness notes, and source-health explanation.
topic-radarowns source fetching, ranking, fallback behavior, public-response caching, brief clusters, and per-source errors.daily-briefmust not reimplement fetchers, ranking, cache, RSS/API parsing, or Polymarket fallback logic; it should consumetopic-radar --format json.
Workflow
-
Treat this skill as read-only content and trend research. Do not request or configure trading credentials, social posting credentials, or paid news API keys by default.
-
For "AI news today / this week / these days" requests, start with the faster AI news preset. It uses a 5-day window, clustered brief output, public-response caching, Google News RSS for mainstream coverage, and the source order
official,news,hn:$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh --preset ai-newsUse
--refreshwhen the user asks for exact latest/current results and cached responses should be bypassed:$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh --preset ai-news --refresh -
Use the broad radar preset when the user asks for general AI/Tech trend scanning across market, developer, research, model, official, and news surfaces. The default profile tracks AI agents, agentic coding, model releases, developer tools, AI infrastructure, inference serving, semiconductors, NVIDIA, robotics, embodied AI, OpenAI, Anthropic, Google DeepMind, and Hugging Face:
$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh --report daily -
Use personal memory only as a steering layer for recurring interests and source preferences before running the script. Do not write secrets, temporary task state, or project state into memory. Keep the report grounded in the script output and linked source items.
-
When Polymarket is requested and the current agent has the
polymarketMCP tools, query read-only MCP first:gamma_list_eventswithactive=true,closed=false, and a smalllimitgamma_list_marketswithactive=true,closed=false, and a smalllimitgamma_search_publicfor the user's focused topic when broad lists are too noisy
Save those raw MCP results as JSON shaped like this:
{ "events": [], "markets": [], "search": [] }Then pass the file to the radar:
$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh \ --sources polymarket,hn,github \ --polymarket-mcp-json /path/to/polymarket-mcp.json \ --report daily -
If no MCP output is available, omit
--polymarket-mcp-json; the script falls back to its bundledpolymarket-readonlyhelper logic and reports per-source errors if the local network blocks Polymarket REST. -
For focused research, pass topics and source filters:
$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh \ --topic "AI agents" \ --topic "developer tools" \ --sources hn,github,arxiv,hf,polymarket \ --report weekly -
For monthly trend archive work, use a fixed calendar window rather than a rolling
--dayswindow:$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh \ --preset radar \ --report monthly \ --month 2026-01 \ --format jsonFor a partial current month, use explicit inclusive dates:
$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh \ --preset radar \ --from 2026-05-01 \ --to 2026-05-15 \ --format jsonTreat fixed windows as source-bounded evidence. Some sources are current snapshots rather than reliable historical archives; the JSON
errorsfield reports those gaps instead of silently inventing monthly history. -
Use JSON when another tool, scheduled job, or agent synthesis step will consume the output:
$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh --preset ai-news --format json -
Use sample mode for smoke checks, demos, or local validation without network access:
$HOME/.hermes/plugins/reporting/skills/topic-radar/scripts/topic-radar.sh --sample --format markdown -
Keep the report source-grounded. Separate observed source signals from inference, and do not present heuristic ranking as objective importance. Treat
signalTieras a presentation hint: high/medium signal can feed Topline and brief clusters, whileearly-watchlistitems are relevant topic samples that need visible metrics such as HN points/comments or GitHub stars/forks.
04 同仓库更多 Skills
removable-skill
暂无简介
removable-skill
暂无简介
removable-project-skill
Fixture project-local skill used to prove remove-project-skill dry-run coverage.
project-sample-skill
Fixture project-local skill used to prove create-project-skill governance coverage.
project-local-skill
Fixture project-local skill used by runtime-kit project-local smoke checks.
project-retro
Generate a repo-local project implementation retrospective by consuming the nils-cli `repo-retro` command — local git history only, no remote API enrichment.