Agent skill
external-intel-provider-rollout
Replace mock intel providers with live external adapters and keep scheduler, status, tests, and docs aligned. Use when working on external market/news API integration, provider env vars, or rollout validation for `news_briefing`, `eod_summary`, and `watch_poll`.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/external-intel-provider-rollout
SKILL.md
External Intel Provider Rollout
Read the contract first, then make the smallest change that moves one provider path closer to live operation.
Use this skill when the task touches any of these areas:
bot/intel/providers/news.pybot/intel/providers/market.pybot/features/intel_scheduler.pybot/app/settings.pydocs/specs/external-intel-api-spec.md- provider status, job status, env vars, or rollout docs
Quick Start
- Read
docs/context/session-handoff.md,docs/context/goals.md, anddocs/specs/external-intel-api-spec.md. - Inspect the current provider interface and the scheduler path that consumes it.
- Identify which one of
news_briefing,eod_summary, orwatch_pollis in scope. - Confirm the expected state updates, logs, tests, and docs before editing.
Workflow
1. Fix the contract before the transport
- Normalize external data into the existing
NewsItem,Quote, andEodSummaryshapes. - Keep vendor-specific fields out of the scheduler and policy layers.
- Preserve the spec's timeout, retry, and rate-limit expectations unless the user asks to change them.
2. Change one provider path at a time
- Prefer a new adapter or a narrow replacement over a broad rewrite.
- Keep the current scheduler semantics intact while swapping the data source.
- Do not couple
news_briefing,eod_summary, andwatch_pollrollout work unless the task explicitly requires it.
3. Preserve operational truth
- Make sure provider failures surface through
set_provider_status(...). - Make sure job outcomes still distinguish
ok,failed,skipped, andno-targetstyle paths when applicable. - Treat stale or partial external data as an operational risk, not just a parsing problem.
4. Validate the risky edge
- Add or update targeted tests around the changed provider path.
- Prefer tests that cover normalization, scheduler failure handling, and status recording.
- If live verification is not possible, leave a short note about what remains unverified.
5. Update runbooks and context
- Update
README.mdwhen env vars, run commands, or operating assumptions change. - Update the relevant
docs/context/*.mdfiles before finishing. - Record remaining vendor, auth, quota, or data freshness risks explicitly.
Repo-Specific Checks
News briefing
- Keep dedup behavior tied to fetched items, not post-success assumptions.
- Verify regional split (
domestic,global) still matches the post body contract.
EOD summary
- Keep the trading-day guard ahead of the external fetch when possible.
- Match
date_text, index changes, and ranking rows to existing render expectations.
Watch poll
- Watch quote freshness and cooldown behavior closely.
- Prefer batch-friendly adapter design even if the current interface is single-symbol.
Done When
- The changed provider path matches
docs/specs/external-intel-api-spec.md. - Relevant tests or logical verification were performed and recorded.
- Operational docs and
docs/context/*were updated when behavior changed. - Remaining rollout risk is written down instead of implied.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?