linkedin-studio/agents
Kjell Tore Guttormsen be12fb8b63 feat(linkedin-studio): wire trend-spotter into the research engine — store + MCP routing + scoring SSOT (§5 slice 2b) [skip-docs]
Bind the layers slices 1 (store) and 2a (config) built: trend-spotter goes from
an amnesiac, niche-hardcoded scanner to a persistent, generic engine.

- Tools: drop the `tools:` allowlist (inherit all session tools incl. any
  research MCP) + `disallowedTools: Write, Edit, NotebookEdit`. An explicit
  allowlist would block every MCP unless its mcp__server__tool name were
  hardcoded — which breaks "prefer whatever MCP the user connected, hardcode
  nothing". WebSearch+WebFetch stay as the always-available floor; Bash runs
  the deterministic store CLI. (CC mechanic verified vs code.claude.com/docs.)
- Store-wiring (de-amnesia): query prior history before polling; persist every
  kept trend through scripts/trends `add` (dedup/union preserved — a raw Write
  would bypass it). Mirrors how specifics-bank is wired from the command layer.
- MCP-first routing: read the profile's "### Research Tooling" declaration,
  prefer a declared MCP, fall back to the floor, fail soft. No hardcoded names.
- Scoring -> SSOT: replace the inline matrix/composite/bands with a pointer to
  references/trend-scoring-modes.md (kortform default, long-form on request).
- Sources from config: replace the hardcoded vendor/outlet list + query bank
  with a read of trends/sources.md (user override) -> trends-sources.template.md
  (shipped default).
- CI: new test-runner Section 16 (trends-store binding guard, floor 21,
  KTG-only skip) mirroring the specifics-bank guard; assertion-count renumbered
  to Section 17. Gate 84 -> 85/0/0. model-consistency green (model unchanged).

Reload required: the tools-grant change takes effect only after a session reload.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBMKqPSVbvSZHtQ4heM1UY
2026-06-22 14:51:50 +02:00
..
__tests__ feat(linkedin-studio): v3.1.0 — Endring 9 adversarial review-pakke + per-artefakt personas 2026-05-29 13:01:24 +02:00
fixtures feat(linkedin-studio): v3.1.0 — Endring 9 adversarial review-pakke + per-artefakt personas 2026-05-29 13:01:24 +02:00
analytics-interpreter.md test(linkedin-studio): M0-16 — lint: EXPECT_REFS=26 + no-bare-path + no-pin + SC2 dry-run (R1) + drop 5 ANALYTICS_ROOT pins it caught 2026-06-18 13:11:50 +02:00
content-optimizer.md docs(linkedin-studio): M0-15 — repoint remaining prose families + route ab-tests/plans 2026-06-18 13:04:18 +02:00
content-planner.md refactor(linkedin-studio): S29e terminology-scrub — rename thought-leadership-angles.md -> content-angles.md + all pointers 2026-06-20 06:39:49 +02:00
content-repurposer.md refactor(linkedin-studio): S31b multiplier-scrub (commands + agents) — generic "Nx" claims -> SSOT 2026-06-20 09:34:20 +02:00
content-reviewer.md feat(linkedin-studio): make long-form review language configurable [skip-docs] 2026-05-30 00:55:04 +02:00
differentiation-checker.md refactor(linkedin-studio): S29e terminology-scrub — rename thought-leadership-angles.md -> content-angles.md + all pointers 2026-06-20 06:39:49 +02:00
editorial-reviewer.md feat(linkedin-studio): make long-form review language configurable [skip-docs] 2026-05-30 00:55:04 +02:00
engagement-coach.md refactor(linkedin-studio): S31c descriptive-%-scrub — platform-norm percentages asserted as fact -> SSOT 2026-06-20 09:54:44 +02:00
fact-checker.md feat(linkedin): v2.2.0 — harden longform gates from 2nd production run 2026-05-28 20:50:56 +02:00
fact-reviewer.md feat(linkedin-studio): v3.1.0 — Endring 9 adversarial review-pakke + per-artefakt personas 2026-05-29 13:01:24 +02:00
language-reviewer.md feat(linkedin-studio): make long-form review language configurable [skip-docs] 2026-05-30 00:55:04 +02:00
network-builder.md refactor(linkedin-studio): S29e terminology-scrub — rename thought-leadership-angles.md -> content-angles.md + all pointers 2026-06-20 06:39:49 +02:00
persona-reviewer.md feat(linkedin): v2.2.0 — harden longform gates from 2nd production run 2026-05-28 20:50:56 +02:00
post-feedback-monitor.md refactor(linkedin-studio): S31c descriptive-%-scrub — platform-norm percentages asserted as fact -> SSOT 2026-06-20 09:54:44 +02:00
strategy-advisor.md refactor(linkedin-studio): S31b multiplier-scrub (commands + agents) — generic "Nx" claims -> SSOT 2026-06-20 09:34:20 +02:00
trend-spotter.md feat(linkedin-studio): wire trend-spotter into the research engine — store + MCP routing + scoring SSOT (§5 slice 2b) [skip-docs] 2026-06-22 14:51:50 +02:00
video-scripter.md refactor(linkedin-studio): S29e terminology-scrub — rename thought-leadership-angles.md -> content-angles.md + all pointers 2026-06-20 06:39:49 +02:00
voice-scrubber.md docs(linkedin-studio): M0-15 — repoint remaining prose families + route ab-tests/plans 2026-06-18 13:04:18 +02:00
voice-trainer.md fix(linkedin-studio): S29b terminology-scrub — "thought leadership" → neutral (agents/) 2026-06-19 22:53:14 +02:00