feat(skills): author the Continuous Research skills, and make its roles honest

The boot log has said `continuous_research — 4 role skills bound, 8 unresolved`
on every start. Those eight roles ran without the instructions their template
promised them, silently: `skills_loader` reports the miss and carries on.

Worse than the missing files was what the prompts described. v1 told the
harvester to sweep "RSS feeds, GitHub trending, HN front page, YouTube /
podcast RSS" — none of which exist. `harvest.rs` searches arXiv and nothing
else. A role prompt describing a machine that was never built is the failure
this codebase keeps paying for, so v2 describes the machine that exists.

Roles now match the pipeline: paper_reader (the harvest already ran; read the
manifest and the papers), signal_ranker (unchanged in spirit), script_writer
(the podcast half, which had no role at all).

Seven skills authored under skills/research/, kebab-case to match the loader —
team_template_loader.rs:177-181 documents the snake_case/kebab-case trap that
already unbinds skills elsewhere:

  arxiv-daily                  what the harvest guarantees, so an agent does
                               NOT re-search arXiv and corrupt the seen-set
  paper-to-project-relevance   name a file or roadmap item, or say "no bearing"
  duplicate-detection          the seen-set catches identity; this catches the
                               same work under a different id
  signal-to-noise-ranking      novelty/relevance/depth, and the two biases to
                               resist (recency up, inconvenience down)
  executive-summary-writing    what it is / why it matters / what to do — decide,
                               do not hedge
  obsidian-vault-conventions   the vault is a human's live workspace; never
                               main, never reorganise, hash the body not the file
  podcast-dialogue-writing     write for someone on a treadmill; the 10-70 char
                               highlight bound is the API's, not a style rule

`web_fetch` dropped from mcp_bundles: runtime_provision.rs binds every mission
claw to `["clawmates_door"]` and never reads that field, so declaring it
instructed roles to use a tool that never arrived. The prompts say `curl` via
Bash, which is what they actually have.

Boot now reports `continuous_research — 11 role skills bound`, with no
unresolved clause. 344 tests pass.

Co-Authored-By: Claude Opus 5 <[email protected]>

skills/research/executive-summary-writing.md

@@ -0,0 +1,56 @@
+---
+name: executive-summary-writing
+description: Writing the three-part item entry — what it is, why it matters to us, what to do — so a digest is readable in two minutes.
+when_to_use: You are writing digest or analysis entries for harvested research items.
+tags: [research, writing]
+---
+
+# The three-part entry
+
+Every item gets exactly three parts. The shape is the discipline: it makes the
+omissions visible.
+
+**What it is** — one sentence, what they actually did. Not what it enables, not
+why it is exciting. If you cannot state the contribution in one sentence you
+have not finished reading.
+
+**Why it matters to us** — the named project, file or open question it touches.
+If nothing applies, the item does not belong in the digest. That rule is what
+keeps a digest from becoming a feed.
+
+**What to do about it** — one decision, from a closed set:
+
+```
+read fully     worth an hour of someone's time
+add to backlog a concrete change we should make
+ignore         seen, judged, not for us
+escalate       changes a plan we are currently executing
+```
+
+## Decide; do not hedge
+
+"Consider evaluating whether this might inform our approach" is four words of
+decision wrapped in ten of insulation. Write `ignore` or write `add to backlog`.
+Being wrong in a specific direction is recoverable; being vague is not, because
+nobody can tell later whether the call was right.
+
+## Two minutes, total
+
+Not two minutes per item — two minutes for the digest. Five items at three
+sentences each is roughly the budget. If an item needs more, it is not a digest
+entry, it is a reading note: link to it and keep the entry short.
+
+## Frontmatter carries the ratio
+
+```yaml
+---
+date: 2026-08-17
+harvested: 23
+surfaced: 4
+---
+```
+
+Harvested-versus-surfaced tracked over time is how you notice selectivity drift.
+A run that surfaces everything has stopped filtering; a run that surfaces
+nothing for a week is either a quiet field or a broken harvest, and the counts
+are what tell you which.