Rewrite 5 skill descriptions as clean one-liners (drop em-dash)

wiki-ingest, wiki-lint, wiki-plan, loop-implement, and orchestrate rendered
without a description line in the session skill list, while configure /
knowledge-flush / wiki-query showed theirs. All eight files DO have valid,
parseable descriptions (verified, incl. the 0.4.0 cache), so it is not a missing
field. No file-level property cleanly separated the two groups (configure carries
the same U+2014 em-dash, more special chars, and a longer description, yet
renders) — so this looks like a display quirk, not a fixable file defect.

As the best-guess fix, rewrite the five as concise, single-sentence, em-dash-free
descriptions (the strongest correlate, even if configure is a counterexample).
Cleaner regardless. Left the three working ones unchanged as controls.

Bump 0.6.0 -> 0.7.0.

Author: choiyounggi

.claude-plugin/marketplace.json

@@ -20,7 +20,7 @@
         "url": "https://github.com/choiyounggi/dev-loop.git"
       },
       "homepage": "https://github.com/choiyounggi/dev-loop",
-      "version": "0.6.0",
+      "version": "0.7.0",
       "tags": [
         "orchestrator",
         "verification-loop",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "dev-loop",
   "description": "loop-orchestrator's verification loop (TDD / PDCA / Reflexion) with the plan step FIXED to a wiki-grounded planning methodology (wiki-plan): every design decision is routed to a bundled semantic-layer wiki before code is written. Adds a knowledge-capture loop — sessions emit verified insights, and knowledge-flush researches, dedups, routes, and opens a wiki PR for owner review.",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "author": {
     "name": "choiyounggi",
     "url": "https://github.com/choiyounggi"

skills/loop-implement/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: loop-implement
-description: The single implementation loop. Plans via wiki-plan (step 2, required) into an ordered, wiki-navigated task list, then executes those tasks IN ORDER — each loading only its named wiki pages, applying their directives with no improvisation, writing tests first (Red), implementing (Green), running, self-reviewing, getting an independent test-quality audit, and judging against done (reporting the wiki references applied); on failure reflect and retry (bounded). Consumes an existing plan if handed one. Use for a non-trivial task or feature. Skip for typos, config values, simple renames.
+description: The single implementation loop. It plans via wiki-plan (step 2, required) into an ordered, wiki-navigated task list, then executes those tasks in order, each loading only its named wiki pages, writing tests first, getting an independent test-quality audit, and judging against done; on failure it reflects and retries (bounded). Use for a non-trivial task or feature. Skip typos, config values, and simple renames.
 ---
 
 # loop-implement — the single implementation loop, driven by a wiki-plan

skills/orchestrate/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: orchestrate
-description: Orchestrate one natural-language goal into parallel tmux Claude Code sessions — clarify requirements, branch by environment, decompose into tasks (with approval), launch a session per task running loop-implement, review and integration-test, then merge after your confirmation. Use when asked to build/implement a goal "with the orchestrator" or to split work across multiple sessions. For a single task, use loop-implement instead.
+description: Orchestrate one natural-language goal into parallel tmux Claude Code sessions. It decomposes the goal (with your approval), plans each task with wiki-plan, implements and reviews, runs an integration test, and merges after your confirmation. Use to build a goal across multiple sessions. For a single task, use loop-implement instead.
 ---
 
 # orchestrate — multi-session orchestrator

skills/wiki-ingest/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wiki-ingest
-description: Add new knowledge to the wiki — a lesson learned, an edge case hit in production, a documented best practice, or a source document. Routes it to the right domain/category, merges into existing pages before creating new ones, and enforces sourcing and positive-guidance rules.
+description: Add one verified lesson or edge case to the bundled wiki. Route it to the right domain and category, merge into an existing page before creating a new one, and enforce sourcing and positive-guidance rules. Use when capturing a documented best practice or a production edge case.
 ---
 
 # Ingest

skills/wiki-lint/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wiki-lint
-description: Wiki health check — finds drift before it compounds. Detects unsourced claims, prohibitions without replacements, vague qualifiers, orphan pages, broken links, oversized pages, stale verification dates, and unresolved contradictions. Run periodically or after a batch of ingests.
+description: Health-check the bundled wiki. Detect unsourced claims, bare prohibitions, broken links, index and page trigger mismatches, vague qualifiers, oversized pages, and stale dates, then fix them. Use to keep the wiki healthy before drift compounds.
 ---
 
 # Lint

skills/wiki-plan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wiki-plan
-description: For a CAPABLE model (Claude Sonnet/Opus, GPT-4-class, Codex) — analyze a feature/change request, make every design decision, and decompose it into ordered, self-contained task specs that a SMALL model (Haiku, Qwen-class) can each execute correctly using only the task spec plus mapped wiki pages. Produces plan.md + tasks/NN-<slug>.md.
+description: The fixed planning methodology for a capable model. Make every design decision grounded in a bundled wiki page (recording a decision-to-page map), then decompose the work into ordered, self-contained tasks, each naming the exact wiki pages that govern it. Runs as loop-implement step 2.
 ---
 
 # Plan — decompose work into small-model-executable tasks