@olegkoval/agent-skills 1.34.0 → 1.35.1

package/.github/prompts/ci-fix-loop.prompt.md

@@ -0,0 +1,184 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Diagnose GitHub Actions CI failures in a loop: fetch failing check logs, fix, push, and repeat until green. Direct analog of qodoloop / coderabbitloop for test and lint failures."
+---
+
+Use the olko:ci-fix-loop skill.
+
+> 🤖 *Auto-generated by **weekly-pattern-learner** · qodoloop and coderabbitloop share the push→poll→diagnose→fix→repeat loop; CI failures have the same shape but no dedicated skill existed*
+
+# CI Fix Loop
+
+Drive a GitHub Actions CI run from red to green: fetch failure logs, diagnose, apply
+a targeted fix, push, and repeat until all required checks pass or a blocker is hit.
+
+## Inputs
+
+- **PR number** (optional): detect from current branch if not given.
+- **Check names** (optional): limit to specific failing checks instead of all.
+- **Max iterations** (default: 5)
+
+## Workflow
+
+### 1. Identify the PR and current CI state
+
+```bash
+# Detect PR from current branch
+gh pr view --json number,headRefName,headRefOid \
+  -q '{number, branch: .headRefName, sha: .headRefOid}'
+
+# Current check status
+gh pr checks --json name,state,conclusion 2>/dev/null \
+  || gh run list --branch <branch> --limit 5
+```
+
+Classify each check as: `pass`, `fail`, `pending`, or `skipped`.
+
+**Exit immediately if all required checks already pass** — nothing to do.
+
+### 2. Loop (max 5 iterations)
+
+#### A. Identify failing checks
+
+```bash
+gh pr checks --json name,state,conclusion \
+  --jq '.[] | select(.conclusion == "failure" or .state == "FAILURE")'
+```
+
+For each failing check, record: check name, workflow file, job name.
+
+Stop if the working set is empty — all required checks are green.
+
+#### B. Check for base-branch regression first
+
+Before touching any code, verify the failure is not already present on `main`:
+
+```bash
+gh run list --branch <base-branch> --workflow <workflow-name> --limit 3 \
+  --json conclusion --jq '.[].conclusion'
+```
+
+If the same check is failing on the base branch, **stop and report** —
+this is not your PR's fault. Do not attempt a fix that masks a base-branch problem.
+Wait for a `Base branch recovered` notice before re-trying.
+
+#### C. Fetch failure logs
+
+For each failing check:
+
+```bash
+# Latest run ID for this branch/workflow
+gh run list --branch <branch> --workflow <workflow-name> --limit 1 \
+  --json databaseId --jq '.[0].databaseId'
+
+# Fetch only failing steps (not the full log)
+gh run view <run-id> --log-failed
+```
+
+Cap log reading at ~200 lines per job — the error is almost always in the last
+50 lines of a failed step.
+
+#### D. Diagnose
+
+Classify the failure before writing any code:
+
+| Category | Examples | Fix target |
+|---|---|---|
+| Test failure | `FAIL TestFoo`, `AssertionError`, `expected X got Y` | Source or test |
+| Lint / format | `gofmt`, `eslint`, `ruff`, `prettier` | Run auto-formatter |
+| Build error | compile error, missing import, type mismatch | Source |
+| Dependency | `npm ERR!`, missing module, lockfile mismatch | Update lockfile |
+| CI config | YAML parse error, bad action ref, missing secret | Workflow YAML |
+| Flaky test | same test passes on manual re-run | Re-run first; mark if it keeps failing |
+
+For flaky-looking failures, re-run the check before touching code:
+
+```bash
+gh run rerun <run-id> --failed
+```
+
+Wait for the rerun result. If it passes on rerun, skip this iteration and go to
+step F to poll for the new result.
+
+#### E. Apply a targeted fix
+
+Fix **only** what the log names as the failure. Do not refactor surrounding code,
+add unrelated tests, or touch files the failing step never mentioned.
+
+Common one-liners:
+
+```bash
+# Go format
+gofmt -w .
+goimports -w .
+
+# Node format / lint
+npx prettier --write .
+npx eslint --fix .
+
+# Python
+ruff check --fix .
+black .
+
+# Lockfile
+npm install          # Node
+poetry lock --no-update  # Python
+go mod tidy          # Go
+```
+
+For test failures: read the failing test and the code it exercises. Fix the code
+or the assertion — but not both in one commit unless the test was clearly wrong
+and the fix is trivial.
+
+#### F. Commit and push
+
+Stage **only the files touched in step E** — never `git add -A`, which can sweep
+in unrelated local changes:
+
+```bash
+git add <files touched>
+git commit -m "fix(ci): <what was broken> (ci-fix-loop iteration N)"
+git push
+```
+
+Confirm the push succeeded before polling. A resolved check whose fix never reached
+the branch is worse than an unresolved one.
+
+#### G. Wait for CI on the new SHA
+
+Poll every ~15s (timeout ~8min) for all previously-failing checks to complete
+on the new push:
+
+```bash
+gh pr checks --json name,state,conclusion,startedAt
+```
+
+Wait until all previously-failing checks show a new result (`pass` or `fail`)
+on the current SHA. Do not act on a result that still shows the old SHA.
+
+Go back to step A.
+
+### 3. Report
+
+| Field | Value |
+|---|---|
+| Iterations | N |
+| Checks fixed | names + root cause |
+| Checks blocked | names + reason (flaky / needs human / base-branch red) |
+| Final status | all green / partial / blocked |
+
+```
+CI fix loop complete.
+  Iterations:  2
+  Fixed:       lint (gofmt: 3 files), test (TestUserCreate — nil pointer in fixture)
+  Blocked:     none
+  Status:      all required checks green
+```
+
+## Chaining
+
+| Before this skill | After this skill |
+|---|---|
+| `olko:pr-description-writer` | `olko:qodoloop` |
+| Any `git push` with failing CI | `olko:coderabbitloop` |

package/{packages/software-development/cloudflare-block-countries/adapters/kiro/steering/cloudflare-block-countries.md → .github/prompts/cloudflare-block-countries.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Block specific countries via Cloudflare WAF Custom Rules using the Cloudflare API. Handles creating new rulesets and updating existing ones across single or multiple zones."
 ---
 
+Use the olko:cloudflare-block-countries skill.
+
 # Cloudflare Country Block via WAF Custom Rules
 
 Block traffic from specific countries using Cloudflare WAF Custom Rules and the Cloudflare API.

package/{packages/software-development/coderabbitloop/adapters/kiro/steering/coderabbitloop.md → .github/prompts/coderabbitloop.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Iteratively drives a GitHub PR to zero unresolved CodeRabbit findings — reads each inline comment's own Prompt for AI Agents block, applies the fix, replies to the thread, resolves it, pushes, and re-triggers CodeRabbit."
 ---
 
+Use the olko:coderabbitloop skill.
+
 # Coderabbitloop
 
 Fix every actionable CodeRabbit finding on a PR, answer each thread, resolve it, and keep going until CodeRabbit has nothing left to say (or a finding needs a human call).

package/{packages/software-development/codexloop/adapters/windsurf/rules/codexloop.md → .github/prompts/codexloop.prompt.md}

@@ -4,6 +4,8 @@
 description: "Iteratively drives a GitHub PR to zero unresolved OpenAI Codex review comments — but verifies every finding against the real code first, fixes only the correct ones, and rebuts false positives without changing correct code."
 ---
 
+Use the olko:codexloop skill.
+
 # Codexloop
 
 Drive a GitHub PR until Codex has no unresolved review comments — **but do not cargo-cult its

package/{packages/software-development/crash-course/adapters/kiro/steering/crash-course.md → .github/prompts/crash-course.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Expert tutor for rapid, source-grounded learning of any topic: a timed 4-hour sprint plus cheat-sheet, learning-ladder, quiz-me, Feynman, and resource-curation modes."
 ---
 
+Use the olko:crash-course skill.
+
 # Crash Course
 
 An expert tutor for rapid, durable learning of any topic. The learner is smart and

package/.github/prompts/dependabot-triage.prompt.md

@@ -0,0 +1,131 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Triage open Dependabot and Renovate PRs in bulk: classify by risk tier, auto-approve and merge safe patch bumps, flag breaking major upgrades for human review, and post a digest."
+---
+
+Use the olko:dependabot-triage skill.
+
+> 🤖 *Auto-generated by **weekly-pattern-learner** · obsidian-pr-sync explicitly filters out dependabot/renovate PRs — the user handles them separately, but no skill existed to batch-triage them*
+
+# Dependabot Triage
+
+Bulk-process open Dependabot and Renovate PRs: approve and merge what is safe,
+flag what needs a human decision, and report what was done.
+
+## Inputs
+
+- **Repository** (optional): default to the current repo.
+- **Auto-merge policy** (optional, default: `patch-only`): `none`, `patch-only`, or `patch-and-minor`.
+- **Require CI** (optional, default: on): only merge PRs whose checks are green.
+
+## Step 1 — Fetch all open dependency PRs
+
+```bash
+# Dependabot PRs
+gh pr list --state open --label "dependencies" \
+  --json number,title,author,labels,headRefName,url,isDraft \
+  --jq '.[] | select(.author.login | test("dependabot|renovate"; "i"))'
+
+# Also catch Renovate PRs not labelled "dependencies"
+gh pr list --state open \
+  --json number,title,author,labels,headRefName,url,isDraft \
+  --jq '.[] | select(.author.login == "renovate[bot]" or .author.login == "dependabot[bot]")'
+```
+
+Merge both result sets, deduplicate by number, skip drafts.
+
+## Step 2 — Classify each PR
+
+Parse the PR title to extract package name and version change.
+
+Dependabot title format: `Bump <package> from <old> to <new>`
+Renovate title format: `Update dependency <package> to v<new>` or `chore(deps): update <package>`
+
+For each PR:
+
+```bash
+gh pr view <NUMBER> --json title,body,labels,reviews \
+  --jq '{title, body: (.body | .[0:500]), labels: [.labels[].name], reviews: [.reviews[].state]}'
+```
+
+Classify:
+
+| Tier | Condition | Default action |
+|------|-----------|----------------|
+| **patch** | semver patch bump (`X.Y.Z → X.Y.Z+1`), no security label | auto-approve and merge (if CI green) |
+| **minor** | semver minor bump (`X.Y.Z → X.Y+1.0`), no security label | approve and merge when `patch-and-minor` policy |
+| **major** | semver major bump (`X.Y.Z → X+1.0.0`) | flag for human: summarize breaking changes |
+| **security** | has `security` label, or title contains "CVE" or "vulnerability" | escalate: approve if CI green AND patch/minor; human if major |
+
+When in doubt about the bump type (e.g. non-semver packages), treat as `minor`.
+
+## Step 3 — Check CI for merge candidates
+
+For each PR classified as auto-approvable:
+
+```bash
+gh pr checks <NUMBER> --json name,state,conclusion \
+  --jq '[.[] | select(.conclusion != "success" and .conclusion != "skipped")] | length'
+```
+
+If CI is still running, wait up to 10 minutes (polling every 30s). If CI fails, demote
+to `blocked` — do not merge a PR with failing checks regardless of policy.
+
+If CI is disabled for dependency PRs in this repo (no checks at all), note it and proceed
+only when the user has passed `--skip-ci-check` explicitly.
+
+## Step 4 — Approve and merge safe PRs
+
+For each auto-approvable PR with green CI:
+
+```bash
+# Approve
+gh pr review <NUMBER> --approve --body "Auto-approved by dependabot-triage: patch bump, CI green."
+
+# Merge (squash is the default; use the repo's configured merge strategy if known)
+gh pr merge <NUMBER> --squash --delete-branch \
+  --subject "$(gh pr view <NUMBER> --json title --jq .title)"
+```
+
+If the merge fails (conflict, branch protection, etc.), fall back to `blocked` and note it.
+
+## Step 5 — Comment on flagged PRs
+
+For each `major` or `blocked` PR, post one comment summarizing why it needs a human:
+
+```bash
+gh pr comment <NUMBER> --body "**dependabot-triage:** This is a major version bump. \
+Review the changelog before merging: $(gh pr view <NUMBER> --json body --jq '.body | split("\n") | map(select(test("changelog|release|BREAKING"; "i"))) | .[0]').
+
+No action was taken."
+```
+
+## Step 6 — Report
+
+Print a digest, then stop. Do not merge anything not listed as approved in this report.
+
+```
+Dependabot triage complete.
+  Merged (patch, CI green):   7 PRs  →  lodash 4.17.20→4.17.21, eslint 8.56.0→8.57.0, ...
+  Merged (security, CI green): 1 PR  →  axios 1.6.2→1.7.9 (CVE-2024-39338)
+  Flagged for human review:    2 PRs →  next.js 14→15 (major), @types/node 20→22 (major)
+  Blocked (CI failing):        1 PR  →  typescript 5.4→5.5 (lint errors)
+  Skipped (draft):             1 PR
+
+  Open a flagged PR and run /pr-to-green after reviewing the changelog.
+```
+
+## Safety guardrails
+
+- Never merge a PR whose author is not `dependabot[bot]` or `renovate[bot]`, even if found by the label query.
+- Never merge a major bump automatically, even if `patch-and-minor` policy is set.
+- Never approve a PR if `gh pr checks` shows any failure — a quiet pass is not the same as no checks.
+- Always post a comment on flagged PRs so the record is visible in the thread.
+
+## Chaining
+
+| Before this skill | After this skill |
+|---|---|
+| morning routine / maintenance window | `olko:pr-to-green` on flagged PRs after human review |
+| `olko:obsidian-pr-sync` (which filters these out) | back to obsidian-pr-sync for remaining human PRs |

package/{packages/software-development/docs-index-keeper/adapters/kiro/steering/docs-index-keeper.md → .github/prompts/docs-index-keeper.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Keep a Markdown docs index in sync through pre-commit, CI, or one-off maintenance flows."
 ---
 
+Use the olko:docs-index-keeper skill.
+
 # docs-index-keeper
 
 Use this skill when a repository keeps docs under `docs/` and needs a Markdown index table updated automatically as docs are added or changed.

package/{packages/music/fill-music-player/adapters/kiro/steering/fill-music-player.md → .github/prompts/fill-music-player.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Fill a portable music player with a curated random selection from a source music library while balancing formats, artists, albums, and capacity."
 ---
 
+Use the olko:fill-music-player skill.
+
 # fill-music-player
 
 Curates a DJ-balanced selection of tracks from a source music library and copies them to a portable player, respecting device capacity and supported formats.

package/{packages/photography/gallery/adapters/windsurf/rules/gallery.md → .github/prompts/gallery.prompt.md}

@@ -4,6 +4,8 @@
 description: "Create photo galleries with AI-assisted layout curation and sequencing."
 ---
 
+Use the olko:gallery skill.
+
 # Gallery Workflow
 
 Composed skill that creates photo galleries by orchestrating atomic scripts and sub-agents.

package/{packages/wearables/garmin-watchface/adapters/windsurf/rules/garmin-watchface.md → .github/prompts/garmin-watchface.prompt.md}

@@ -4,6 +4,8 @@
 description: "Design, build, test, screenshot and publish Garmin Connect IQ watch faces in Monkey C."
 ---
 
+Use the olko:garmin-watchface skill.
+
 # Garmin Connect IQ watch faces
 
 Monkey C gives you almost no safety net. The compiler is happy to build a face

package/{packages/software-development/geminiloop/adapters/kiro/steering/geminiloop.md → .github/prompts/geminiloop.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Iteratively drives a GitHub PR to zero unresolved Gemini Code Assist comments — treats each one as a claim to verify, fixes only the genuinely-correct findings, and rebuts the rest with evidence instead of editing correct code."
 ---
 
+Use the olko:geminiloop skill.
+
 # Geminiloop
 
 Drive a GitHub PR until Gemini Code Assist has no unresolved comments — **but do not cargo-cult

package/{packages/software-development/gh-cli/adapters/kiro/steering/gh-cli.md → .github/prompts/gh-cli.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Use the GitHub CLI effectively for repositories, PRs, Actions, releases, and more."
 ---
 
+Use the olko:gh-cli skill.
+
 # GitHub CLI (gh)
 
 Comprehensive reference for GitHub CLI (gh) - work seamlessly with GitHub from the command line.

package/{packages/software-development/git-commit/adapters/windsurf/rules/git-commit.md → .github/prompts/git-commit.prompt.md}

@@ -4,6 +4,8 @@
 description: "Create conventional commits with diff-aware staging and message generation."
 ---
 
+Use the olko:git-commit skill.
+
 # Git Commit with Conventional Commits
 
 ## Overview

package/{packages/software-development/macos-menubar-app/adapters/windsurf/rules/macos-menubar-app.md → .github/prompts/macos-menubar-app.prompt.md}

@@ -4,6 +4,8 @@
 description: "Build a production-quality macOS menubar or notch app in SwiftUI — MenuBarExtra, sandbox entitlements, keyboard shortcuts, sound effects, accessibility permissions, and App Store preparation."
 ---
 
+Use the olko:macos-menubar-app skill.
+
 > 🤖 *Auto-generated by **weekly-pattern-learner** · SwiftUI macOS menubar app pattern observed in FocusNotch session, Jun 2026 (364 user turns, ~48 MB transcript covering idea → spec → impl → critique cycles → App Store)*
 
 # macOS Menubar / Notch App (SwiftUI)

package/.github/prompts/morning-routine.prompt.md

@@ -0,0 +1,130 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Run the complete start-of-day setup in one pass: roll over unfinished Obsidian tasks to today's daily note, sync open GitHub PRs that need your attention, and sweep Dependabot patch bumps. Chains obsidian-task-rollover, obsidian-pr-sync, and dependabot-triage."
+---
+
+Use the olko:morning-routine skill.
+
+> 🤖 *Auto-generated by **weekly-pattern-learner** · obsidian-task-rollover, obsidian-pr-sync, and dependabot-triage all describe themselves as morning-routine steps but no meta-skill chains them into a single first-thing-of-day pass*
+
+# Morning Routine
+
+Run the three start-of-day workflows in sequence, then summarize what needs your
+attention today. Each phase is idempotent — re-running is safe.
+
+## Inputs
+
+- **VAULT_DAILY** (required): absolute path to the Obsidian daily notes folder
+- **GH_USERNAME** (required): GitHub login for PR filtering
+- **ORG_PREFIX** (optional): org name to group as "Work" in the PR section
+- **--skip-rollover** (optional): skip task rollover (e.g. Monday after a break)
+- **--skip-pr-sync** (optional): skip GitHub PR sync
+- **--skip-dependabot** (optional): skip Dependabot triage
+
+If any required config is missing, ask once before starting — don't abort midway.
+
+## Phase 1 — Task rollover
+
+Initialize the daily note path once, before any optional phase:
+
+```bash
+NOTE="${VAULT_DAILY}/$(date +%Y-%m-%d).md"
+```
+
+Run `olko:obsidian-task-rollover` on the **previous workday's** note.
+
+`obsidian-task-rollover` is an end-of-day migration skill — it copies unchecked tasks
+from a given day's note into the next workday's note with a `[>]` marker. When invoked
+here in the morning, it should operate on **yesterday's** (or the last workday's) note
+so those unchecked tasks are pulled forward into today's note. If yesterday's note does
+not exist, skip this step and note it in the report.
+
+**Skip if** `--skip-rollover` is set, or if it's Monday and the user has explicitly
+said they clear the board on Fridays.
+
+After this phase, confirm:
+```bash
+grep -c "^\- \[ \]" "$NOTE" 2>/dev/null || echo "0"  # open tasks today
+grep -c "^\- \[>\]" "$NOTE" 2>/dev/null || echo "0"  # migrated tasks
+```
+
+Record counts for the final report.
+
+## Phase 2 — PR sync
+
+Run `olko:obsidian-pr-sync`.
+
+This fetches all open GitHub PRs where the user is assignee or review-requested,
+filters out bots and drafts, and writes or replaces the `## PRs to review` section
+in today's daily note. PRs are grouped into Work (ORG_PREFIX org) and Personal.
+
+**Skip if** `--skip-pr-sync` is set.
+
+After this phase, count PRs written:
+```bash
+grep -c "^\- \[ \] \[" "$NOTE" 2>/dev/null || echo "0"
+```
+
+## Phase 3 — Dependabot triage (quick sweep)
+
+Run `olko:dependabot-triage` with `patch-only` auto-merge policy.
+
+This auto-approves and merges safe patch bumps whose CI is green, flags major
+upgrades for human review, and posts a digest. The `patch-only` policy means no
+minor or major bumps are merged automatically — just the safest dependency noise.
+
+**Skip if** `--skip-dependabot` is set, or if there are no open dependency PRs:
+
+```bash
+gh pr list --state open \
+  --json author --jq '
+    [.[] | select(.author.login | test("dependabot|renovate"; "i"))]
+    | length
+  ' 2>/dev/null
+```
+
+If the count is 0, skip phase 3 and note it in the report.
+
+## Final report
+
+Print a compact brief suitable for the start of the day:
+
+```
+Morning routine complete — YYYY-MM-DD
+
+  Tasks:        N open today (M carried over from yesterday)
+  PRs:          X work PRs, Y personal PRs → see ## PRs to review in today's note
+  Dependabot:   Z merged (patch, CI green), W flagged for review
+
+  Today's top 3:
+    [read from ## Top 3 for today section if populated, else print "(not filled in yet)"]
+
+  Flagged for you:
+    - [PRs older than 7 days ⚠️ from the PR sync, if any]
+    - [Major Dependabot bumps flagged for human decision, if any]
+```
+
+If a phase failed (auth expired, vault not found, network error), surface the error
+clearly rather than silently skipping that phase.
+
+## Invocation patterns
+
+**Manual (user-triggered):**
+User says "start my day", "run morning routine", or "set up today's note".
+Run the full flow and show the final report.
+
+**Scheduled (cron / CCR):**
+No user prompt needed. Run all three phases silently and emit the report as the
+run's output. Useful as a pre-meeting brief or as a first message in a new session.
+
+**Partial run:**
+If the user wants to re-sync only PRs mid-day: `--skip-rollover --skip-dependabot`.
+
+## Chaining
+
+| Before this skill | After this skill |
+|---|---|
+| — (start of session) | Work the PR queue (`olko:pr-to-green` on flagged items) |
+| — | `olko:dependabot-triage` with `patch-and-minor` if the quick sweep flagged many |
+| `olko:obsidian-task-rollover` alone | nothing — this skill already calls it |

package/{packages/software-development/mvp-oneshot/adapters/kiro/steering/mvp-oneshot.md → .github/prompts/mvp-oneshot.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Turn a rough product idea into a shippable one-week MVP in one pass via a four-role prompt chain: scope a build prompt, ruthlessly trim it, plan the build, and self-review the vertical slice."
 ---
 
+Use the olko:mvp-oneshot skill.
+
 # MVP Oneshot
 
 You are a senior startup engineer running a four-role prompt chain in a single pass.

package/{packages/software-development/obsidian-pr-sync/adapters/windsurf/rules/obsidian-pr-sync.md → .github/prompts/obsidian-pr-sync.prompt.md}

@@ -4,6 +4,8 @@
 description: "Fetch open GitHub PRs assigned to you or requesting your review, and write a grouped, age-sorted '## PRs to review' section into today's Obsidian daily note. Idempotent — re-running replaces the section."
 ---
 
+Use the olko:obsidian-pr-sync skill.
+
 # Obsidian PR Sync
 
 Fetch all open PRs where the user is assigned or requested as reviewer, filter out

package/{packages/software-development/obsidian-task-rollover/adapters/windsurf/rules/obsidian-task-rollover.md → .github/prompts/obsidian-task-rollover.prompt.md}

@@ -4,6 +4,8 @@
 description: "Bullet-journal end-of-day task migration: copy unchecked tasks from today's Obsidian daily note to the next workday's note under '## Carried over', and mark them [>] in the source. Skips weekends, idempotent."
 ---
 
+Use the olko:obsidian-task-rollover skill.
+
 # Obsidian Task Rollover
 
 Bullet-journal–style end-of-day task migration. Unfinished tasks (`- [ ]`) from

package/{packages/software-development/open-source-publisher/adapters/kiro/steering/open-source-publisher.md → .github/prompts/open-source-publisher.prompt.md}

@@ -1,10 +1,11 @@
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
 
 ---
-inclusion: manual
 description: "Prepare an open-source repository for public publishing with a minimal icon, social preview image, GitHub Pages site, README standardization, CI/CD checks, release hygiene, optional donation setup, and optional motion previews for generated static images."
 ---
 
+Use the olko:open-source-publisher skill.
+
 # open-source-publisher
 
 Use this skill to audit whether an OSS repository is ready to publish, then help only with missing or weak pieces: recognizable icon, shareable social image, GitHub Pages site, standardized README, CI/CD hygiene, release readiness, and optional donation links.