feat(skills): recoup-content-clip-video — clip long-form video into shorts via the OpusClip API#76
feat(skills): recoup-content-clip-video — clip long-form video into shorts via the OpusClip API#76sweetmantech wants to merge 1 commit into
Conversation
…horts via the OpusClip API Minimal first pass: SKILL.md with auth, base URL, the submit→wait→fetch flow, and links to the OpusClip API docs (quickstart + llms.txt index). Route + fixture added per resolver rules. Also unblocks CI on main: recoup-internal-video-grok-1.5-imagine-facetime (#74) was unreachable because the resolver slug regex disallowed dots — broadened to [a-z0-9.-] in check_resolvable.py / run_resolver_eval.py and added its missing route + fixture. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
📝 WalkthroughWalkthroughThis PR adds a new ChangesClip-Video Skill and Resolver Routing
Estimated code review effort: 2 (Simple) | ~10 minutes Possibly related PRs
Poem A rabbit clips a long, long reel, 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@scripts/run_resolver_eval.py`:
- Line 85: The SKILL_TOKEN_PLAIN regex currently overmatches by allowing any dot
anywhere, which causes trailing sentence punctuation to be treated as part of
the token in run_resolver_eval.py. Update the pattern in SKILL_TOKEN_PLAIN to be
version-aware so it still accepts valid dotted version segments but stops before
terminal punctuation, and make sure the token parsing logic that relies on this
regex returns the correct skill name instead of falling back to none.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 35d8dc3d-5b06-45d6-9342-471e7b1b9aa3
📒 Files selected for processing (6)
README.mdRESOLVER.mdresolver-eval.jsonlscripts/check_resolvable.pyscripts/run_resolver_eval.pyskills/recoup-content-clip-video/SKILL.md
| MIN_PASS = float(os.environ.get("RECOUP_RESOLVER_EVAL_MIN_PASS", "1.0")) | ||
| FRONTMATTER_KEY = re.compile(r"^([A-Za-z][\w-]*):\s?(.*)$") | ||
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9-]+") | ||
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9.-]+") |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Keep dot support, but stop matching sentence punctuation.
recoup-[a-z0-9.-]+ will also absorb a trailing . in model replies, so a correct answer like recoup-internal-video-grok-1.5-imagine-facetime. falls through to none. Make the pattern version-aware instead of letting . match anywhere.
♻️ Proposed fix
-SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9.-]+")
+SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9-]+(?:\.[a-z0-9-]+)*")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9.-]+") | |
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9-]+(?:\.[a-z0-9-]+)*") |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@scripts/run_resolver_eval.py` at line 85, The SKILL_TOKEN_PLAIN regex
currently overmatches by allowing any dot anywhere, which causes trailing
sentence punctuation to be treated as part of the token in run_resolver_eval.py.
Update the pattern in SKILL_TOKEN_PLAIN to be version-aware so it still accepts
valid dotted version segments but stops before terminal punctuation, and make
sure the token parsing logic that relies on this regex returns the correct skill
name instead of falling back to none.
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
2 issues found across 6 files
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="skills/recoup-content-clip-video/SKILL.md">
<violation number="1" location="skills/recoup-content-clip-video/SKILL.md:13">
P2: For multi-org users, the GET `/exportable-clips` endpoint requires a `x-opus-org-id` header. The current Setup only documents `Authorization: Bearer $OPUS_PRO_API_KEY`, so users with multiple organizations will get a 400 error on step 3 (Fetch clips) with no guidance on how to resolve it. Consider adding a note that this header may be needed, referencing the Org ID from the OpusClip dashboard.</violation>
</file>
<file name="scripts/run_resolver_eval.py">
<violation number="1" location="scripts/run_resolver_eval.py:85">
P2: The broadened character class `[a-z0-9.-]+` will greedily absorb a trailing `.` when the skill slug appears at the end of a sentence in a model reply (e.g., `"…use recoup-internal-video-grok-1.5-imagine-facetime."`). The resulting match won't exist in `skill_dirs()`, turning a correct answer into a false negative. A version-segment-aware pattern avoids this while still supporting dotted slugs like `grok-1.5`.</violation>
</file>
Reply with feedback, questions, or to request a fix.
Re-trigger cubic
|
|
||
| ## Setup | ||
|
|
||
| - Auth: `Authorization: Bearer $OPUS_PRO_API_KEY` (never hardcode the key; get |
There was a problem hiding this comment.
P2: For multi-org users, the GET /exportable-clips endpoint requires a x-opus-org-id header. The current Setup only documents Authorization: Bearer $OPUS_PRO_API_KEY, so users with multiple organizations will get a 400 error on step 3 (Fetch clips) with no guidance on how to resolve it. Consider adding a note that this header may be needed, referencing the Org ID from the OpusClip dashboard.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At skills/recoup-content-clip-video/SKILL.md, line 13:
<comment>For multi-org users, the GET `/exportable-clips` endpoint requires a `x-opus-org-id` header. The current Setup only documents `Authorization: Bearer $OPUS_PRO_API_KEY`, so users with multiple organizations will get a 400 error on step 3 (Fetch clips) with no guidance on how to resolve it. Consider adding a note that this header may be needed, referencing the Org ID from the OpusClip dashboard.</comment>
<file context>
@@ -0,0 +1,32 @@
+
+## Setup
+
+- Auth: `Authorization: Bearer $OPUS_PRO_API_KEY` (never hardcode the key; get
+ one at https://clip.opus.pro/dashboard).
+- Base URL: `https://api.opus.pro/api`
</file context>
| MIN_PASS = float(os.environ.get("RECOUP_RESOLVER_EVAL_MIN_PASS", "1.0")) | ||
| FRONTMATTER_KEY = re.compile(r"^([A-Za-z][\w-]*):\s?(.*)$") | ||
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9-]+") | ||
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9.-]+") |
There was a problem hiding this comment.
P2: The broadened character class [a-z0-9.-]+ will greedily absorb a trailing . when the skill slug appears at the end of a sentence in a model reply (e.g., "…use recoup-internal-video-grok-1.5-imagine-facetime."). The resulting match won't exist in skill_dirs(), turning a correct answer into a false negative. A version-segment-aware pattern avoids this while still supporting dotted slugs like grok-1.5.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At scripts/run_resolver_eval.py, line 85:
<comment>The broadened character class `[a-z0-9.-]+` will greedily absorb a trailing `.` when the skill slug appears at the end of a sentence in a model reply (e.g., `"…use recoup-internal-video-grok-1.5-imagine-facetime."`). The resulting match won't exist in `skill_dirs()`, turning a correct answer into a false negative. A version-segment-aware pattern avoids this while still supporting dotted slugs like `grok-1.5`.</comment>
<file context>
@@ -82,7 +82,7 @@ def load_fixtures() -> list[dict]:
MIN_PASS = float(os.environ.get("RECOUP_RESOLVER_EVAL_MIN_PASS", "1.0"))
FRONTMATTER_KEY = re.compile(r"^([A-Za-z][\w-]*):\s?(.*)$")
-SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9-]+")
+SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9.-]+")
</file context>
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9.-]+") | |
| SKILL_TOKEN_PLAIN = re.compile(r"recoup-[a-z0-9-]+(?:\.[a-z0-9-]+)*") |
1 participant
What
Adds
recoup-content-clip-video— a minimal first-pass skill for turning long-form video (podcast, interview, livestream, live set) into social-ready short clips via the OpusClip API.Kept intentionally basic so we can layer on today's workflow (curation preferences, brand templates, social posting, webhooks) in follow-ups:
SKILL.mdwith auth (OPUS_PRO_API_KEYenv var), base URL, and the core submit → wait → fetch flowhttps://help.opus.pro/llms.txt— every doc page has a.mdvariant)Also: unblocks CI on main
check_resolvable.py/run_resolver_eval.pywere failing on main:recoup-internal-video-grok-1.5-imagine-facetime(#74) has a dot in its slug, and the resolver slug regex (recoup-[a-z0-9-]+) can't parse dotted names — so the skill could never have a parseable route. Fixed by broadening the regex to[a-z0-9.-]and adding the missing route + fixture. (Alternative was renaming that skill; left that call to a follow-up if we'd rather enforce dot-free slugs.)Validation
All five gates pass locally:
portability_lint,check_vendored,validate_manifests,check_resolvable(36/36 reachable),run_resolver_eval(48 positives + 15 negatives, full coverage).🤖 Generated with Claude Code
Summary by cubic
Adds
recoup-content-clip-videoto turn long-form video into social-ready clips via the OpusClip API. Also broadens resolver slug parsing to allow dots, makingrecoup-internal-video-grok-1.5-imagine-facetimeresolvable and unblocking CI.New Features
recoup-content-clip-videofor clipping podcasts/streams/interviews into shorts.SKILL.mdwithOPUS_PRO_API_KEYauth, base URL, and submit → wait/poll → fetch flow; linked OpusClip docs.Bug Fixes
[a-z0-9.-]in validation/eval scripts.recoup-internal-video-grok-1.5-imagine-facetime, restoring CI checks.Written for commit 57ebe8b. Summary will update on new commits.
Summary by CodeRabbit
New Features
Documentation
Bug Fixes