Skip to content

Update combo evaluation status from deferred to active #420

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
yacosta738 wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Update combo evaluation status from deferred to active #420

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .agents/journal/scribe-journal.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,3 +27,8 @@

**Learning:** The `agentsync skill suggest` command's technology detection shifted from a small hard-coded set to a data-driven catalog (`src/skills/catalog.v1.toml`) now supporting 73+ technologies. The documentation had drifted significantly (claiming only 7 supported).
**Action:** When documenting "supported" lists that are data-driven, use "N+" terminology and refer to the source-of-truth catalog file to ensure long-term accuracy.

## 2026-05-20 - Implemented Combo Evaluation Documented as Deferred
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot May 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Fix the journal entry date to a non-future date.

The entry is dated 2026-05-20, but this PR was created on 2026-05-16. This makes the audit trail temporally inconsistent; please use the actual entry date (or explicitly mark it as planned).

🤖 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 @.agents/journal/scribe-journal.md at line 31, Update the journal header "##
2026-05-20 - Implemented Combo Evaluation Documented as Deferred" so the date is
not in the future relative to the PR (change 2026-05-20 to the actual entry date
2026-05-16 or another past date), or explicitly mark the entry as planned by
replacing the header with a clear planned prefix like "## [Planned 2026-05-20] -
Implemented Combo Evaluation Documented as Deferred" to avoid temporal
inconsistency in the audit trail.


**Learning:** Both the CLI reference and the Skills guide claimed that active evaluation of multi-technology "combo" entries was deferred. However, Phase 2 of `recommend_skills` in `src/skills/suggest.rs` already implements this logic, providing specific recommendations for combinations like `react-hook-form` + `zod`.
**Action:** Before claiming a feature is "deferred" or "planned," verify the relevant logic phases in the implementation (e.g., Phase 2 evaluation loops).
2 changes: 1 addition & 1 deletion website/docs/src/content/docs/guides/skills.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,7 +183,7 @@ Recommendation metadata now comes from a hybrid catalog model:
- Providers may expose an **optional catalog overlay**. Valid provider entries extend or override matching embedded entries by stable ids.
- Invalid provider entries are ignored individually; if provider metadata is missing, unreadable, or invalid at the top level, AgentSync falls back to the embedded catalog.
- A single technology can recommend **multiple skills**. For example, the embedded catalog currently maps `astro` to `frontend-design`, `accessibility`, `performance`, `core-web-vitals`, and `seo`, and maps `github_actions` to both `github-actions` and `pinned-tag`.
- The schema also supports explicit **combo** entries (multi-technology recommendations). Those entries are loaded and preserved now, but active combo evaluation is currently deferred.
- The schema also supports explicit **combo** entries (multi-technology recommendations). Phase 2 combo evaluation is functional and used to recommend specific skills when multiple technologies (e.g., `react-hook-form` + `zod`) are detected.

### Compatibility bridge: canonical ids vs current runtime ids

Expand Down
2 changes: 1 addition & 1 deletion website/docs/src/content/docs/reference/cli.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,7 +173,7 @@ Behavior:
- Recommendations are opinionated, not exhaustive.
- The runtime loads an embedded declarative catalog first, then optionally overlays valid provider metadata.
- One detected technology may map to multiple recommended skills.
- Combo catalog entries are supported in schema and loading, but active combo evaluation is currently deferred.
- Combo catalog entries allow recommending specific skills when a combination of technologies is detected (e.g., React + shadcn/ui).
- `--install` opens an interactive selector in a TTY.
- `--install --all` is the explicit non-interactive path and installs every not-yet-installed recommendation.
- Recommendation-driven installs reuse the same install pipeline and registry updates as `skill install`, and they skip recommendations that are already installed.
Expand Down
Loading