Skip to content

Reframe messaging to self-improving skills, consolidate v0.2.0#24

Merged
WellDunDun merged 2 commits intodevfrom
WellDunDun/personalization-sdk
Mar 8, 2026
Merged

Reframe messaging to self-improving skills, consolidate v0.2.0#24
WellDunDun merged 2 commits intodevfrom
WellDunDun/personalization-sdk

Conversation

@WellDunDun
Copy link
Collaborator

Summary

  • Align all consumer-facing surfaces (README, llms.txt, SKILL.md, AGENTS.md, launch playbook) with "self-improving skills" narrative from the personalization strategy analysis
  • Consolidate v0.3.0 features into v0.2.0 since dev branch ships everything together
  • Add Personalization SDK vision to ROADMAP with 4-item roadmap section on consumer personalization, creator SDK, and telemetry

What Changed

  • Messaging: "skill observability" → "self-improving skills for AI agents" across 9 files
  • Version consolidation: README and CHANGELOG now reflect one v0.2.0 release with all features
  • Roadmap expansion: Added "Personalization SDK (Vision)" section with SDK contract, per-user adaptation, workflow personalization, and creator telemetry
  • npm keywords: Updated from "observability" to "self-improving"
  • Launch playbook: 10 submission one-liners updated for consistency

Ready for March 17 launch with unified messaging.

Align all consumer-facing surfaces (README, llms.txt, package.json,
SKILL.md, AGENTS.md, launch playbook, integration guide) with the
"self-improving skills" narrative from the personalization strategy
analysis. Consolidate v0.3.0 features into v0.2.0 since dev branch
ships everything together. Add Personalization SDK vision to roadmap.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@coderabbitai
Copy link

coderabbitai bot commented Mar 8, 2026

📝 Walkthrough

Summary by CodeRabbit

  • New Features

    • Announced 0.2.0 highlights: batch trigger validation, synthetic eval generation, cheap-loop evolution mode, and model-selection flags for evolve/proposals.
  • Documentation

    • Updated product messaging to emphasize self-improving skills.
    • Refreshed README, guides, playbook, and docs to reflect new framing and release notes.
    • Added planned "Personalization SDK (Vision)" entry.
  • Chores

    • Expanded platform support to include OpenClaw.
    • Updated package metadata and keywords.

Walkthrough

This PR reframes project messaging and documentation from "skill observability and continuous improvement" to "self-improving skills," updates v0.2.0 release notes and README feature ordering, expands platform mentions to include OpenClaw, and adds a Personalization SDK entry to the roadmap. Changes are documentation and metadata only.

Changes

Cohort / File(s) Summary
Release documentation
CHANGELOG.md, README.md, CHANGELOG.md
Reworked v0.2.0 Unreleased block: consolidated feature bullets (batch trigger validation, full skill-body evolution, cheap-loop mode, synthetic eval generation, per-stage model control). README "What's New" and comparison table updated to reflect "Self-improving skills + auto-rollback."
Project metadata & skill descriptors
package.json, AGENTS.md, skill/SKILL.md
Updated package description and keywords (removed "observability"; added "self-improving", "eval", "grading", "evolution", "cli", "agent", "telemetry", "bun", "typescript"). AGENTS.md and SKILL.md narrative changed to self-improving-skills framing and OpenClaw mention.
Docs, marketing, and guides
docs/integration-guide.md, docs/launch-playbook-tracker.md, llms.txt
Reworded integration and marketing copy from "skill observability CLI" to "self-improving skills CLI"; updated newsletter/conference copy and hashtags; reformatted llms.txt intro to concise bullets.

Sequence Diagram(s)

(omitted — changes are documentation/metadata only)

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Title check ⚠️ Warning The PR title does not follow conventional commits format; it lacks the required prefix (feat|fix|docs|chore|refactor|test|perf|ci). Prepend a conventional commits prefix. For example: 'docs: Reframe messaging to self-improving skills, consolidate v0.2.0' or 'chore: Reframe messaging to self-improving skills, consolidate v0.2.0'.
✅ Passed checks (2 passed)
Check name Status Explanation
Description check ✅ Passed The PR description comprehensively covers messaging reframing, version consolidation, and roadmap expansion—all directly aligned with the changeset across 9 files.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch WellDunDun/personalization-sdk

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 1

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)
package.json (1)

20-35: 🧹 Nitpick | 🔵 Trivial

Consider adding "openclaw" to keywords.

Keywords include claude-code, codex, and opencode but omit openclaw — despite OpenClaw being prominently featured as a supported platform throughout the PR (AGENTS.md, integration-guide.md, README.md).

Suggested addition
   "keywords": [
     "selftune",
     "skill",
     "self-improving",
     "claude-code",
     "codex",
     "opencode",
+    "openclaw",
     "eval",
     "grading",
     "evolution",
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@package.json` around lines 20 - 35, Update the package.json "keywords" array
to include "openclaw" so the project metadata matches documentation and
supported platforms; locate the "keywords" property in package.json and add
"openclaw" to the existing list (near entries like "claude-code", "codex",
"opencode") ensuring proper JSON syntax and commas.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@CHANGELOG.md`:
- Line 10: The changelog entry header "## [0.2.0] — 2026-03-05" is incorrect for
this PR; either change that header back to an "Unreleased" section (e.g., "##
[Unreleased]") so the notes remain pre-release, or update the date to the
intended ship date "2026-03-17" and keep the "## [0.2.0]" tag—edit the header
line in CHANGELOG.md accordingly to reflect the correct unreleased state or the
real release date.

---

Outside diff comments:
In `@package.json`:
- Around line 20-35: Update the package.json "keywords" array to include
"openclaw" so the project metadata matches documentation and supported
platforms; locate the "keywords" property in package.json and add "openclaw" to
the existing list (near entries like "claude-code", "codex", "opencode")
ensuring proper JSON syntax and commas.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 6085f4e3-c0e8-43a3-8aed-e963c1ee0f09

📥 Commits

Reviewing files that changed from the base of the PR and between d6e03fc and 2e5a851.

📒 Files selected for processing (9)
  • AGENTS.md
  • CHANGELOG.md
  • README.md
  • ROADMAP.md
  • docs/integration-guide.md
  • docs/launch-playbook-tracker.md
  • llms.txt
  • package.json
  • skill/SKILL.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

♻️ Duplicate comments (1)
CHANGELOG.md (1)

10-10: ⚠️ Potential issue | 🟠 Major

Keep 0.2.0 under Unreleased until March 17, 2026.

This PR was opened on March 8, 2026, so a dated 0.2.0 header still makes the changelog read like the release has already shipped. Either keep these notes under Unreleased until the actual cut, or merge this only when the March 17, 2026 release is published.

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@CHANGELOG.md` at line 10, The changelog header "## [0.2.0] — 2026-03-17"
incorrectly shows a dated release; change that header to keep the 0.2.0 notes
under Unreleased until the actual release (e.g., replace the line with "##
[Unreleased]" or "## [0.2.0] — Unreleased") so the entry no longer reads as
already shipped; ensure the unique header string "## [0.2.0] — 2026-03-17" is
updated and leave any associated bullet notes unchanged.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Duplicate comments:
In `@CHANGELOG.md`:
- Line 10: The changelog header "## [0.2.0] — 2026-03-17" incorrectly shows a
dated release; change that header to keep the 0.2.0 notes under Unreleased until
the actual release (e.g., replace the line with "## [Unreleased]" or "## [0.2.0]
— Unreleased") so the entry no longer reads as already shipped; ensure the
unique header string "## [0.2.0] — 2026-03-17" is updated and leave any
associated bullet notes unchanged.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 62e93b4a-d67f-4dc0-8fed-61d456e78d26

📥 Commits

Reviewing files that changed from the base of the PR and between 2e5a851 and 6611ade.

📒 Files selected for processing (1)
  • CHANGELOG.md

@WellDunDun WellDunDun merged commit 5a426b9 into dev Mar 8, 2026
5 checks passed
@WellDunDun WellDunDun deleted the WellDunDun/personalization-sdk branch March 8, 2026 11:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant