Skip to content

docs(skills): remove dated prompt patterns from bundled skills - #367

Merged
BlackHole1 merged 1 commit into
mainfrom
docs/remove-dated-skill-prompts
Sep 24, 2026
Merged

BlackHole1 merged 1 commit into
mainfrom
docs/remove-dated-skill-prompts

Conversation

@BlackHole1

Copy link
Copy Markdown
Member

A prompt audit of the bundled skills found instructions that outlived their context. The worst one tells OpenClaw and QoderWork to replace their host id with one "from the supported list", a list that vanished when the skills moved to per-agent templates, so the model is invited to rewrite an already correct --agent value.

<!-- agentic:if agent=openclaw|qoderwork -->
If this shared skill file is running in another supported host, replace
`<!-- agentic:var agent -->` with that host id from the supported list.
<!-- agentic:endif -->

The rest is the same kind of cleanup. oo-find-skills stated its keyword rule five times, carried a circular tie-break rule and a "four options" recap that is wrong when only two options exist, and llm-client taught a hand-written JSON prompt, parse, and retry loop that oo llm json already does with schema validation. oo-powered told authors to keep boundary conditions out of the description while skill-authoring asks for them, and AGENTS.md had drifted from CLAUDE.md by missing bun run knip. The embedded-assets test now asserts the rendered --agent qoderwork instead of the removed sentence.

A prompt audit of the bundled skills turned up instructions that outlived their context. The publish skill told OpenClaw and QoderWork to swap their host id using a "supported list" that disappeared when the skills moved to per-agent templates, the find-skills skill repeated its keyword rule five times and carried circular tie-break coaching and a hardcoded "four options" that is wrong when only two exist, and _llm-client.md_ taught a hand-rolled JSON prompt, parse, and retry loop that `oo llm json` already provides.

This removes the dead instructions, states each rule once, points structured output at `oo llm json`, aligns the description guidance in _oo-powered.md_ with _skill-authoring.md_, and adds the `bun run knip` step that _AGENTS.md_ was missing relative to _CLAUDE.md_.

Signed-off-by: Kevin Cui <bh@bugs.cc>
@coderabbitai

coderabbitai Bot commented Sep 24, 2026 •

Copy link
Copy Markdown

Review in Change Stack →

Navigate logical layers of code changes, visualize relationships, and explore their blast radius.

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Essentials

Run ID: 7b4e9a06-777f-469d-9390-4ef07060af15

📥 Commits

Reviewing files that changed from the base of the PR and between 173c218 and 2c75e24.

📒 Files selected for processing (8)
  • AGENTS.md
  • contrib/skills/shared/oo-create-skill/references/oo-powered.md
  • contrib/skills/shared/oo-find-skills/SKILL.md
  • contrib/skills/shared/oo-find-skills/references/oo-cli-contract.md
  • contrib/skills/shared/oo-publish-skill/SKILL.md
  • contrib/skills/shared/oo/references/llm-client.md
  • contrib/skills/shared/oo/references/search-and-selection.md
  • src/application/commands/skills/embedded-assets.test.ts
💤 Files with no reviewable changes (1)
  • contrib/skills/shared/oo-publish-skill/SKILL.md

Included review availability: 3 reviews are currently available. Your included PR review attempts over the past 7 days set your current allowance at 5 reviews per hour.


Summary by CodeRabbit

  • Documentation
    • Updated skill-search guidance to preserve original-language terms, clarify provider selection, and retain explicit confirmation before installation.
    • Revised structured-output guidance to use the JSON command for schema validation and retries, with batch recovery focused on missing or invalid items.
    • Updated skill setup and publishing instructions, including the response guidance when an installation is declined and host-specific publishing details.

Walkthrough

Skill guidance now refers authors to the description trigger contract and directs runtime code that needs schema-valid JSON to use oo llm json. Search and installation guidance changes its keyword, ranking, and response instructions. Publishing guidance removes a host-specific replacement note, and a rendering test updates its QoderWork assertions. Development standards add bun run knip to the required post-change checks.

Priority: ⬇️ Low

Merge Risk: ⚪ Minimal · up to 2c75e

The updated guidance and checks appear consistent, and declined installations still receive one short acknowledgement before the response stops. No actionable merge risk remains beyond normal checks.

🚥 Pre-merge checks | ✅ 4
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title uses the required format, type(scope): subject, uses English, and accurately summarizes the removal of outdated prompt patterns from bundled skills.
Description check ✅ Passed The description directly explains the changes to bundled skills, structured-output guidance, agent identifiers, development checks, and tests.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
✨ Simplify code
  • Commit to this branch
  • Create a new PR

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

@BlackHole1
BlackHole1 merged commit 592f0cb into main Sep 24, 2026
7 checks passed
@BlackHole1
BlackHole1 deleted the docs/remove-dated-skill-prompts branch September 24, 2026 06:42
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