LCORE-2077: Document Agent Skills feature#1776
Conversation
Add user-facing documentation for the Agent Skills feature: - Skills guide with configuration, SKILL.md authoring, and runtime behavior - Example skills (openshift-troubleshooting with references, code-review minimal) - Example lightspeed-stack-skills.yaml config file - README updates: Agentic Capabilities table and Agent Skills config section Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (2)
WalkthroughThis PR adds comprehensive documentation and examples for Agent Skills in the Lightspeed Core Stack. It updates the main README with new sections, introduces a detailed skills guide covering configuration and authoring, provides an example configuration file, and adds two example skills with supporting reference materials. ChangesAgent Skills Feature Documentation
🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
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: 5
🤖 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 `@docs/skills_guide.md`:
- Around line 18-19: The TOC entry linking to the fragment "`#error-reference`" is
dead; either add an "Error Reference" section heading to the document that
matches that fragment (e.g., a heading such as "## Error Reference" with the
relevant content) or remove the TOC line referencing "`#error-reference`" so the
table of contents only links to existing headings; update the TOC items "-
[Error Reference](`#error-reference`)" and/or add the matching "Error Reference"
section to resolve the broken link.
- Around line 48-60: The fenced code blocks that show directory trees (the three
blocks containing the /var/skills/ tree) are missing language identifiers;
update each opening fence from ``` to ```text (or another appropriate language)
so markdownlint MD040 is satisfied — locate the directory tree blocks (the block
starting with "/var/skills/") and replace their opening backticks to include
"text" for all three occurrences.
In `@examples/skills/code-review/SKILL.md`:
- Around line 17-43: Add a blank line after each level-3 heading (the "###
Correctness", "### Security", "### Maintainability", "### Performance", and "###
Testing" headings) so that each heading is followed by an empty line before the
subsequent list items; edit SKILL.md to insert the missing newline(s)
immediately after those heading lines to satisfy markdownlint rule MD022.
In `@examples/skills/openshift-troubleshooting/SKILL.md`:
- Around line 22-24: The fenced code blocks in SKILL.md that contain shell
commands (e.g., the block showing "oc get pods -n <namespace> | grep -v Running"
and the other command blocks at lines noted) are missing a language tag; update
each triple-backtick fence to include "bash" (```bash) so markdownlint MD040 is
satisfied and rendering/linting is consistent for the command examples in
SKILL.md.
In `@README.md`:
- Around line 205-213: Update the Capability table entry for "Agent Skills" to
reflect that it is now available (change "Upcoming (Q2)" to "Supported" or
similar live-status) so it matches the active configuration and usage documented
later (the "Agent Skills" section and the referenced "[Agent Skills
Guide](docs/skills_guide.md)"); ensure the wording and status string you use
exactly matches other table entries (e.g., "Supported") and update any adjacent
description text if needed to avoid contradiction.
🪄 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: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: fdfa7bd2-3d28-4406-9c97-6099c2cd130e
📒 Files selected for processing (6)
README.mddocs/skills_guide.mdexamples/lightspeed-stack-skills.yamlexamples/skills/code-review/SKILL.mdexamples/skills/openshift-troubleshooting/SKILL.mdexamples/skills/openshift-troubleshooting/references/common-errors.md
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (12)
- GitHub Check: Konflux kflux-prd-rh02 / lightspeed-stack-on-pull-request
- GitHub Check: E2E: server mode / ci / group 1
- GitHub Check: E2E: library mode / ci / group 2
- GitHub Check: E2E: library mode / ci / group 1
- GitHub Check: E2E: server mode / ci / group 2
- GitHub Check: E2E: server mode / ci / group 3
- GitHub Check: build-pr
- GitHub Check: E2E: library mode / ci / group 3
- GitHub Check: unit_tests (3.13)
- GitHub Check: unit_tests (3.12)
- GitHub Check: E2E Tests for Lightspeed Evaluation job
- GitHub Check: Pylinter
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2026-05-20T08:09:30.641Z
Learnt from: max-svistunov
Repo: lightspeed-core/lightspeed-stack PR: 1580
File: docs/design/llama-stack-config-merge/poc-results/library-mode/synthesized-run.yaml:107-110
Timestamp: 2026-05-20T08:09:30.641Z
Learning: In Llama-stack config YAMLs, when defining a Llama Guard safety shield entry, set `provider_shield_id` to the *guard model identifier* (e.g., `meta-llama/Llama-Guard-3-8B`). Do not use a chat/generative model id (e.g., `openai/gpt-4o-mini`): a chat-model id (or `native_override`) indicates only an override landed and does **not** mean the safety shield is actually gating queries. Ensure any E2E coverage for the related implementation (JIRA/E2E tests) exercises a real Llama Guard model to verify that the shield is effective.
Applied to files:
examples/lightspeed-stack-skills.yaml
🪛 LanguageTool
examples/skills/code-review/SKILL.md
[style] ~26-~26: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...ameterized (no string concatenation)? - Are file paths validated to prevent directo...
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
[style] ~50-~50: Consider using a different verb for a more formal wording.
Context: ... 3. Issues: Problems that should be fixed, ordered by severity - Critical:...
(FIX_RESOLVE)
README.md
[style] ~745-~745: The phrase ‘do not have the ability to’ might be wordy. Consider using “can't”.
Context: ...uct teams at deployment time. End users do not have the ability to add skills. For the full configuration...
(HAS_THE_ABILITY_TO)
docs/skills_guide.md
[style] ~30-~30: The phrase ‘do not have the ability to’ might be wordy. Consider using “can't”.
Context: ...nt time**. End users of LS app products do not have the ability to add skills, similar to how they cannot ...
(HAS_THE_ABILITY_TO)
🪛 markdownlint-cli2 (0.22.1)
examples/skills/code-review/SKILL.md
[warning] 17-17: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 22-22: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 28-28: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 34-34: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 39-39: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
examples/skills/openshift-troubleshooting/SKILL.md
[warning] 22-22: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 28-28: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 40-40: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 48-48: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 55-55: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
docs/skills_guide.md
[warning] 18-18: Link fragments should be valid
(MD051, link-fragments)
[warning] 48-48: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 82-82: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 216-216: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🔇 Additional comments (2)
examples/lightspeed-stack-skills.yaml (1)
1-33: LGTM!examples/skills/openshift-troubleshooting/references/common-errors.md (1)
1-60: LGTM!
|
Added small section in README for agentic capabilities, PTAL |
Add upcoming notices to README and skills guide since the feature is not yet implemented. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
jrobertboos
left a comment
jrobertboos
left a comment
There was a problem hiding this comment.
Overall LGTM, however I would remove the Q2 tag from HITL as I am not sure that we are going to fully deliver that this quarter :). You can probably just leave it as "Upcoming".
| | RAG | Supported | Retrieval-Augmented Generation with vector stores ([RAG Guide](docs/rag_guide.md)) | | ||
| | A2A Protocol (Client) | Supported | Agent-to-Agent communication as client ([A2A Protocol](docs/a2a_protocol.md)) | | ||
| | Conversation History | Supported | Persistent conversation context across requests | | ||
| | Human-in-the-Loop | Upcoming (Q2) | Interactive approval or confirmation steps | |
There was a problem hiding this comment.
I am not sure that this is actually planned for Q2
4 participants
Description
Add user-facing documentation for the Agent Skills feature (LCORE-1339), based on the design spec at
docs/design/agent-skills/agent-skills.md.docs/skills_guide.md— Configuration guide, SKILL.md authoring reference, runtime behavior, limitations, and error referenceexamples/skills/openshift-troubleshooting/— Example skill withreferences/subdirectory demonstrating the reference file patternexamples/skills/code-review/— Minimal single-file example skillexamples/lightspeed-stack-skills.yaml— Example config showing skills configuration with both directory and individual path optionsREADME.md— Added Agentic Capabilities table (MCP Tools, RAG, Safety Shields, A2A, Conversation History, and upcoming features) and Agent Skills configuration sectionType of change
Tools used to create PR
Related Tickets & Documents
Checklist before requesting a review
Testing
🤖 Generated with Claude Code
Summary by CodeRabbit
Release Notes