Skip to content

feat: agl-skill - #534

Open
dalongbao wants to merge 2 commits into
microsoft:mainfrom
dalongbao:feature/agl-optimizer-skill-recipe
Open

feat: agl-skill#534
dalongbao wants to merge 2 commits into
microsoft:mainfrom
dalongbao:feature/agl-optimizer-skill-recipe

Conversation

@dalongbao

Copy link
Copy Markdown

No description provided.

Copilot AI review requested due to automatic review settings July 30, 2026 21:21

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Pull request overview

This PR adds an installable Agent Skills package (agl-optimizer) to the repository, along with a skills catalog README, so compatible agents can discover and load the skill via the Agent Skills format.

Changes:

  • Added skills/agl-optimizer/SKILL.md defining the agl-optimizer skill (metadata + optimization guidance, action space, and boundaries).
  • Added skills/README.md documenting the skill, installation options, and published evaluation context/results.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File Description
skills/README.md Introduces the skills catalog, installation instructions, and benchmark/result context for agl-optimizer.
skills/agl-optimizer/SKILL.md Adds the Agent Skills spec file (frontmatter + content) for the agl-optimizer skill.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread skills/agl-optimizer/SKILL.md Outdated
@@ -0,0 +1,90 @@
---
name: agl-optimizer

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

should be agl

Comment thread skills/README.md Outdated

Our evaluation uses a different protocol: Claude Code, Codex, and Copilot act as agentic optimizers that can edit the whole agent. Results are held-out test means pooled across \$5, \$10, and \$25 budgets (`n = 9`) and are shown as mean ± standard deviation. Higher is better; bold marks the better mean within each row.

| Benchmark (train/test) | Optimizer | agl-skill v9.7 (%) | No-skill control (%) | Change (pp) |

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

don't put 9.7 here

Comment thread skills/README.md Outdated
Our evaluation uses a different protocol: Claude Code, Codex, and Copilot act as agentic optimizers that can edit the whole agent. Results are held-out test means pooled across \$5, \$10, and \$25 budgets (`n = 9`) and are shown as mean ± standard deviation. Higher is better; bold marks the better mean within each row.

| Benchmark (train/test) | Optimizer | agl-skill v9.7 (%) | No-skill control (%) | Change (pp) |
| :--- | :--- | ---: | ---: | ---: |

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

line chart

Comment thread skills/README.md Outdated
| ALFWorld (3553/134) | Claude Code | **89.1** ± 26.4 | 88.2 ± 33.1 | +0.9 |
| ALFWorld (3553/134) | Codex | 97.5 ± 4.7 | **97.8** ± 5.9 | −0.3 |
| ALFWorld (3553/134) | Copilot | 97.5 ± 7.2 | **99.9** ± 0.3 | −2.4 |

@ultmaster ultmaster Jul 31, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

columns:
accuracy cost

rows:
before optimizer
claude code w/ skill
codex w/ skill
copilot w/ skill

Comment thread skills/README.md Outdated
| ALFWorld (3553/134) | Codex | 97.5 ± 4.7 | **97.8** ± 5.9 | −0.3 |
| ALFWorld (3553/134) | Copilot | 97.5 ± 7.2 | **99.9** ± 0.3 | −2.4 |

Because the two tables use different protocols and data splits, compare results within a table, not across tables. Full per-budget scores, cost breakdowns, and caveats are available in [RESULTS_V9_7.md](https://github.com/agent-lightning/agl-skill/blob/verifier-v8/RESULTS_V9_7.md).

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

don't put links here. it won't be publicly accessible

Comment thread skills/agl/SKILL.md
@dalongbao

Copy link
Copy Markdown
Author

@microsoft-github-policy-service agree company="Microsoft"

@dalongbao
dalongbao requested a review from ultmaster July 31, 2026 13:51
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.

3 participants