CtrlK
BlogDocsLog inGet started
Tessl Logo

rstudio-update-copilot

Use when updating the copilot-language-server version in the RStudio repository, e.g. bumping to a new release. This skill is for macOS and Linux only.

88

1.35x
Quality

83%

Does it follow best practices?

Impact

100%

1.35x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary instruction skill: copy-paste-ready commands, per-file syntax variants handled explicitly, and validation checkpoints with stop conditions at every risky stage. The only improvement is trimming a few lines that explain shell behavior Claude already knows.

DimensionReasoningScore

Conciseness

The body is efficient — every step is a command or a precise edit instruction, and the rationale given (why the branch must be 'main', why credentials are checked before editing, why a temp dir avoids sudo) is non-obvious project context rather than concepts Claude already knows. A few lines trim Claude-competent explanation (e.g. "The `trap` ensures the temp directory is cleaned up whether the install succeeds or fails"), keeping it at anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Guidance is fully executable: exact bash commands with the `<VERSION>` placeholder, the precise per-file syntax for all four files (including the Windows batch no-quotes variant), the exact branch/commit/PR strings, and a runnable verification snippet with mktemp and trap. This matches anchor 5 ('copy-paste ready commands; specific examples cover the common cases') with no gaps.

5 / 5

Workflow Clarity

Eight clearly sequenced steps with explicit validation checkpoints throughout: stop if branch is not main, validate the version format, prerequisite checks with per-failure remediation (install aws/wget, configure credentials), 'verify all four files contain the new version string', confirm exit code 0 and the 'Successfully uploaded' message, and confirm the install exit code. This is a batch edit of four files with an inline verification pass, matching anchor 5's 'explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

The skill is a single self-contained file with no bundle directories and no content that belongs in separate files — the ~110 lines are all essential instructions, organized under numbered section headings (Arguments, Steps 1-8, per-file subsections) that make navigation trivial. For a self-contained skill whose content is appropriately placed inline with nothing to split out, this matches the well-organized-structure condition for a top score; it is not anchor 4 because there are no organization gaps or buried references.

5 / 5

Total

19

/

20

Passed

Description

73%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-scoped, distinctive description with an explicit 'Use when' trigger and natural phrasing, weakened mainly by underselling what the skill actually does. Enumerating the full scope (update version strings, upload to S3, verify, open PR) would lift both completeness and specificity toward the top anchors.

Suggestions

Enumerate the concrete actions in the 'what' clause, e.g. "Updates the pinned copilot-language-server version across four files, uploads the release to S3, verifies the install, and opens a PR" — this would raise specificity from 3 toward 5.

Add trigger synonyms users might say, such as "upgrade copilot-language-server" or "bump the copilot version", to broaden natural-term coverage toward anchor 5.

Fold the platform constraint into the trigger clause ("Use when updating ... on macOS or Linux") so the 'when' guidance carries the boundary too.

DimensionReasoningScore

Specificity

The description names one concrete action — "updating the copilot-language-server version in the RStudio repository" — with the clarification "e.g. bumping to a new release", but omits the other concrete actions the skill performs (uploading to S3, verifying the install, opening a PR). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive'); it is not anchor 4 because several specific actions are missing, and not anchor 2 because a real concrete action is named rather than generic handling.

3 / 5

Completeness

Both parts are present: the 'what' ("updating the copilot-language-server version in the RStudio repository") and an explicit 'when' ("Use when updating the copilot-language-server version ... e.g. bumping to a new release"). It is not anchor 5 because the 'what' is thin — it does not convey the upload/verify/PR scope — while the platform boundary ("for macOS and Linux only") adds useful but partial specificity beyond a full trigger enumeration.

4 / 5

Trigger Term Quality

Natural phrases a user would say are present — "update ... copilot-language-server version", "bumping to a new release", "RStudio repository" — giving good keyword coverage. It falls short of anchor 5 because common synonyms and variations are missing (e.g. "upgrade copilot", "GitHub Copilot", "copilot server"), but exceeds anchor 3 because the included terms are natural and directly relevant rather than merely adequate.

4 / 5

Distinctiveness Conflict Risk

This is a clear niche with distinct triggers: the exact product name "copilot-language-server" plus "the RStudio repository" makes triggering for the wrong skill extremely unlikely, and the "macOS and Linux only" boundary further disambiguates. It matches anchor 5 cleanly; no neighboring anchor fits better since it is more specific than the anchor-4 example ('works with PDF and Word document files').

5 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rstudio/rstudio
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.