CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fluid-release

Fluid Framework client release group — minor releases, patch releases, and post-release type test updates. Covers release prep, branching, version bumps, changelogs, release notes, and type test baselines. In autonomous mode, auto-detects state from the repo, attempts to execute, and falls back to a GitHub issue on failure. Triggers on "release", "do the release", "release status", version bump, release notes, changelog, release branch, or release engineering.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The content is a well-engineered orchestration guide: fully executable commands, a clear state-driven decision table, explicit validation checkpoints and error-recovery paths for a risky publishing workflow, and clean one-level-deep progressive disclosure into three phase references. The main weakness is redundancy — the fallback-to-issue policy and remote-selection guidance each appear multiple times and could be consolidated.

Suggestions

Consolidate the fallback-to-issue policy — currently stated in 'Autonomous Mode' requirements, 'Before Starting' blocker handling, and the 'Autonomous Mode: Fallback to Issues' section — into a single authoritative section and reference it from the other two spots.

Merge the remote-selection guidance duplicated between 'Environment Detection' (release_remote snippet) and 'Key Context' (Git remote preference bullet) into one location.

Reduce the repeated pointers to CI-safe alternatives (linked in both Environment Detection and Behavior by Mode) to a single mention.

DimensionReasoningScore

Conciseness

The body is dense with operational specifics and avoids explaining concepts Claude already knows, but the blocker/fallback-to-issue policy is stated three times (Autonomous Mode requirements, Before Starting blocker handling, and the dedicated "Autonomous Mode: Fallback to Issues" section), and remote-selection plus CI-safe-alternative pointers are duplicated between Environment Detection, Key Context, and Behavior by Mode. Mostly efficient, but the repetition could be consolidated into a single section — matching the 'could be tightened' anchor rather than the 'minor instances' level above.

3 / 5

Actionability

Guidance is fully executable throughout: copy-paste-ready commands such as `git tag -l 'client_v*' --sort=-version:refname | head -1`, `gh pr list --search "release-prep/<VERSION>" --state all`, and `pnpm -r --include-workspace-root exec npm pkg set version=<VERSION>`, plus a CI-safe alternatives table with exact replacement commands and concrete branch-name examples like `release-prep/2.90.0/4-bump-2.91.0`. This matches the anchor for copy-paste ready commands covering the common cases.

5 / 5

Workflow Clarity

The multi-phase process is clearly sequenced (environment detection → mode selection → four-step state auto-detection → state/action decision table → phase selection) with explicit validation checkpoints: the release-blocker check with a stop condition, `pnpm flub release prepare` readiness check, ADO candidate/commit/stage verification before recommending publishing, and publication verification before the patch bump. Error-recovery feedback loops are present (fallback GitHub issue with exact remaining commands, retry guidance for feed propagation), which matters for this risky batch/publishing workflow — matching the top anchor.

5 / 5

Progressive Disclosure

SKILL.md serves as a well-organized orchestration overview, and the three bundle files in references/ (minor-release-prep.md, release-execution.md, type-test-updates.md) are each clearly linked from the Workflow Selection table's Reference column and inline with anchor-specific links (e.g., type-test-updates.md#ci-resilience). References are one level deep — the reference files link only to siblings and back to SKILL.md — and the split (detection/mode logic inline, step-by-step phase detail in references) is appropriate, matching the top anchor.

5 / 5

Total

18

/

20

Passed

Description

88%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 strong description: concrete and comprehensive about capabilities, explicit about trigger conditions, and written in correct third-person voice. The only weaknesses are a handful of missing natural trigger synonyms and slightly generic single-word triggers that could overlap with other release-related skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete, comprehensive actions — "minor releases, patch releases, and post-release type test updates", "release prep, branching, version bumps, changelogs, release notes, and type test baselines", "auto-detects state from the repo... falls back to a GitHub issue on failure" — all in third person voice. Coverage spans every phase of the skill with no gaps, matching the top anchor rather than the 'minor gaps' level below.

5 / 5

Completeness

It explicitly answers both questions: the "what" enumerates concrete capabilities (release prep, branching, version bumps, changelogs, release notes, type test baselines) and the "when" is explicit with concrete trigger phrases ("Triggers on 'release', 'do the release', 'release status'..."). This matches the anchor for clearly and explicitly answering both what and when.

5 / 5

Trigger Term Quality

"Triggers on 'release', 'do the release', 'release status', version bump, release notes, changelog, release branch, or release engineering" provides good natural coverage — "do the release" is exactly what a user would say. A few natural synonyms are missing (e.g., "cut a release", "publish", "ship the release"), keeping it below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

"Fluid Framework client release group" establishes a clear niche with mostly distinct triggers, but generic terms like "release", "changelog", and "release engineering" carry minor overlap risk with other release-engineering or changelog skills. It sits between 'mostly distinct' and 'clear niche with minimal conflict risk', closer to the former due to the broad single-word triggers.

4 / 5

Total

18

/

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

microsoft/FluidFramework

Path

.github/skills/fluid-release/SKILL.md

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.