CtrlK
BlogDocsLog inGet started
Tessl Logo

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 schedule and 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.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable orchestration guide with clean one-level-deep references and explicit validation/feedback loops. The main weakness is redundancy: the autonomous fallback-to-issue and mode-behavior guidance is repeated across multiple sections and could be consolidated.

Suggestions

Consolidate the fallback-to-issue instructions, which currently appear in three near-duplicate places (autonomous requirements, blocker handling, and 'Autonomous Mode: Fallback to Issues'), into a single canonical section referenced elsewhere.

Merge the 'Mode Selection' and 'Behavior by Mode' / 'Checkpoints' coverage of interactive vs autonomous differences to avoid restating the same mode distinction twice.

Consider moving the CI-safe command alternatives table and working branch convention into a reference file to slim the overview, since they are detail-oriented rather than decision/orchestration content.

DimensionReasoningScore

Conciseness

The body is domain-specific and command-dense rather than explaining concepts Claude already knows, but the fallback-to-issue instructions are repeated essentially three times (autonomous requirements, blocker handling, and the 'Fallback to Issues' section) and mode behavior is restated across 'Mode Selection' and 'Behavior by Mode'; not a 1 because it is not padded with generic explanation, not a 3 because the redundancy could be tightened.

2 / 3

Actionability

Fully executable, copy-paste-ready commands throughout — 'git tag -l ... --sort=-version:refname | head -1', 'git ls-remote --heads upstream', 'gh pr list --repo microsoft/FluidFramework --search ...', and the CI-safe alternatives table with exact 'pnpm -r --include-workspace-root exec npm pkg set version=<VERSION>' commands; not a 2 because guidance is concrete and complete rather than pseudocode.

3 / 3

Workflow Clarity

Clear sequencing via the auto-detect Steps 1-4 and state-to-action table, with explicit validation (readiness check via 'pnpm flub release prepare client' and the release-blocking issue/PR check that halts on failure) and feedback loops (resume from prior-progress branches/PRs, fallback to issues on error); not a 2 because checkpoints and validation are explicit rather than implicit.

3 / 3

Progressive Disclosure

Four one-level-deep reference files (release-schedule, minor-release-prep, release-execution, type-test-updates), all present on disk and clearly signaled through the Workflow Selection table, with per-phase detail appropriately split out of the overview; not a 2 because references are well-signaled and shallow rather than nested or poorly organized.

3 / 3

Total

11

/

12

Passed

Description

100%

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, third-person description that concretely enumerates capabilities, provides an explicit trigger clause, and occupies a distinct niche. No weaknesses relative to the rubric anchors.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'minor releases, patch releases, and post-release type test updates' and 'release prep, branching, version bumps, changelogs, release notes, and type test baselines' — matching the 'lists multiple specific concrete actions' anchor; not a 2 because the action set is comprehensive rather than partial.

3 / 3

Completeness

Explicitly answers what ('Covers release prep, branching, version bumps, changelogs, release notes, and type test baselines') and when ('Triggers on ...') with an explicit trigger clause; not a 2 because the 'when' is stated outright, not merely implied.

3 / 3

Trigger Term Quality

'Triggers on "release", "do the release", "release status", version bump, release notes, changelog, release branch, or release engineering' gives good coverage of natural phrases a user would say; not a 2 because it spans many common variations rather than just a few keywords.

3 / 3

Distinctiveness Conflict Risk

'Fluid Framework client release group' carves a clear niche with release-engineering-specific triggers unlikely to fire for unrelated skills; not a 2 because the domain and triggers are distinct rather than merely 'somewhat specific'.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/FluidFramework
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.