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.

73

Quality

92%

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

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.

A well-engineered operational skill: executable commands, explicit validation and error-recovery paths, and clean one-level-deep reference structure for all four phase files. The only notable improvement is consolidating the thrice-repeated fallback-to-issue instructions into a single section.

Suggestions

State the GitHub-issue fallback protocol once (e.g., keep only the 'Autonomous Mode: Fallback to Issues' section) and reference it from the other two spots to remove ~15 lines of repetition.

Consider moving the CI-safe command alternatives table into a reference file, since it is only needed in the CI environment, further slimming the always-loaded body.

DimensionReasoningScore

Conciseness

The body is dense and operational — tables, exact commands, and no padding explaining concepts Claude already knows. The main trim opportunity is redundancy: the GitHub-issue fallback protocol is spelled out three times (autonomous requirements, 'Blocker handling', and the 'Fallback to Issues' section). This fits the 4 anchor (efficient, minor over-explanation that could be trimmed) rather than 5, where every token would earn its place.

4 / 5

Actionability

Guidance is copy-paste ready throughout: exact git/gh/pnpm commands ('git tag -l \'client_v2.*\' --sort=-version:refname | head -1', 'gh pr list --repo microsoft/FluidFramework --search "release-prep/<NEXT_VERSION>"'), a CI-safe alternatives table with concrete substitutions, exact branch naming patterns, and a state-to-action decision table. Fully executable with specific examples covering the common cases.

5 / 5

Workflow Clarity

Multi-phase sequencing is explicit: a phase-selection table, a four-step auto-detection procedure, and a state→action table covering every intermediate state including overdue releases. Validation checkpoints are present (pnpm flub release prepare readiness check, release-blocking issue/PR queries, prior-progress detection before each phase, ADO pipeline verification), with an explicit error-recovery loop (stop and open a labeled GitHub issue with the remaining commands). The body routes to per-phase reference files unambiguously.

5 / 5

Progressive Disclosure

The body is an overview that delegates step detail to four real, one-level-deep reference files, each clearly signaled in the phase table ('[minor-release-prep.md](references/minor-release-prep.md)' etc.), with the schedule split into its own reference. Key context that applies across phases (remotes, version scheme, branch naming, CI-safe commands) stays inline where it belongs. Navigation is easy and nothing is nested beyond one level.

5 / 5

Total

19

/

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 capabilities, an explicit trigger clause with natural phrasings, and a clearly scoped niche. The only gaps are a couple of missing natural synonyms ('publish', 'cut a release') and trigger terms that, taken alone, are generic enough to risk overlap with other release-type skills.

Suggestions

Add one or two natural trigger synonyms users commonly say, such as 'publish the release' or 'cut a release', to broaden trigger_term_quality.

Qualify the broadest trigger terms (e.g., 'release') with context like 'Fluid Framework client' to further reduce overlap risk with other release-oriented skills.

DimensionReasoningScore

Specificity

The description lists many concrete, specific capabilities — 'minor releases, patch releases, and post-release type test updates', 'release prep, branching, version bumps, changelogs, release notes, and type test baselines', plus 'auto-detects state from the schedule and repo... falls back to a GitHub issue on failure' — comprehensive coverage with no vague filler. It matches the 5-anchor pattern of listing multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both 'what' (release prep, branching, version bumps, changelogs, release notes, type test baselines) and 'when' ('Triggers on "release", "do the release", "release status", version bump, release notes, changelog, release branch, or release engineering') with concrete trigger phrases, exactly matching the 5 anchor. It also names the niche (Fluid Framework client release group) rather than stopping at generic release language.

5 / 5

Trigger Term Quality

Trigger terms are natural and varied ('release', 'do the release', 'release status', 'version bump', 'release notes', 'changelog', 'release branch', 'release engineering'), but a few common phrasings are missing — e.g., 'publish', 'cut a release', 'ship a release'. This fits the 4 anchor (good coverage, a few natural terms missing) rather than the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'Fluid Framework client release group' carves out a clear niche and most triggers are release-specific, but broad terms like 'release', 'changelog', and 'version bump' could overlap with other release/engineering skills in adjacent repos or groups. This is the 4 anchor (mostly distinct; minor overlap risk with closely related skills), not 5, since the trigger words alone are fairly generic.

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
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.