CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flux-controller-patch-releases

Run the upstream Flux controller patch release procedure for helm-controller, image-automation-controller, image-reflector-controller, kustomize-controller, notification-controller, source-controller, and source-watcher. Use when preparing a new controller patch release from a release series branch, drafting changelog entries, tagging releases, and opening the follow-up changelog PRs back to main.

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

88%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 exceptionally actionable, well-sequenced operational skill: exact commands for every step, explicit validation checkpoints and error-recovery paths for the risky operations (tagging, amending, cherry-picking), and no filler. The two weaker spots are the duplication between the Important rules and Critical Checks sections and the absence of any file split for the detailed changelog/dependency guidance.

Suggestions

Consolidate the duplicated rules: state each fetch/pull/approval constraint once (either in Important rules or Critical Checks, not both) and merge the two 'cannot approve your own PRs' statements into the approval-watch bullet, trimming roughly 15 lines without losing any constraint.

Move the 'How To Build The Changelog Entry' and 'Dependency update PRs' sections (~90 lines of detail) into a references/ file (e.g. references/changelog.md) linked from a short inline summary, so SKILL.md stays a lean overview of the release flow while the changelog-depth material is loaded only when drafting entries.

DimensionReasoningScore

Conciseness

The body is dense, purely operational, and explains nothing Claude already knows, but it carries real redundancy: "You cannot approve your own PRs" is stated twice (in the approval-watch bullet and again as its own rule), and the Critical Checks section restates fetch/pull rules already given in Preconditions and Release Flow steps 1 and 8. This fits anchor 4 (efficient, minor instances that could be trimmed) rather than 3, since there is no padded explanation, and not 5 because the duplication could be consolidated.

4 / 5

Actionability

Fully executable throughout: the controller-detection loop is copy-paste ready shell (for-each-ref, rev-list --count), and every step has exact commands (`git switch -c release-vX.Y.Z release/vX.Y.x`, `git tag -s -m "vX.Y.Z"`, `gh pr merge <num> -R fluxcd/<repo> --merge`, the approval-watch while loop, the GraphQL reviewThreads query). Matches the anchor-5 copy-paste-ready standard.

5 / 5

Workflow Clarity

The eleven-step flow is clearly sequenced with explicit validation checkpoints and error recovery: confirm tags against GitHub before starting, wait for CI green and approval before merging, `gh run watch --exit-status` on the release workflow, confirm the branch before cherry-picking (with the failure mode of landing on main spelled out), and a `git diff --stat` check that the version bump survived an amend. This matches anchor 5 including feedback loops for the destructive/batch operations (tag pushes, force-pushes, merges).

5 / 5

Progressive Disclosure

The single 340-line file is well organized with clear sections (Important rules, Release Flow, Changelog Entry, Critical Checks) and no nested or buried references, and the bundle has no separate files to navigate. However, everything is inline at 7x the simple-skill size — the ~90 lines of changelog-building and dependency-update guidance are detailed material that could live in a reference file — so it fits anchor 4 (good structure, minor organization gaps) rather than 5, while being clearly above anchor 3's poorly-organized examples.

4 / 5

Total

18

/

20

Passed

Description

92%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: third-person, concrete, and comprehensive, with an explicit "Use when" clause covering the real trigger scenarios (patch release preparation, changelog drafting, tagging, follow-up PRs). The only weakness is modest synonym coverage of natural trigger phrases.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "preparing a new controller patch release from a release series branch", "drafting changelog entries", "tagging releases", "opening the follow-up changelog PRs back to main" — and enumerates all seven target controllers, giving comprehensive coverage of the procedure's user-facing actions with no meaningful gaps, matching the score-5 anchor.

5 / 5

Completeness

It explicitly answers both questions: the "what" ("Run the upstream Flux controller patch release procedure" for the named controllers) and a concrete "Use when preparing a new controller patch release..., drafting changelog entries, tagging releases, and opening the follow-up changelog PRs" trigger clause, matching anchor 5.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("patch release", "changelog entries", "tagging releases", "release series branch", plus all seven controller names users would name directly), but it lacks common synonyms such as "cut a release" or "release notes", so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5, and is clearly above anchor 3.

4 / 5

Distinctiveness Conflict Risk

A clear niche — upstream Flux controller patch releases for seven explicitly named fluxcd repos — with distinct triggers that no generic release/changelog skill would match; conflict risk is minimal, matching anchor 5.

5 / 5

Total

19

/

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

fluxcd/agent-skills

Path

internal/skills/flux-controller-patch-releases/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.