CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-release-manager

Agent skill for release-manager - invoke with $agent-release-manager

49

2.51x
Quality

28%

Does it follow best practices?

Impact

78%

2.51x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-release-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body is a thorough, well-sectioned release-management reference with concrete tool-call examples, but it is held to mid-range scores by verbosity (including a duplicate frontmatter block), non-executable placeholder path syntax, absent validate->retry feedback loops, and a total lack of progressive file splitting. It is competent but not lean or rigorously workflow-safe.

Suggestions

Delete the duplicate YAML frontmatter block (the second ---...--- section) and trim the generated PR-body/changelog templates to concise templates or move them to a reference file.

Fix path syntax so examples are executable: replace '$' separators with '/' and resolve ':owner/:repo' placeholders to concrete values or clearly marked variables.

Add an explicit validation feedback loop to the release pipeline (run tests/lint/build; if any fail, fix and re-run before proceeding to PR creation).

Split detailed material (full code pipelines, CI/CD workflow, strategies) into files under references/ and link to them from a concise SKILL.md overview to enable progressive disclosure.

DimensionReasoningScore

Conciseness

The ~370-line body has substantial concrete content but is padded with a stray duplicate YAML frontmatter block, a verbose generated PR-body template, and changelog boilerplate; it is mostly actionable but could be tightened considerably, so it does not reach the lean score-3 anchor.

2 / 3

Actionability

It provides concrete MCP/Bash/gh calls, but examples are not copy-paste ready: paths use '$' as separators (e.g. 'release$v1.0.72', '$workspaces$ruv-FANN$...') and ':owner/:repo' placeholders are unresolved, fitting the 'concrete but incomplete / missing key details' anchor.

2 / 3

Workflow Clarity

The Batch Release Workflow is sequenced (swarm init, branch, clone, write, commit, validate, PR, track), but it chains validation with && and lacks an explicit validate->fix->retry feedback loop; per the rubric, missing feedback loops in destructive/batch release operations caps this at 2.

2 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the body is a single ~370-line monolith with clear section headers but everything inline; it has structure, yet content that should be split (detailed examples, CI/CD config, strategies) is not separated, matching the score-2 anchor.

2 / 3

Total

8

/

12

Passed

Description

7%

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

The frontmatter description is a bare label-plus-invocation-token that conveys almost no capability or usage guidance, scoring at the bottom of the rubric on specificity, triggers, and completeness. It is saved from a total minimum only by the inherent distinctiveness of the release-management niche.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Coordinates multi-package releases, bumps versions, runs test/lint/build validation, creates release PRs, and manages rollbacks'.

Add an explicit trigger clause such as 'Use when the user asks to cut a release, coordinate versions across packages, or prepare a release pull request'.

Replace the '$agent-release-manager' invocation token with natural user-facing keywords ('release', 'version bump', 'deploy', 'changelog') so it triggers on real phrasing.

Remove the duplicate second YAML frontmatter block in the body so the canonical description is the only one and is unambiguous.

DimensionReasoningScore

Specificity

The description only states 'Agent skill for release-manager' and an invocation hint; it names no concrete actions (e.g. coordinate versions, run validation, deploy, roll back), matching the vague/abstract anchor rather than the score-2 'names domain and some actions'.

1 / 3

Completeness

It fails to clearly answer either 'what does this do' (no real capability described) or 'when should Claude use it' (no 'Use when...' clause or equivalent trigger), so both what and when are missing/very weak.

1 / 3

Trigger Term Quality

The only trigger-like phrase is the technical invocation token '$agent-release-manager', which is not a natural keyword a user would say, rather than natural terms like 'release', 'deploy', or 'version bump'.

1 / 3

Distinctiveness Conflict Risk

'release-manager' denotes a relatively distinct niche unlikely to conflict broadly, but the description is too thin to establish clear distinguishing triggers, so it sits at 'somewhat specific but could overlap'.

2 / 3

Total

5

/

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
ruvnet/ruflo
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.