CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release

Release context-mode v2 from the v2 branch. Runs the checks and the live test, shows the next version and notes, then starts the release workflow and watches it.

Quality

81%

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

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.

The body is an exemplary release runbook: fully executable commands, explicit stop conditions and validation at every step, a clearly defined skip-live variant, and an explicit list of out-of-scope one-time actions. The only weakness is hardcoded volatile values (test count, model name/version) inline, which will age and slightly bloat the token budget.

DimensionReasoningScore

Conciseness

The body is uniformly imperative with no concept explanations Claude already knows, but it hardcodes time-sensitive values inline ("the 131 tracked tests", "Sonnet 5, effort low", "v2") that will go stale and are not placed in a deprecated/old-patterns section, plus a few meta-sentences that could be trimmed. Fits anchor 4 ('efficient; minor instances that could be trimmed') better than 5.

4 / 5

Actionability

Every step carries a copy-paste-ready command (`git status --porcelain`, `node e2e/live/run.mjs --all`, `gh workflow run release.yml --ref v2 -f sha=$(git rev-parse HEAD)`, `gh run watch`), and the skip-live variant includes the exact command variant and its expected notes line. Fully executable and covers the common cases.

5 / 5

Workflow Clarity

Eight clearly sequenced steps each with explicit validation and stop conditions ("The branch must be `v2` and the tree must be clean", "If a row is `FAIL`, stop", "refuse to continue" at the skip limit), plus a defined error policy ("Stop and report at the first step that fails; do not retry"). The destructive/batch cap does not apply since validation checkpoints are present throughout.

5 / 5

Progressive Disclosure

A self-contained runbook under 50 lines with no need for external references, organized as numbered steps plus clearly separated variant (`skip-live`) and exclusions sections. Per the rubric's simple-skill note, this scores 5 with just well-organized sections; no bundle files exist to reference.

5 / 5

Total

19

/

20

Passed

Description

62%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.

The description is specific to its project and clearly states what the skill does with several concrete actions, but it lacks any explicit 'when to use' guidance and has thin natural-language trigger coverage. Even accounting for disable-model-invocation (user-invoked only), an explicit use-when clause and trigger synonyms would strengthen it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the owner asks to release, ship, or cut a release of context-mode v2 from the v2 branch."

Include natural trigger synonyms users would actually say ("release", "ship", "publish", "cut a release") alongside the technical terms.

Replace the generic phrase "Runs the checks" with the named checks (e.g. "runs the E2E cases and the KEEP-PASS unit tests") to close the specificity gap.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Runs the checks and the live test, shows the next version and notes, then starts the release workflow and watches it") but "the checks" is generic and coverage omits the streak tracking, migration checkpoint, and skip-live behavior. Not 5 because coverage is not comprehensive; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

The 'what' is clear (release v2, run checks and live test, show version/notes, start and watch the workflow), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"Release", "v2", "live test", and "release workflow" are relevant keywords a user might say, but common variations such as "ship", "publish", or "cut a release" are missing. Not 4 because keyword coverage is thinner than 'good with a few missing'.

3 / 5

Distinctiveness Conflict Risk

"Release context-mode v2 from the v2 branch" names a specific project, version, and branch, giving it a clear niche with minimal conflict risk against other skills. Anchors below (4, 'minor overlap risk') fit less well since the project-specific scoping leaves almost no overlap.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing, 2 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

mksglu/context-mode

Path

.claude/skills/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.